US Pat. No. 9,918,690

SYNTHETIC DATA-DRIVEN HEMODYNAMIC DETERMINATION IN MEDICAL IMAGING

Siemens Healthcare GmbH, ...

18. A method for hemodynamic determination in medical imaging, the method comprising:
generating a plurality of examples of anatomical arrangements not representing any particular patient with computer modeling
in silico, physical modeling in vitro, or both computer modeling in silico and physical modeling in vitro;

storing a value for a flow characteristic for each of the examples of the anatomical arrangements; and
training, with machine learning, using the stored value for the flow characteristic for each of the examples of the anatomical
arrangements, a classifier for predicting the flow characteristics for different anatomical arrangements.

US Pat. No. 9,375,184

SYSTEM AND METHOD FOR PREDICTION OF RESPIRATORY MOTION FROM 3D THORACIC IMAGES

Siemens Corporation, Ise...

1. A method for predicting respiratory motion of a patient, comprising:
generating a patient-specific anatomical model of the respiratory system from a 3D thoracic image of the patient;
deforming the patient-specific anatomical model of the respiratory system using a biomechanical model;
personalizing the biomechanical model for the patient by estimating a patient-specific thoracic pressure force field to drive
the biomechanical model; and

predicting respiratory motion of the patient using the personalized biomechanical model driven by the patient-specific thoracic
pressure force field,

wherein the patient-specific anatomical model includes at least one lung region, a thorax region, and a sub-diaphragm region,
and generating the patient-specific anatomical model of the respiratory system from the 3D thoracic image of the patient comprises:

segmenting the at least one lung region, the thorax region, and the sub-diaphragm region in the 3D thoracic image;
generating a respective mesh for each of the segmented at least one lung region, thorax region, and sub-diaphragm region;
and

defining a plurality of pressure zones on the meshes for the thorax region and the sub-diaphragm region.

US Pat. No. 9,423,478

MAGNETIC SHIELD FOR MR MAGNET

SIEMENS HEALTHCARE GMBH, ...

1. A magnetic shield for a field magnet of a magnetic resonance system with active shielding, comprising:
a hollow body which extends along an axis and is designed to accommodate the field magnet; and
a wall including a first area, a second area, and a third area which are disposed along the axis,
wherein the second area separates the first area and the third area from one another, and
wherein the second area has a smaller wall thickness than the first area and the third area and an inner surface of the second
area facing towards the inside of the hollow body is recessed in relation to the inner surfaces of the first area and of the
third area facing towards the inside of the hollow body.

US Pat. No. 9,468,395

MEDICAL UNIT AND METHOD FOR IMPROVING EXAMINATION AND TREATMENT WORKFLOWS

SIEMENS HEALTHCARE GMBH, ...

1. A medical unit, comprising:
a medical device;
a 3D radar array that detects positional data of an object in an examination space of the medical device;
a processing unit that monitors a movement of the object based on the detected data;
a control unit that controls the medical device based on the monitored movement of the object; and
a post-processing unit that post-processes medical data acquired by the medical device, wherein the post-processing comprises
of correcting movement artifacts based on the monitored movement of the object.

US Pat. No. 9,967,970

CIRCUIT ARRANGEMENT FOR REDUCING THE MAXIMUM ELECTRICAL FIELD STRENGTH, HIGH VOLTAGE GENERATION UNIT WITH SUCH A CIRCUIT ARRANGEMENT AND X-RAY GENERATOR WITH SUCH A HIGH VOLTAGE GENERATION UNIT

Siemens Healthcare GmbH, ...

1. A circuit arrangement comprising:electronic first components arranged on a circuit board and lying at high-voltage potential; and
functionless, electronic second components lying at high-voltage potential,
wherein the electronic second components are arranged on the circuit board adjacent to the electronic first components, and
wherein the electronic second components are configured to reduce a maximum electrical field strength between the electronic first components and a reference potential and/or between pads of the circuit board and the reference potential.

US Pat. No. 9,555,263

APPARATUS, SYSTEM AND METHOD FOR SUPPORTING A BRACHYTHERAPY

SIEMENS HEALTHCARE GmbH, ...

1. A method for supporting a brachytherapy comprising steps of:
introducing at least one radiation means and at least one dose measuring means into a target area of an object under treatment
including at least one target object;

measuring a value of a radioactive radiation originating from the at least one radiation means using the at least one dose
measuring means;

transmitting the measured value to a processing unit;
receiving an image obtained from an image apparatus by the processing unit, wherein the image includes the at least one radiation
means introduced into the target area, the at least one dose measuring means introduced into the target area, and the at least
one target object;

determining a position of the at least one radiation means introduced into the target area, a position of the at least one
dose measuring means introduced into the target area, and a position of the at least one target object from the received image;

determining a local distribution of a radiation dose of the at least one radiation means from the measured value, wherein
the local distribution is determined on the determined position of the at least one radiation means and the determined position
of the at least one dose measuring means that are introduced into the determined position of the target area;

comparing the determined local distribution of the radiation dose of the at least one radiation means with a predeterminable
local distribution;

outputting a warning signal if the determined local distribution exceeds the predeterminable local distribution;
checking whether an abort criterion is fulfilled; and
repeating the steps from the measurement of the value of the radioactive radiation until the abort criterion is fulfilled.

US Pat. No. 9,519,039

DETERMINING THE FORM OF RF PULSES FOR SELECTIVE EXCITATION IN MAGNETIC RESONANCE IMAGING

Siemens Healthcare GmbH, ...

1. A magnetic resonance method involving the generation of high-frequency pulses and magnetic gradients (gx, gy, gz) for the selective excitation of an object that is to be examined, whereby the magnetic resonance method comprises the following
steps:
providing a transversal magnetization m(r, T) which is described by
wherein i stands for an imaginary unit, ? stands for a gyromagnetic ratio, m0 stands for an equilibrium magnetization, t stands for a time, r; stands for a position vector and T stands for a duration of a pulse, T2 stands for a transversal relaxation time, ?s stands for a shift of the resonance frequency, b1(t) stands for a high-frequency pulse, and k(t) stands for a vector of the k-space trajectory that is given by the magnetic gradients,
determining the high-frequency pulse by means of a signal equation s(t) according to:
wherein V stands for a volume that is to be examined, so that, except for factors, the high-frequency pulse is obtained as:
wherein J(t) is a Jacobi determinant that, under the premise of the bijectivity of k(t) onto a value range of t, yields the
dependence of the coordinate transformation between the time parameterization and the k-space parameterization,
using the high-frequency pulse to excite the volume that is to be examined,
detecting the measured signal generated by the high-frequency pulse in the volume that is to be examined, and
evaluating the measured signal.

US Pat. No. 9,471,987

AUTOMATIC PLANNING FOR MEDICAL IMAGING

Siemens Healthcare GmbH, ...

1. A non-transitory computer-readable medium embodying a program of instructions executable by machine to perform steps for
medical imaging planning, the steps comprising:
(i) learning hierarchical detectors based on training image data;
(ii) detecting reference anatomical primitives in first image data of a subject by applying the learned hierarchical detectors;
(iii) deriving one or more imaging parameters based on a geometric model, wherein the geometric model defines a geometric
relationship between at least one of the detected reference anatomical primitives and the one or more imaging parameters;
and

(iv) presenting, via a user interface, the one or more imaging parameters for use in acquisition, reconstruction or processing
of second image data of the subject.

US Pat. No. 9,938,458

CERAMIC SCINTILLATOR FIBER

SIEMENS HEALTHCARE GMBH, ...

1. A method for production of a scintillator fiber, comprising:provisioning a suspension of a binder dissolved in a solvent and a scintillator material; and
pressing the suspension into a precipitation bath in which the binder is insoluble.

US Pat. No. 9,508,157

RECONSTRUCTION OF ANEURYSM WALL MOTION

Siemens Medical Solutions...

1. A system for image-based reconstruction, comprising:
an electrocardiogram monitor that acquires electrocardiogram signal data from a patient; and
a computer system communicatively coupled to the electrocardiogram monitor, wherein the computer system includes
a non-transitory memory device for storing computer readable program code, and
a processor device in communication with the memory device, the processor being operative with the computer readable program
code to perform steps including

sorting three-dimensional projection image data of an aneurysm wall in a vascular structure of interest of the patient into
phase-binned image data according to phases of the electrocardiogram signal data,

reconstructing, based on the phase-binned image data, three-dimensional layouts of the aneurysm wall in the vascular structure
of interest by

reconstructing an average three-dimensional image of the aneurysm wall by using the phase-binned image data, and
for at least one of the phases, minimizing a difference between the average three-dimensional image and the phase-binned image
data correlated to the phase to generate at least one of the three-dimensional layouts associated with the phase, and

determining motion of the aneurysm wall between the phases based on the reconstructed three-dimensional layouts.

US Pat. No. 10,054,656

METHOD AND APPARATUS THAT ACQUIRE MAGNETIC RESONANCE DATA USING A 3D TURBO OR FAST SPIN ECHO PULSE SEQUENCE WITH A LENGTHENED ECHO SPACING

Siemens Healthcare GmbH, ...

1. A method of acquiring magnetic resonance (MR) data from a subject, comprising:with a computer, accessing or generating a modified form of a standard 3D turbo or fast spin echo (3D-TSE/FSE) imaging protocol, with said standard 3D-TSE/FSE imaging protocol comprising at least one echo spacing following a radiation of an excitation radio-frequency (RF) pulse, wherein a length of said at least one echo spacing in said standard 3D-TSE/FSE imaging protocol is determined by the radiation of a number of refocusing RF pulses, via an RF channel that comprises an RF amplifier, and a subsequent readout of an echo produced by nuclear spins excited by the radiated excitation RF pulse which have also been refocused by each refocusing RF pulse in said standard 3D-TSE/FSE imaging protocol;
from said computer, operating said MR data acquisition unit with a reduced loading of said RF amplifier, where the reduced loading of the RF amplifier is produced by modifying said at least one echo spacing of the standard 3D-TSE/FSE imaging protocol in order to lengthen the length of the at least one echo spacing to more than 500 ms, while also radiating a modified number of refocusing RF pulses that is less than the number of said refocusing RF pulses that occur in said standard 3D-TSE/FSE imaging protocol, and said MR data acquisition unit thereby acquiring raw MR data that is or has been read out from said echo; and
in said computer, executing an image reconstruction algorithm in order to convert said acquired raw MR data into MR image data representing an image of the subject, and making the MR image data that represents the image of the subject available in electronic form at an output of said computer.

US Pat. No. 9,761,014

SYSTEM AND METHOD FOR REGISTERING PRE-OPERATIVE AND INTRA-OPERATIVE IMAGES USING BIOMECHANICAL MODEL SIMULATIONS

Siemens Healthcare GmbH, ...

1. A method for registering a pre-operative image of a patient to an intra-operative image of the patient, comprising:
generating an initially registered pre-operative image by estimating deformations of one or more segmented anatomical structures
in the pre-operative image using biomechanical gas insufflation model constrained registration with the intra-operative image;
and

refining the initially registered pre-operative image using diffeomorphic non-rigid refinement.

US Pat. No. 9,595,120

METHOD AND SYSTEM FOR MEDICAL IMAGE SYNTHESIS ACROSS IMAGE DOMAIN OR MODALITY USING ITERATIVE SPARSE REPRESENTATION PROPAGATION

Siemens Healthcare GmbH, ...

1. A method for synthesizing a target medical image from a source medical image comprising:
cropping a plurality of image patches from the source medical image; and
generating a synthesized target medical image from the source medical image by jointly performing sparse coding between each
image patch of the source medical image and a corresponding image patch of the synthesized target image based on jointly trained
source and target dictionaries, wherein generating a synthesized target medical image from the source medical image by jointly
performing sparse coding between each image patch of the source medical image and a corresponding image patch of the synthesized
target image based on jointly trained source and target dictionaries comprises:

for each of the plurality of image patches of the source medical image:
calculating a shared sparse coefficient for the image patch of the source medical image and the corresponding image patch
of the target synthesize medical image that results in an optimal joint reconstruction of the image patch of the source medical
image and the corresponding image patch of the synthesized target medical image using the jointly trained source and target
dictionaries;

reconstructing the corresponding image patch of the synthesized target medical image based on the shared sparse coefficient
using the trained target dictionary; and

assigning a pixel value of a center pixel in the reconstructed corresponding image patch of the synthesized target medical
image to a pixel in the synthesized target medical image at which the corresponding image patch of the synthesized target
medical image is centered.

US Pat. No. 9,582,926

COHERENT MEMORY ACCESS IN MONTE CARLO VOLUME RENDERING

SIEMENS HEALTHCARE GMBH, ...

1. A computer-implemented method for iterative Monte Carlo volume rendering, the method comprising:
tracing, by a computer processor, a plurality of light rays into a scene containing volumetric data, the light rays configured
for simulating global illumination;

randomizing, by a computer processor, a scattering location and a scattering direction of the plurality of light rays through
the volume, wherein a common sequence of random numbers is used in order for the scattering direction of each of the plurality
of randomized light rays to be substantially parallel;

computing, by the computer processor, at least one trilinearly interpolated and shaded sample along each of the plurality
of randomized light rays based on stored volumetric data, wherein at least a portion of the stored volumetric data used in
at least a portion of the computing is configured for coherent memory access;

rendering, by the computer processor, the volume with the global illumination based on a plurality of iterations of the tracing,
the randomizing, and the computing.

US Pat. No. 10,055,870

METHOD AND SYSTEM FOR DISPLAYING AN AUGMENTED REALITY TO AN OPERATOR OF A MEDICAL IMAGING APPARATUS

Siemens Healthcare GmbH, ...

1. A method for automatically supporting an operator in proceeding through an execution sequence protocol, comprising multiple sequence steps, with which a patient is being examined in a medical imaging apparatus, said method comprising:in a computer, determining the execution sequence protocol to be implemented for said patient;
with an image data detector, acquiring image data that show a field of vision, as seen by the operator, comprising at least a part of the medical imaging apparatus and the patient;
in said computer, determining a next sequence step of said execution sequence, which is to be implemented by said operator;
in said computer, receiving sensor data from a sensor selected from the group consisting of an acceleration sensor, a magnetic field sensor, and ultrasound sensor, a photo detector, and an RF coil;
in said computer, using said sensor data to determine at least one of a position of the medical imaging apparatus in the image data, an orientation of the medical imaging apparatus in the image data, and a sight position of the operator;
in said computer, generating visual information that informs said operator about said next sequence step; and
from said computer, causing said visual information to be projected at a viewing facility, seen by said operator, by displaying augmented reality to the operator in which said field of vision is shown augmented by said visual information, with said visual information being shown at a location in said field of vision that is selected by said computer dependent on said at least one of said position of the medical imaging apparatus in the image data, said orientation of the medical imaging apparatus in the image data, and said sight position of the operator.

US Pat. No. 9,910,110

MEDICAL IMAGING DEVICE COMPRISING A HOUSING UNIT THAT HAS A CASING SHELL AND METHOD FOR PRODUCING A CASING SHELL OF THE MEDICAL IMAGING DEVICE

Siemens Healthcare GmbH, ...

1. A medical imaging device comprising:
a detection unit; and
a housing unit that surrounds said detection unit and includes a casing shell,
wherein the casing shell includes a netlike supporting structure unit and an elastic spring-mass unit,
wherein the netlike supporting structure unit comprises an inner supporting ring and an outer supporting ring, and
wherein the netlike supporting structure unit comprises a plurality of connecting braces that connect the inner supporting
ring to the outer supporting ring.

US Pat. No. 9,594,976

SPARSE APPEARANCE LEARNING-BASED SEGMENTATION

SIEMENS HEALTHCARE GMBH, ...

1. A method for segmentation of a vessel, the method comprising:
extracting a centerline for a vessel represented in medical imaging data representing a patient, the extracting being a function
of a cost term;

calculating the cost term as a function of similarity of patches of the medical imaging data to machine-learned appearance
patterns at multiple scales relative to the medical imaging data, the cost term indicating membership as in the vessel or
not in the vessel of different locations for the patches;

segmenting the vessel as represented in the medical imaging data, the segmenting being a function of the centerline; and
generating an image of the vessel segmented from the medical imaging data.

US Pat. No. 9,589,211

LEARNING-BASED AORTA SEGMENTATION USING AN ADAPTIVE DETACH AND MERGE ALGORITHM

Siemens Healthcare GmbH, ...

1. A method for segmenting a structure of interest in medical imaging data, comprising:
generating a binary mask highlighting structures in medical imaging data, the highlighted structures comprising a connected
component including a structure of interest;

computing a probability map by classifying voxels in the highlighted structures using a trained classifier;
performing a plurality of detaching operations on the highlighted structures to split the connected component into a plurality
of detached connected components;

determining an optimal detaching parameter representing a number of the detaching operations; and
classifying a detached connected component resulting from performing the number of detaching operations corresponding to the
optimal detaching parameter as the structure of interest based on the probability map and the trained classifier.

US Pat. No. 9,747,525

METHOD AND SYSTEM FOR IMPROVED HEMODYNAMIC COMPUTATION IN CORONARY ARTERIES

Siemens Healthcare GmbH, ...

1. A method for non-invasive assessment of an arterial stenosis, comprising:
segmenting a plurality of mesh candidates for an anatomical model of an artery including a stenosis region of a patient from
medical imaging data;

computing a hemodynamic index for the stenosis region in each of the plurality of mesh candidates; and
determining whether a variation among values of the hemodynamic index for the stenosis region in each of the plurality of
mesh candidates is significant with respect to a threshold associated with a clinical decision regarding the stenosis region
by determining whether the variation among values of the hemodynamic index for the stenosis region in each of the plurality
of mesh candidates is entirely below the threshold for the clinical decision or is entirely above the threshold for the clinical
decision.

US Pat. No. 9,715,726

METHOD AND SYSTEM FOR B0 DRIFT AND RESPIRATORY MOTION COMPENSATION IN ECHO-PLANAR BASED MAGNETIC RESONANCE IMAGING

Siemens Healthcare GmbH, ...

1. A method for B0 drift and respiratory motion compensation in echo-planar based magnetic resonance imaging (MRI) comprising:
obtaining at least two phase images of a target region of a patient from each of a first echo-planar imaging (EPI) acquisition
and a second EPI acquisition;

generating a first susceptibility map based on the at least two phase images of the target region of the patient obtained
from the first EPI acquisition and a second susceptibility map based on the at least two phase images of the target region
of the patient obtained from the second EPI acquisition;

initializing a smooth polynomial function for modeling the B0 drift and respiratory motion between the first EPI acquisition and the second EPI acquisition based on the first and second
susceptibility maps; and

iteratively reconstructing a compensated temperature map showing temperature changes in tissue in the target region of the
patient based on the smooth polynomial function to compensate for temperature map inaccuracies due to B0 drift and respiratory motion.

US Pat. No. 9,684,045

IMAGING THE TEETH BY MEANS OF MAGNETIC RESONANCE TECHNOLOGY WITH NON-UNIQUE GRADIENTS

SIEMENS HEALTHCARE GMBH, ...

1. A gradient system of a magnetic resonance system comprising:
a gradient coil which generates three superimposed gradient fields in a coordinate system,
wherein at least one of the three gradient fields extends in parallel or orthogonally to an approximately U-shaped center
plane of the teeth of a jaw of a patient,

wherein the at least one of the gradient fields is not spatially unique in a respective direction of the coordinate system,
and

wherein the at least one of the gradient fields has the same field strength for at least two different coordinate areas in
the respective direction.

US Pat. No. 9,613,452

METHOD AND SYSTEM FOR VOLUME RENDERING BASED 3D IMAGE FILTERING AND REAL-TIME CINEMATIC RENDERING

SIEMENS HEALTHCARE GMBH, ...

1. A method for volume rendering based filtering of a 3D volume, comprising:
generating a set of 2D projection images of the 3D volume using cinematic volume rendering; and
generating a reconstructed 3D volume from the set of 2D projection images using an inverse linear volumetric ray tracing operator.

US Pat. No. 9,715,637

METHOD AND SYSTEM FOR AUTOMATIC AORTA SEGMENTATION

Siemens Healthcare GmbH, ...

1. A method for aorta segmentation in a 3D volume, comprising:
detecting an aortic root in the 3D volume using marginal space learning (MSL); and
tracking an ascending aorta from the detected aortic root in the 3D volume; and
generating a segmented aorta including the detected aortic root and the ascending aorta.

US Pat. No. 9,664,803

METHOD FOR CALIBRATING A COUNTING DIGITAL X-RAY DETECTOR, X-RAY SYSTEM FOR PERFORMING SUCH A METHOD AND METHOD FOR ACQUIRING AN X-RAY IMAGE

Siemens Healthcare GmbH, ...

1. An X-ray system comprising:
a counting digital X-ray detector comprising:
an X-ray converter operable for converting X-ray radiation into an electrical signal;
a matrix composed of a plurality of counting pixel elements;
a drive and readout unit; and
at least one global discriminator and one global digital-to-analog converter having an adjustable global threshold value that
is appliable to all or a subset of the plurality of counting pixel elements, wherein each pixel element of the plurality of
counting pixel elements has a signal input, a counter and at least one local discriminator and one local digital-to-analog
converter having an individually adjustable local threshold value for the respective pixel element, and wherein for each pixel
element of the plurality of counting pixel elements above a summed threshold value, an incoming signal is counted by a memory
unit;

an X-ray source operable for emitting X-ray radiation;
a memory unit operable for storing count rates of the plurality of counting pixel elements; and
a calculation unit configured for determining or calculating individual correction threshold values for individual pixel elements
of the plurality of counting pixel elements.

US Pat. No. 9,588,209

METHOD OF MULTISLICE MR ELASTOGRAPHY WITH MULTIBAND ACQUISITION

Siemens Healthcare GmbH, ...

1. A method for performing multi-slice MR Elastography on an anatomical region of interest associated with a patient, the
method comprising:
inducing a plurality of shear waves at a shear wave frequency value in the anatomical region of interest using an external
driver;

imaging the anatomical region of interest during a single patient breath-hold using a MRI acquisition process comprising:
applying a multiband Radio Frequency (RF) pulse to the anatomical region of interest,
applying a slice selection gradient to the anatomical region of interest simultaneously with the multiband RF pulse, the slice
selection gradient operable to select a plurality of tissue slice locations from the anatomical region of interest,

acquiring an RF signal corresponding to the plurality of tissue slice locations in response to the multiband RF pulse and
the slice selection gradient;

generating a plurality of phase images of the anatomical region of interest based on the RF signal; and
processing the plurality of phase images using an inversion algorithm to generate one or more quantitative images depicting
stiffness of the anatomical region of interest.

US Pat. No. 9,569,736

INTELLIGENT MEDICAL IMAGE LANDMARK DETECTION

Siemens Healthcare GmbH, ...

1. A method for intelligent image parsing, the method comprising:
specifying a state space of an artificial agent for discrete portions of a training image;
determining a set of actions, each action specifying a possible change in a parametric space with respect to the test image;
establishing a reward system based on applying each action of the set of actions and based on at least one target state;
learning, by the artificial agent, an optimal action-value function approximator specifying the behavior of the artificial
agent to maximize a cumulative future reward value of the reward system, wherein the behavior of the artificial agent is a
sequence of actions moving the agent towards the at least one target state; and

applying the learned artificial agent on a test image to automatically parse image content.

US Pat. No. 9,569,863

SYSTEM FOR ACCELERATED SEGMENTED MR IMAGE DATA ACQUISITION

Siemens Healthcare GmbH, ...

1. A system for accelerated segmented magnetic resonance (MR) image data acquisition, comprising:
an RF (Radio Frequency) signal generator for generating RF excitation pulses in anatomy and enabling subsequent acquisition
of associated RF echo data; and

a magnetic field gradient generator for generating magnetic field gradients for anatomical volume selection, phase encoding,
and readout RF data acquisition in a three dimensional (3D) anatomical volume,

wherein said RF signal generator and said magnetic field gradient generator are configured to acquire temporally consecutive
segments of k-space line data representative of a first individual image slice in a gradient echo method by adaptively varying
an RF excitation pulse flip angle between acquisition of the temporally consecutive segments before acquiring temporally consecutive
segments of k-space line data representative of a second individual image slice, and

wherein the adaptive variation of the RF excitation pulse flip angles is calculated to provide an equal magnetization across
segments.

US Pat. No. 9,552,955

ELECTRON SOURCE

SIEMENS HEALTHCARE GMBH, ...

1. A system for regulating an electron source, the system comprising:
a plurality of electron emission cathodes operable to release a current;
at least one control electrode;
a gate current regulator configured for regulation of a gate current flowing through the at least one control electrode via
a voltage difference between the at least one control electrode and an electron emission cathode of the plurality of electron
emission cathodes; and

a gate current measuring unit in a control loop including the gate current regulator, the gate current measuring unit operable
to measure the gate current, the gate current being a portion of the current released by the plurality of electron emission
cathodes,

wherein an electron current of at least one electron emission cathode of the plurality of electron emission cathodes is proportional
to the gate current.

US Pat. No. 9,524,550

SYSTEM AND METHOD FOR CORONARY DIGITAL SUBTRACTION ANGIOGRAPHY

Siemens Healthcare GmbH, ...

1. A method for extracting coronary vessels from a contrast image, comprising:
calculating a motion field between each of a plurality of mask images and a background region of the contrast image and calculating
covariances of motion vectors of each motion field;

generating a plurality of background layer predictions by generating a background layer prediction from each of the plurality
of mask images based on the motion field and the covariances of the motion field from each of the plurality of mask images;

combining the plurality of background layer predictions using statistical fusion to generate a final estimated background
layer; and

extracting a coronary vessel layer from the contrast image by subtracting the final estimated background layer from the contrast
image.

US Pat. No. 9,507,913

DATA DRIVEN REDUCTION OF MULTI-SCALE MODELS

Siemens Healthcare GmbH, ...

16. A system for computing multi-scale, physiological measurements using a data-driven model, the system comprising:
a receiver module configured to receiving new input parameters;
a database configured to store physiological measurements associated with a multi-scale physiological system;
a modeling processor configured to:
use dimensionality reduction techniques on the database to identify a reduced set of components explaining the multi-scale
physiological system,

learn a data-driven model of the multi-scale physiological system from the database according to a process comprising:
receiving a plurality of related physiological measurement values corresponding to times between a start time value and a
current time value,

selecting a subset of simulated physiological measurement vectors from the database,
creating an interpolated related physiological measurement vector based on the subset of simulated physiological measurement
vectors and the related physiological measurement values, and

projecting the interpolated related physiological measurement vector onto a manifold space to yield a plurality of related
physiological measurement manifold coefficients,

receive new input parameters,
compute new physiological measurements from the new input parameters based on the plurality of related physiological measurement
manifold coefficients, using the data-driven model,

compute new derived physiological indicators based on the reduced set of components, and
display at least one of the new physiological measurements and the new derived physiological indicators.

US Pat. No. 9,470,772

MAGNETIC RESONANCE IMAGE DISTORTION CORRECTION WITH A REFERENCE VOLUME

SIEMENS HEALTHCARE GMBH, ...

1. A method for distortion correction in magnetic resonance imaging, the method comprising:
acquiring first and second magnetic resonance volumes representing first and second different portions of a patient at a first
resolution, the first and second magnetic resonance volumes having first and second field of views, and wherein the first
and second different portions have an overlapping area;

acquiring a third magnetic resonance volume representing a third portion of the patient and having a third field of view,
the third magnetic resonance volume having an isocenter in the overlapping area, having a field of view smaller than the first
and the second field of view, and acquired at a second resolution less than the first resolution;

non-rigidly registering the third magnetic resonance volume with the first magnetic resonance volume;
correcting distortion in the first magnetic resonance volume based on the registering between the first and third magnetic
resonance volumes;

non-rigidly registering the third magnetic resonance volume with the second magnetic resonance volume;
correcting distortion in the second magnetic resonance volume based on the registering between the second and third magnetic
resonance volumes;

composing the distortion corrected first magnetic resonance volume with the distortion corrected second magnetic volume; and
generating an image as a function of the composed first and second magnetic resonance volumes.

US Pat. No. 9,811,913

METHOD FOR 2D/3D REGISTRATION, COMPUTATIONAL APPARATUS, AND COMPUTER PROGRAM

Siemens Healthcare GmbH, ...

1. A method for registering a three-dimensional image data record of a target region of a patient with a two-dimensional x-ray
image of the target region recorded in a recording geometry, wherein, after prescribing an initial transformation as a test
transformation to be optimized, the method comprises:
selecting at least one rigid reference structure with an associated contour, visible in the x-ray image, from anatomical structures
contained in the image data record, which were established during an evaluation;

establishing a two-dimensional gradient x-ray image and a three-dimensional gradient data record of the image data record,
wherein at least one two-dimensional gradient comparison image, which is forward projected in the recording geometry of the
x-ray image using the test transformation, is established from the gradient data record;

finding a neighborhood in the gradient x-ray image from a plurality of neighborhoods extending about test points for a plurality
of contour points in the gradient comparison image corresponding to initial points on the three-dimensional contour of the
at least one selected reference structure in the recording geometry of the x-ray image, which neighborhood best corresponds
to a local neighborhood of the contour point due to a comparison measure and extends about a comparison point;

establishing local two-dimensional displacement information by comparison of the contour points with the associated comparison
points;

establishing movement parameters of a three-dimensional movement model describing a movement of the target region between
recording of the image data record and the x-ray image from the local two-dimensional displacement information; and

establishing a registration transformation describing the registration by correcting the test transformation based on the
movement parameters.

US Pat. No. 9,778,383

TRANSMISSION OF PET-SIGNALS BY MEANS OF TIME DIVISION MULTIPLEXING

Siemens Medical Solutions...

1. A nuclear imaging system, comprising:
a detector configured to detect at least one photon event;
a timing signal path electrically coupled to the detector and configured to generate a timing signal indicative of a timing
of the at least one photon event;

an energy signal path electrically coupled to the detector and configured to generate an energy signal indicative of an energy
of the at least one photon event; and

a time-domain multiplexer configured combine the timing signal and the energy signal into a compound signal,
wherein the timing signal path comprises:
a comparator; and
a filter electrically coupled to the comparator
wherein the filter comprises a mixed timing pickoff (MTP) filter.

US Pat. No. 9,655,563

EARLY THERAPY RESPONSE ASSESSMENT OF LESIONS

Siemens Healthcare GmbH, ...

1. A method for therapy response assessment, the method comprising:
obtaining a pre-therapy medical image of a patient, the pre-therapy medical image representing at least one lesion of the
patient;

obtaining a post-therapy medical image of the patient, the post-therapy medical image of the patient representing the at least
one lesion of the patient;

convolving, by a processor, the pre-therapy and post therapy medical images with a texture feature learned from training images,
the texture feature comprising an independent sub-space analysis feature; and

classifying, by the processor, a therapy response of the lesion with a machine-learnt classifier with a result of the convolving
as an input feature to the machine-learnt classifier.

US Pat. No. 9,603,576

VISUALIZATION OF DUAL ENERGY COMPUTED TOMOGRAPHY AIRWAYS DATA

Siemens Healthcare GmbH, ...

1. A computer-implemented method of depicting an airway tree of a patient, the method comprising:
generating, by a computed tomography system, an iodine map of the airway tree from dual energy computed tomography (DECT)
imaging data acquired from the patient;

performing, by the computed tomography system, segmentation and modeling defining a region of interest of the airway tree
for rendering from the DECT imaging data, the defined region of interest including at least a portion of the airway tree and
excluding at least a different portion of the airway tree; then

rendering the region of interest of the airway tree with information derived from the generated iodine map based on the airway
segmentation and modeling from the DECT imaging data; and

displaying a graphical image of the region of interest of the airway tree on a user interface.

US Pat. No. 9,558,568

VISUALIZATION METHOD FOR A HUMAN SKELETON FROM A MEDICAL SCAN

Siemens Healthcare GmbH, ...

1. A method for visualizing a skeleton having a plurality of bones, the method comprising:
segmenting, from a three-dimensional (3D) image scan of a body including the skeleton, an image volume for the skeleton;
straightening each bone of the plurality of bones based on a corresponding segmented image volume of the skeleton; and
generating a two-dimensional (2D) image based on the straightened corresponding segmented image volume of each bone of the
plurality of bones, the 2D image being a 2D unfolded view of a full head-to-toe unfolded skeleton view of the body.

US Pat. No. 9,730,609

METHOD AND SYSTEM FOR AORTIC VALVE CALCIFICATION EVALUATION

Siemens Healthcare GmbH, ...

1. A method for automatic aortic valve calcification evaluation, comprising:
detecting a patient-specific aortic valve model in a 3D medical image volume;
segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model; and
generating a 2D calcification plot showing locations of the segmented calcifications relative to aortic valve leaflets of
the patient-specific aortic valve model.

US Pat. No. 9,651,639

METHOD AND DEVICE FOR DETERMINING A CHANGE OVER TIME IN A BIOMARKER IN A REGION TO BE EXAMINED

SIEMENS HEALTHCARE GmbH, ...

1. A method for determining a change over time in a biomarker in a region to be examined of a patient from magnetic resonance
data, comprising:
exciting a first magnetic resonance signal in the region using a first magnetic resonance measuring sequence for detecting
at least one property of the biomarker in the region;

receiving a first magnetic resonance data from the region, wherein the first magnetic resonance data comprises a first item
of information relating to the at least one property;

extracting the first item of information from the first magnetic resonance data and producing a first biomarker value from
the first item of information;

storing the first biomarker value together with patient information;
exciting a second magnetic resonance signal in the region using a second magnetic resonance measuring sequence for detecting
the at least one property of the biomarker in the region in a follow-up examination;

receiving a second magnetic resonance data from the region in the follow-up examination, wherein the second magnetic resonance
data comprises a second item of information relating to the at least one property;

extracting the second item of information from the second magnetic resonance data and producing a second biomarker value from
the second item of information in the follow-up examination;

storing the second biomarker value together with the patient information in the follow-up examination;
determining a change between the first and the second biomarker values using the patient information; and
storing or outputting the change between the first and the second biomarker values using the patient information,
wherein the biomarker is selected from the group consisting of:
a correlation between individual areas of the patient's brain, with the first and the second magnetic resonance measuring
sequences being designed as a resting state magnetic resonance sequence,

a perfusion behavior in individual areas of the patient's brain, with the first and the second magnetic resonance measuring
sequences being designed as an Arterial Spin Labeling sequence, and

a morphology of an area of the patient's brain, with the at least one property being the size of the area of the patient's
brain.

US Pat. No. 9,622,673

SYSTEM FOR DETERMINING ELECTRICAL STATUS OF PATIENT ATTACHED LEADS

Siemens Healthcare GmbH, ...

1. A system for determining electrical status of patient attached leads in medical patient monitoring, comprising:
a repository of data indicating a plurality of predetermined impedance value ranges and corresponding associated lead status
information of at least one electrical lead attached to a patient for conducting electrical signals for use in patient monitoring;

an impedance measurement processor using a substantially passive impedance bridge network operating exclusive of constant
current injection for automatically successively determining whether an impedance value of a particular patient attached lead
of a plurality of electrical leads attached to patient skin is within a particular impedance value range of a plurality of
predetermined impedance value ranges and capturing a cardiac impedance distribution together with electrophysiological vectors
on different leads for together mapping to localize cardiac tissue conditions and indicating a potential patient medical condition
supporting diagnosis, said impedance measurement processor predicts a lead signal voltage conveyed on said particular patient
attached lead using remaining acceptable lead signals in response to a determination said particular impedance value range
of said particular patient attached lead indicates an unacceptable connection and comprises a failed lead, wherein said prediction
of said lead signal conveyed on said particular patient attached lead is in response to a weighted lead signal combination
using remaining said acceptable lead signals; and

an output processor for communicating data comprising a message identifying an electrical status of a particular lead of said
plurality of electrical leads by deriving status information from said repository in response to a determination said impedance
value of said particular patient attached lead is within said particular impedance value range.

US Pat. No. 9,622,831

METHOD AND APPARATUS TO PROVIDE UPDATED PATIENT IMAGES DURING ROBOTIC SURGERY

Siemens Healthcare GmbH, ...

1. A method for providing current images of a surgical site during a robotically-implemented surgical procedure, comprising:
operating a medical imaging device to acquire 3D data representing a volume of a patient situated on a patient table, said
volume comprising anatomy that will be manipulated, during a surgical procedure, by a manually-operated surgical robot;

providing said 3D data to a processor and, in said processor, reconstructing a 3D image of said volume from said 3D data;
via said processor, segmenting a 3D volumetric image of said anatomy from said 3D image of said volume;
in said processor, automatically determining at least one material property of said anatomy;
in said processor, bringing a coordinate system of said surgical robot into registration with a coordinate system of said
medical imaging device;

beginning said surgical procedure and, in said surgical procedure, manually operating said surgical robot to apply at least
one force to said anatomy that produces a geometrical change of said anatomy;

providing an electronic signal representing said force to said processor and, in said processor, automatically updating the
segmented volumetric image of said anatomy, based on said force and said at least one material property of said anatomy, to
produce an updated segmented volumetric image of said anatomy that visually shows said change in the geometry of said anatomy;
and

at a display screen in communication with said processor, displaying said updated segmented volumetric image of said anatomy
in real-time during said surgical procedure.

US Pat. No. 9,585,627

HISTOLOGICAL DIFFERENTIATION GRADE PREDICTION OF HEPATOCELLULAR CARCINOMA IN COMPUTED TOMOGRAPHY IMAGES

SIEMENS HEALTHCARE GMBH, ...

1. A method of determining the histological grade of Hepatocellular Carcinoma (HCC), comprising:
acquiring a Computed Tomography (CT) image of a person including an HCC tumor;
delineating the HCC tumor; and
assigning a histological grade to the HCC tumor, wherein assigning the histological grade to the HCC tumor comprises:
applying a plurality of filters to the HCC tumor, wherein each of the filters produces a corresponding response image and,
for each of the filters, a convolution operation is performed on the filter and the CT image to produce the response image
corresponding to that filter;

computing an average response of the HCC tumor in each of the response images and recording each of the average responses
as an Independent Subspace Analysis (ISA) feature; and

determining the histological grade of the HCC tumor based on the ISA features by using a classifier.

US Pat. No. 9,521,985

AUTOMATIC DETECTION OF CONTRAST INJECTION

Siemens Healthcare GmbH, ...

1. A method for automatically detecting the presence of a contrast agent in an x-ray image, comprising:
acquiring a preliminary x-ray image of a region of interest of a subject prior to administration of the contrast agent;
estimating a background image based on the acquired preliminary x-ray image;
administering the contrast agent into the subject;
acquiring a main set of x-ray images including a plurality of image frames;
subtracting the estimated background image from each image frame of the acquired main set of x-ray images to create a plurality
of subtracted images corresponding to the plurality of image frames;

determining a measure of image intensity for each of the subtracted images;
selecting one or more of the subtracted images having a highest image intensity;
fitting a predefined shape model to the selected one or more subtracted images by using a semi-global optimization strategy;
using the fitting of the predefined shape model to the one or more subtracted images to fit the shape model to each of the
plurality of subtracted images;

calculating a feature value for each image frame based on pixel intensities of each pixel fitted to the shape model for the
corresponding subtracted image;

determining an image frame of peak contrast by selecting the image frame with the greatest feature value; and
using the determined image frame of peak contrast to indicate the presence of the contrast agent in the main set of x-ray
images,

wherein the semi-global optimization strategy comprises:
performing a global search on a 2-D space of translation with a course grid using three different groups of five scale and
rotation parameters to find a course-grid optimization;

starting from the course-grid optimization, performing a global search with all five scale and rotation parameters within
a region defined by a size of one grid of the course grid to enhance the course-grid optimization; and

performing fine-tuning of the enhanced course-grid optimization using a hill climbing algorithm as a local optimization strategy
within a region that is smaller than the size of one grid of the course grid,

wherein the five scale and rotation parameters include x-direction scale, y-direction scale, x-direction translation, y-direction
translation, and rotation.

US Pat. No. 9,811,906

METHOD AND DATA PROCESSING UNIT FOR SEGMENTING AN OBJECT IN A MEDICAL IMAGE

SIEMENS HEALTHCARE GMBH, ...

1. A method for segmenting an object in a medical image, the method comprising:
providing the medical image;
performing a plurality of iteration steps, input of a first iteration step of the plurality of iteration steps including the
medical image as an input image and the input of each further iteration step of the plurality of iteration steps includes
a vote map generated in a preceding iteration step as the input image, wherein each iteration step of the plurality of iteration
steps comprises:

generating a plurality of patches, a portion of the input image and a patch location being assigned to each patch of the plurality
of patches, the patch location being indicative of a location of the portion of the input image relative to the input image,

for each patch of the plurality of patches
determining a vote location based on the portion of the respective input image assigned to the respective patch and
determining a target location based on the vote location and the patch location assigned to that patch;
generating a vote map, wherein each patch of the plurality of patches contributes to a respective pixel value at the target
location of the respective patch in the vote map;

determining a structure in the vote map of the final iteration step of the plurality of iteration steps;
determining a subset of patches of the plurality of patches of the first iteration step that contributed to the structure
in the vote map of the final iteration step; and

segmenting the object based on the subset of patches to obtain a segmentation outcome.

US Pat. No. 9,668,699

METHOD AND SYSTEM FOR ANATOMICAL OBJECT DETECTION USING MARGINAL SPACE DEEP NEURAL NETWORKS

Siemens Healthcare GmbH, ...

1. A method for anatomical object detection in a medical image of a patient, comprising:
receiving a medical image of a patient including a target anatomical object; and
detecting a pose of the target anatomical object in the medical image in a series of marginal parameter spaces of increasing
dimensionality using a respective trained deep neural network for each of the marginal parameter spaces, wherein each respective
trained deep neural network inputs image patches of the medical image, samples pixels or voxels in each input image patch
in a sparse sampling pattern adaptively learned during training of the respective trained deep neural network, and operates
directly on the pixels or voxels sampled from each input image patch to calculate one or more candidates for the target anatomical
object in a respective one of the marginal parameter spaces and wherein, for each of the marginal parameter spaces, a respective
cascade of trained shallow sparse neural networks filters image patches of the medical image to remove negative image patches
prior to the remaining image patches being input to the respective trained deep neural network for that marginal parameter
space.

US Pat. No. 9,542,741

METHOD AND SYSTEM FOR AUTOMATIC PELVIS UNFOLDING FROM 3D COMPUTED TOMOGRAPHY IMAGES

Siemens Healthcare GmbH, ...

1. A method for automatic pelvis unfolding from a 3D medical image, comprising:
receiving a 3D medical image;
segmenting pelvis anatomy in the 3D medical image; and
reformatting the 3D medical image to visualize an unfolded pelvis based on one of a flat medial surface that is a 2D surface
fit within the segmented pelvis anatomy or a mesh slab fit to the pelvis in the 3D medical image.

US Pat. No. 9,521,988

VESSEL TREE TRACKING IN ANGIOGRAPHY VIDEOS

Siemens Healthcare GmbH, ...

14. A system for tracking vessels in image data, the system comprising:
an imaging computer configured to execute a plurality of components comprising:
an annotation component configured to annotate a target vessel in a plurality of image frames,
a landmark selection component configured to select a plurality of tracking targets associated with the target vessel based
on a first frame included in the plurality of image frames,

a hypothesis generation component configured to select a plurality of landmark hypothesis points for each tracking target
in the each of the plurality of image frames,

a graph construction component configured to construct a directed acyclic graph from the plurality of landmark hypothesis
points, and

a graph solving component configured to solve the directed acyclic graph to yield a plurality of optimal landmarks for each
respective image frame in the plurality of image frames;

a display configured to:
present each respective image frame included in the plurality of image frames, and
overlay a visual indication of the target vessel on each respective image frame in the plurality of image frames based on
the plurality of optimal landmarks associated with the respective image frame; and

a guidewire tracking component configured to track a location of a guidewire, wherein the plurality of landmark hypothesis
points is selected based on the location of the guidewire related to the target vessel.

US Pat. No. 9,519,981

VISUALIZING BRAIN NETWORK CONNECTIVITY

Siemens Healthcare GmbH, ...

1. A method for visualizing brain network connectivity in 3-dimensions (3D), comprising:
receiving image data corresponding to a brain of interest;
constructing a brain network from the image data by recursively clustering network nodes using knowledge of brain networks,
wherein centroids of hierarchical clusters are determined and used as nodes to construct hierarchical brain networks to guide
connections of a target network of the whole brain, wherein edges are started from leaf nodes and then converged toward ancestor
nodes;

rendering edges between nodes using B-Spline curves constructed from control points found by searching for a nearest common
ancestor of two related nodes of the target network from the hierarchical brain networks;

duplicating at least one control point for spline edges sharing a common ancestor to create an extra copy of said at least
one control point;

bundling spline edges by applying a global strength parameter ?;
displaying a 3D visualization of the brain network connectivity by rendering left/right view images into a frame buffer object
(FBO) at full screen resolution, and attaching content from the FBO as textures to a corresponding viewer or viewers; and

coloring edges by an alpha blending technique that blends a color of a start node and a color of an end node, wherein a local
blending factor is a normalized distance to the start node and a global blending factor is a normalized line length.

US Pat. No. 9,947,117

RECONSTRUCTION OF A RESULTANT IMAGE TAKING ACCOUNT OF CONTOUR SIGNIFICANCE DATA

SIEMENS HEALTHCARE GMBH, ...

1. A method for calculating resultant image data of an examination object from scan data acquired during a relative rotation movement between a radiation source of an X-ray image recording system and the examination object, the method comprising:reconstructing initial image data from the scan data;
deriving contour data from the initial image data;
calculating contour significance data from at least one of the scan data and the initial image data; and
calculating the resultant image data using the contour data and the contour significance data.

US Pat. No. 9,633,455

DICTIONARY-FREE MR PARAMETER INFERENCE FOR FINGERPRINTING RECONSTRUCTION

Siemens Healthcare GmbH, ...

1. A method of generating Magnetic Resonance (MR) parameter maps, the method comprising:
creating one or more parameter maps, each respective parameter map comprising initial parameter values associated with one
of a plurality of MR parameters;

performing a dynamical update process over a plurality of time points, wherein the dynamical update process performed at each
respective time point comprises:

applying a randomized pulse sequence to subject using an MR scanner to acquire a k-space dataset, wherein the randomized pulse
sequence is configured to excite a distinct range of values associated with the plurality of MR parameters;

applying a reconstruction process to the k-space dataset to generate an image; and
using a tracking process to update the one or more parameter maps based on the randomized pulse sequence and the image.

US Pat. No. 9,510,800

METHOD AND APPARATUS FOR REDUCING MOTION INDUCED BLUR IN MEDICAL IMAGES USING TIME GATE PROCESSING

Siemens Medical Solutions...

1. A method of processing data for medical imaging, the method comprising:
providing a first gate data representing a first plurality of time gates for a first medical imaging modality, wherein the
first plurality of time gates are based on a plurality of cycles of an acquired physiological signal of a person;

determining a gate width for a second medical imaging modality; and
generating a second gate data representing a second plurality of time gates for the second medical imaging modality, wherein
each time gate in the second plurality of time gates has the determined gate width and is generated dependent on a respective
time gate in the first plurality of time gates,

wherein each time gate in the second plurality of time gates is centered relative to a respective time gate in the first plurality
of time gates.

US Pat. No. 9,662,017

METHODS AND SYSTEMS FOR ACQUIRING MULTIPLE INTERLEAVED SLICES IN MAGNETIC RESONANCE IMAGING

Siemens Healthcare GmbH, ...

1. A method for operating a Magnetic Resonance (MR) imaging system, the method comprising:
generating radio frequency (RF) excitation pulses in a volume of patient anatomy comprising a patient's heart to provide subsequent
acquisition of associated RF echo data;

generating slice select magnetic field gradients for phase encoding and readout RF data acquisition in the volume of patient
anatomy;

acquiring a plurality of slices of an image of the volume of patient anatomy within a plurality of cycles, each of the plurality
of cycles representing time period between successive beats of the patient's heart;

causing, by a control processor, accelerated acquisition of two or more slices of the plurality of slices within a quiescent
phase of each of the plurality of cycles;

applying, by the control processor, one or more saturation areas proximate to a target volume of the patient anatomy; and
wherein causing accelerated acquisition of the two or more slices within the quiescent phase of each of the plurality of cycles
further comprises under-sampling the two or more acquired slices.

US Pat. No. 9,898,824

METHOD FOR VOLUME EVALUATION OF PENUMBRA MISMATCH IN ACUTE ISCHEMIC STROKE AND SYSTEM THEREFOR

Siemens Healthcare GmbH, ...

1. A method for automatically locating and segmenting ischemic brain penumbra during an exam of a brain by a magnetic resonance
(MR) imaging system and evaluating a volume of penumbra mismatch, which comprises the steps of:
a) performing MR diffusion-weighted imaging (DWI) of the brain for acquiring b0 and b1000 native diffusion images of slices
of the brain and creating an apparent diffusion coefficient (ADC) map of each of the slices of the brain;

b) performing MR perfusion-weighted imaging (PWI) of the brain for acquiring native perfusion images of the slices of the
brain, wherein for each slice, several of the native perfusion images are successively acquired during successive acquisition
periods;

c) for each of the slices of the brain, segmenting the b0 native diffusion image of the slice of the brain to create a contour
mask, the contour mask being a mask of a contour of a parenchyma appearing in the b0 native diffusion image of the slice of
the brain;

d) for each of the slices of the brain, creating a necrosis and cerebrospinal fluid mask, hereafter NC mask, from the apparent
diffusion coefficient (ADC) map of the slice of the brain;

e) fusing the contour mask and the NC mask of a same slice of the brain;
f) for each of the slices of the brain, aligning all the native perfusion images acquired for the slice with the NC mask obtained
for the slice so that a head axis in the native perfusion images becomes aligned with a head axis in the NC mask and then
fusing the NC mask with each native perfusion image for obtaining an improved perfusion image;

h) randomly selecting N perfusion voxels whose positions are outside of the necrosis, wherein N is smaller or equal to a total
amount M of the perfusion voxels acquired during one acquisition period for all the slices, and using improved perfusion images
for classifying each randomly selected perfusion voxel in a class of voxels among K classes of voxels, wherein a random selection
of the perfusion voxels includes increasing a distance between a randomly selected voxel and the necrosis from first randomly
selecting perfusion voxels to a last randomly selecting perfusion voxel;

i) creating a map of the brain that represents the K classes;
j) creating a final image of the brain by grouping in the map of the brain the classes in a predefined number F of families,
wherein the family whose voxels represent a largest volume corresponds to a healthy parenchyma, and remaining families which
have at least one voxel that is connected directly or indirectly to the necrosis correspond to the penumbra; and

k) calculating a volume of the penumbra mismatch from the final image of the brain, wherein the volume of the penumbra mismatch
equals to a sum of volumes of the voxels belonging to each family corresponding to the penumbra.

US Pat. No. 9,766,308

MAGNETIC RESONANCE UNIT, A MAGNETIC RESONANCE APPARATUS WITH THE MAGNETIC RESONANCE UNIT, AND A METHOD FOR DETERMINATION OF A MOVEMENT BY A PATIENT DURING A MAGNETIC RESONANCE EXAMINATION

SIEMENS HEALTHCARE GMBH, ...

1. A magnetic resonance unit, comprising:
a housing unit;
a patient accommodation area for accommodation and/or holding of at least one part region of a patient for a magnetic resonance
examination;

a first movement sensor unit for acquiring a first item of movement information of a movement of the patient; and
a second movement sensor unit for acquiring a second item of movement information of the movement of the patient,
wherein the patient accommodation area is at least partially surrounded by the housing unit, the first movement sensor unit,
and the second movement sensor unit,

wherein the first movement sensor unit exhibits a first field of view for the acquisition of a first part region of the patient
and/or of the patient accommodation area,

wherein the second movement sensor unit exhibits a second field of view for the acquisition of a second part region of the
patient and/or of the patient accommodation area that is arranged differently to the first part region of the patient and/or
of the patient accommodation area,

wherein the first and the second movement sensor units are arranged outside of the patient accommodation area,
wherein the first and the second movement sensor units are arranged on the housing unit in an area on a side facing away from
the patient accommodation area, and

wherein the first movement sensor unit and/or the second movement sensor unit acquires at least one item of movement information
of the movement of the patient by a run-time measurement of at least one sensor signal.

US Pat. No. 9,760,690

CONTENT-BASED MEDICAL IMAGE RENDERING BASED ON MACHINE LEARNING

Siemens Healthcare GmbH, ...

1. A method for content-based rendering based on machine learning in a rendering system, the method comprising:
loading, from memory, a medical dataset representing a three-dimensional region of a patient;
applying, by a machine, the medical dataset to a machine-learnt model, the machine-learned model trained with deep learning
to extract features from the medical dataset and trained to output values for two or more physically-based rendering parameters
based on input of the medical dataset, the two or more physically-based rendering parameters being settings of a physically-based
renderer, the settings used by the physically-based renderer to control rendering from three dimensions to two-dimensions,
at least one of the two or more rendering parameters being controls for data consistency handling, lighting design, viewing
design, material propriety, or internal renderer property;

rendering, by the physically-based renderer, a photorealistic image of the three-dimensional region of the patient using the
output values resulting from the applying as the settings to control the rendering from the medical dataset, the rendering
of the medical dataset of the three-dimensional region being to the photorealistic image in the two-dimensions; and

transmitting the photorealistic image.

US Pat. No. 9,665,936

SYSTEMS AND METHODS FOR SEE-THROUGH VIEWS OF PATIENTS

Siemens Healthcare GmbH, ...

1. A computer-implemented method for providing a see-through visualization of a patient, the method comprising: receiving
an image dataset representative of anatomical features of the patient acquired using a medical image scanner; acquiring a
body surface model of the patient using an RGB-D sensor; aligning the body surface model with the image dataset in a canonical/common
coordinate system to yield an aligned body surface model by determining a plurality of first landmarks in the image dataset;
determining a plurality of second landmarks in the body surface model, each of the plurality of second landmarks corresponding
to a distinct one of the plurality of first landmarks; and using correspondences between the plurality of first landmarks
and a plurality of second landmarks to align the body surface model with the image dataset; determining a relative pose of
a mobile device with respect to the RGB-D sensor; creating a pose dependent visualization of the patient by rendering the
image dataset at a viewpoint corresponding to the relative pose of the mobile device; and presenting the see-through pose
dependent visualization of the patient on the mobile device.

US Pat. No. 9,576,356

REGION CLUSTERING FOREST FOR ANALYZING MEDICAL IMAGING DATA

Siemens Healthcare GmbH, ...

1. A method for training a region clustering forest, comprising:
receiving a set of medical training images for a population of patients;
extracting a set of image patches from each image in the set of medical training images; and
generating a plurality of region clustering trees each minimizing a loss function based on respective randomly selected subsets
of the set of image patches to train the region clustering forest, wherein each of the plurality of region clustering trees
cluster image patches at a plurality of leaf nodes and the loss function measures a compactness of the cluster of image patches
at each leaf node in each of the plurality of region clustering trees.

US Pat. No. 9,911,225

LIVE CAPTURING OF LIGHT MAP IMAGE SEQUENCES FOR IMAGE-BASED LIGHTING OF MEDICAL DATA

Siemens Healthcare GmbH, ...

1. A method for light map capture, the method comprising:
receiving over time, by a processor, patient volume scan data for a target area;
capturing over time, by at least one camera, lighting environment data that intersects an exterior surface on a patient for
the target area;

transmitting over time, by the at least one camera, the lighting environment data to the processor;
lighting over time, by the processor, the patient volume scan data with the lighting environment data, the lighting providing
a lighted patient volume data; and

rendering over time, by the processor, an image from the lighted patient volume data.

US Pat. No. 9,855,179

RAIL GUIDE HAVING A SECURING UNIT, PATIENT TABLE HAVING A RAIL GUIDE FOR ACCESSORIES, AND METHOD FOR OPERATING A RAIL GUIDE

Siemens Healthcare GmbH, ...

1. A securable rail guide, comprising:
a guide rail;
a runner rail disposed in said guide rail and movable along said guide rail; and
at least one securing unit being embodied to fix said runner rail in position in said guide rail in a releasable manner, said
at least one securing unit containing:

a locking unit disposed on said guide rail and embodied to secure said runner rail in a locked position, said locking unit
having a lever embodied to fix said runner rail in position; and

an unlocking unit disposed on said runner rail, said unlocking unit being operatively connected to said locking unit in such
a way that an actuation of said unlocking unit releases said runner rail allowing its free movement along said guide rail.

US Pat. No. 9,638,778

METHODS AND SYSTEMS FOR IMPROVING SNR IN MULTI-SLICE MULTI-SEGMENT MAGNETIC RESONANCE IMAGING

Northwestern University, ...

1. A method for operating a Magnetic Resonance (MR) imaging system, the method comprising:
generating radio frequency (RF) excitation pulses in patient anatomy to provide subsequent acquisition of associated RF echo
data;

generating slice select magnetic field gradients for phase encoding and readout RF data acquisition in the patient anatomy;
acquiring a segment of a plurality of segments of k-space data for each of a plurality of slices of an imaged volume within
each of a plurality of cycles; and

causing, by a control processor, a RF signal generator and a gradient generator to change an order of the slices that the
segments of k-space data are acquired for between consecutive cycles of the plurality of cycles.

US Pat. No. 9,582,916

METHOD AND SYSTEM FOR UNSUPERVISED CROSS-MODAL MEDICAL IMAGE SYNTHESIS

SIEMENS HEALTHCARE GMBH, ...

1. A method for unsupervised cross-modal synthesis of a target modality medical image from a source modality medical image,
comprising:
receiving the source modality medical image;
generating multiple candidate target modality intensity values for each of a plurality of voxels of the target modality medical
image based on corresponding voxels in the source modality medical image; and

generating a synthesized target modality medical image by selecting, jointly for all of the plurality of voxels in the target
modality medical image, intensity values from the multiple candidate target modality intensity values generated for each of
the plurality of voxels.

US Pat. No. 9,542,761

GENERALIZED APPROXIMATE MESSAGE PASSING ALGORITHMS FOR SPARSE MAGNETIC RESONANCE IMAGING RECONSTRUCTION

Siemens Healthcare GmbH, ...

1. A method for reconstructing magnetic resonance imaging data, the method comprising:
acquiring a measurement dataset using a magnetic resonance imaging device;
determining an estimated image dataset based on the measurement dataset;
performing an iterative reconstruction process to refine the estimated image dataset, wherein each iteration of the iterative
reconstruction process comprises:

updating the measurement dataset and a sparse coefficient dataset based on the estimated image dataset and a plurality of
belief propagation terms, wherein the sparse coefficient dataset comprises mean sparse coefficient data and variance sparse
coefficient data,

incorporating a noise prior dataset into the measurement dataset,
incorporating a sparsity prior dataset into the sparse coefficient dataset by (a) updating the mean sparse coefficient data
by applying a soft thresholding operator to the mean sparse coefficient data and (b) updating the variance sparse coefficient
data by applying a derivative soft thresholding operator to the mean sparse coefficient data,

updating the plurality of belief propagation terms based on the measurement dataset and the sparsity prior dataset, and
updating the estimated image dataset based on the plurality of belief propagation terms; and
generating a reconstructed image and confidence map using the estimated image dataset.

US Pat. No. 9,858,689

FAST AND MEMORY EFFICIENT REDUNDANT WAVELET REGULARIZATION WITH SEQUENTIAL CYCLE SPINNING

Siemens Healthcare GmbH, ...

1. A computer-implemented method of performing image reconstruction with sequential cycle-spinning, the method comprising:
acquiring, by a computer system, an input signal comprising k-space data using a magnetic resonance imaging (MRI) device;
initializing, by the computer system, an estimate of a sparse signal associated with the input signal;
selecting, by the computer system, one or more orthogonal wavelet transforms corresponding to a wavelet family;
performing, by the computer system, an iterative reconstruction process to update the estimate of the sparse signal over a
plurality of iterations, wherein each iteration comprises:

applying the one or more orthogonal wavelet transforms to the estimate of the sparse signal to yield one or more orthogonal
domain signals,

updating the estimate of the sparse signal by applying a non-convex shrinkage function to the one or more orthogonal domain
signals, and

applying a shift to the one or more orthogonal wavelet transforms; and
following the iterative reconstruction process, generating an image based on the estimate of the sparse signal.

US Pat. No. 9,785,858

METHOD AND SYSTEM FOR HIERARCHICAL PARSING AND SEMANTIC NAVIGATION OF FULL BODY COMPUTED TOMOGRAPHY DATA

Siemens Healthcare GmbH, ...

1. A method for detecting anatomic landmarks and segmenting organs in a full or partial body computed tomography (CT) volume,
comprising:
detecting one or more predetermined slices of the CT volume, wherein detecting one or more predetermined slices of the CT
volume comprises:

detecting candidates for the predetermined slices using trained slice detectors, and
estimating a final slice position for each of the predetermined slices based on inter-slice geometric relationships using
a discriminative anatomical network (DAN) that connects the trained slice detectors;

detecting a plurality of anatomic landmarks and organ centers in the CT volume, wherein each of the plurality of anatomic
landmarks and organ centers is detected in a portion of the CT volume constrained based on one of the detected one or more
predetermined slices; and

segmenting a plurality of organs in the CT volume based on the detected organ centers and the detected anatomic landmarks.

US Pat. No. 9,734,573

METHODS AND SYSTEMS FOR AUTOMATICALLY DETERMINING MAGNETIC FIELD INVERSION TIME OF A TISSUE SPECIES

The United States of Amer...

1. A computer-implemented method for determining magnetic field inversion time of a tissue species, the method comprising:
generating a T1-mapping image of a tissue of interest, the T1-mapping image comprising a plurality of T1 values within an
expected range of T1 values for the tissue of interest;

creating an image mask based on predetermined identification information about the tissue of interest;
applying the image mask to the T1-mapping image to yield a masked image;
identifying a largest connected region of the masked image;
determining a mean relaxation time value for the largest connected region; and
determining a time point for nulling longitudinal magnetization of healthy portions of the tissue of interest based on the
mean relaxation time value for the largest connected region.

US Pat. No. 9,700,219

METHOD AND SYSTEM FOR MACHINE LEARNING BASED ASSESSMENT OF FRACTIONAL FLOW RESERVE

Siemens Healthcare GmbH, ...

1. A method for determining fractional flow reserve (FFR) for a stenosis of interest for a patient, comprising:
receiving a medical image of the patient including the stenosis of interest;
detecting image patches corresponding to the stenosis of interest and a coronary tree of the patient; and
determining an FFR value for the stenosis of interest using a trained deep neural network regressor applied directly to the
detected image patches without first extracting features from the medical image, wherein the trained deep neural network regressor
is trained using a first set of training image patches without corresponding FFR values to train weights of layers other than
a final layer of the deep neural network regressor and a second set of training image patches including identified stenosis
image patches and corresponding FFR values to refine the weights of all layers including the final layer of the deep neural
network regressor.

US Pat. No. 9,618,593

PHASE ENHANCED UTE WITH IMPROVED FAT SUPPRESSION

Siemens Healthcare GmbH, ...

1. A computer-implemented method of performing magnetic resonance imaging with ultra-short echo time pulse sequences, the
method comprising:
defining short T2 threshold limits for enhancement;
acquiring a multi-echo ultra-short echo time response;
determining a complex dataset based on the multi-echo ultra-short echo time response;
identifying a plurality of phase components from the complex dataset, wherein each phase component is associated with a T2
relaxation time within the short T2 threshold limits;

identifying a plurality of frequency components from the complex dataset, wherein each frequency component is associated with
the T2 relaxation time within the short T2 threshold limits;

deriving a magnitude dataset from the complex dataset;
applying a fitting algorithm to the magnitude dataset to yield a plurality of magnitude components, wherein each magnitude
component is associated with the T2 relaxation time within the short T2 threshold limits;

creating a plurality of phase masks based on the plurality of phase components and the plurality of frequency components;
applying the plurality of phase masks to the magnitude dataset to obtain a combined dataset; and
presenting an image on a display based on the combined dataset.

US Pat. No. 9,600,891

WEB BASED FAST QUERY VISUALIZATION OF TIME-VARYING MULTI-VARIATE VESSEL FLOW FIELD BY USING UNIFORM PARTITION STRATEGY

Siemens Healthcare GmbH, ...

1. A method for visualizing flow data from computation fluid dynamics (CFD) applications in 2-dimensions (2D), comprising
the steps of:
receiving a 3-dimensional (3D) image volume from a CFD simulation of fluids flowing through vessels in a patient that is a
snapshot of a fluid flow in the vessels at a certain time;

subdividing the 3D image volume into 3D data blocks;
minimizing a sum over energy interactions defined for each pair of data blocks in the 3D image volume, wherein said minimization
preserves a local shape of the vessels, wherein minimizing the sum over energy interactions is performed on a graphics processing
unit (GPU), wherein minimizing the sum over the energy interactions comprises minimizing E=?{square root over (?ijEij2)}

wherein

wherein wn and wnn are weights for neighboring and non-neighboring blocks, respectively, tij=|vi?vj| is a target distance between blocks bi and bj in a 2D image wherein vi and vj are 2D positions of bi and bj, eij is a Euclidean distance between bi and bj in the 3D volume, gij is a geodesic distance between bi and bj in the vessels in the 3D image, and d is a threshold that separates neighboring blocks from non-neighboring blocks, wherein
the minimization is performed by varying the target positions vi and vj; and

using the minimized energy E to display on a monitor a 2D sketch of the 3D image volume, wherein the 2D sketch is displayed
in real-time with respect to the time scale of the CFD simulation.

US Pat. No. 9,568,573

METHODS AND SYSTEMS FOR AUTOMATED MAGNETIC FIELD SHIMMING

Siemens Healthcare GmbH, ...

1. A method for automated magnetic field shimming in a Magnetic Resonance (MR) imaging system, the method comprising:
generating radio frequency (RF) excitation pulses in a volume of patient anatomy comprising a patient's heart to provide subsequent
acquisition of associated RF echo data;

generating slice select magnetic field gradients on a static magnetic field for phase encoding and readout RF data acquisition
in the volume of patient anatomy;

generating a plurality of shimming routines, each shimming routine comprising applying non-linear magnetic field gradients
to the static magnetic field to modify the homogeneity of the static magnetic field;

acquiring a plurality of maps of the static magnetic field, each of the plurality of maps being acquired between each shimming
routine;

determining, by a control processor, a base function for each of the plurality of shimming coils from: (i) intermediate magnitudes
and directions of the static magnetic field produced by each of the plurality of shimming coils during each shimming routine;
and (ii) intermediate currents supplied to each of the plurality of shimming coils during each shimming routine; and

determining, by the control processor, updated magnitudes and directions of the static magnetic field produced by each of
the plurality of shimming coils by expanding the determined base function for each of the plurality of shimming coils into
low order polynomials.

US Pat. No. 9,510,738

INSTRUMENT SYSTEM

SIEMENS HEALTHCARE GMBH, ...

1. An instrument system, comprising:
an endoscopic instrument comprising a work head attached to one end of a flexible support arm to be introduced into a patient;
and

a trocar to be placed in a surface of the patient's body comprising:
a main body to be fixed locally relative to the patient with a through-opening for the endoscopic instrument,
a guide body which, with the endoscopic instrument inserted into the patient, encloses a longitudinal section of the support
arm with a guide channel guiding the guide body such that at least a spatial guidance direction of the support arm is defined
in the longitudinal section,

a plurality of cables acting on the guide body causing an explicit change of a relative position of the guidance direction
relative to the main body, and

a spring element connecting the main body to the guide body,
wherein the cables are actuated to locate the trocar to a work position,
wherein the cables are shortened differently with respect to each other when the cables are actuated,
wherein a distance between the main body and an exit end of the guide body and the spatial guidance direction of the support
arm are changed in relation to a basic position of the trocar when the cables are actuated,

wherein the spring element is relaxed when the trocar is in the basic position,
wherein the cables apply a force against the spring element when the cables are actuated,
wherein the spring element is deformed when the trocar is held in the work position by applying a force against the spring
element via the cables,

wherein the trocar moves back from the work position to the basic position by relieving the force against the spring element
via the cables, and

wherein the spring element is located around the cables.

US Pat. No. 9,953,136

SYSTEM FOR DISPLAYING AND EDITING DATA FOR A MEDICAL DEVICE

Siemens Healthcare GmbH, ...

1. A system for management and processing of data of a medical facility, the system comprising:at least one viewing application for execution by a processor and stored in memory on a user device, wherein the viewing application is configured for displaying medical image datasets held in cloud storage of a public cloud such that each of the medical image datasets is accessible via an associated Uniform Resource Locator (URL) when a corresponding cloud subscription is available, wherein the viewing application is further configured to be downloaded via an associated URL from the cloud storage of the public cloud when the corresponding cloud subscription is available, wherein the URL of the image dataset to be displayed is configured to be specified as an argument, wherein the viewing application comprises:
a View layer comprising at least one component that defines graphical content of a graphical user interface (GUI) page for display of two-dimensional (2D) image data or three-dimensional (3D) image data;
a ViewModel layer comprising one component, which, for a component or each component of the at least one component of the View layer, defines functions for the control elements of the GUI page for display and processing of the image data;
a Model layer comprising one component that defines variables for the image data to be displayed; and
a driver layer comprising:
a component configured to load 2D datasets and edit the 2D datasets for display on a screen; and
a further component that is loadable or activatable as an option, the further component configured to load 3D image datasets or two-dimensional views derived therefrom and edit the 3D image datasets or two-dimensional views for display on a screen,
wherein the component of the ViewModel layer defines a common set of functions for the display and processing of the 2D image data and the 3D image data.

US Pat. No. 9,824,448

METHOD FOR ACQUIRING A MAGNETIC FIELD INHOMOGENEITY VALUE AND DISTORTION CORRECTION METHOD FOR MAGNETIC RESONANCE IMAGING SYSTEM

Siemens Healthcare GmbH, ...

2. A distortion correction method for a magnetic resonance imaging (MRI) system, comprising:
based on magnetic field inhomogeneity values of pixels of a magnetic resonance image obtained in the MRI system using a basic
magnetic field of the MRI system, obtaining, in a processor, pixel offsets of the pixels in a phase encoding direction;

using the pixel offsets to subject the pixels to distortion correction in said processor;
using a general formula
?nPE=?·?B +?,
wherein ?nPE is the pixel offsets, ?B is magnetic field inhomogeneity values on pixels of a magnetic resonance image obtained in the MRI
system by a main magnetic field of the MRI system, ? is a conversion parameter, and ? is an adjustment parameter; and

making the distortion-corrected pixels available from the processor in electronic form as a data file.

US Pat. No. 9,786,069

REFINED RECONSTRUCTION OF TIME-VARYING DATA

Siemens Healthcare GmbH, ...

1. A non-transitory computer-readable medium embodying instructions executable by machine to perform operations for data reconstruction
comprising:
performing a first four-dimensional reconstruction of time-varying data to generate a four-dimensional Digital Subtraction
Angiography (DSA) dataset of an object of interest;

identifying a volume of interest in the four-dimensional DSA dataset;
extracting the volume of interest from the four-dimensional DSA dataset to generate a volume array;
refining the volume of interest based on the volume array to generate a refined dataset; and
performing a second four-dimensional reconstruction based on the refined dataset to generate a zoomed-in four-dimensional
representation of the volume of interest.

US Pat. No. 9,700,276

ROBUST MULTI-OBJECT TRACKING USING SPARSE APPEARANCE REPRESENTATION AND ONLINE SPARSE APPEARANCE DICTIONARY UPDATE

Siemens Healthcare GmbH, ...

1. A computer-implemented method for tracking one or more catheter objects in a sequence of images, the method comprising:
determining, by a computer, a foreground portion of the first image comprising portions of the first image corresponding to
one or more catheter electrode locations;

determining, by the computer, a background portion of the first image which excludes the foreground portion;
applying, by the computer, a steerable filter or a pre-processing method to the background portion of the first image to create
a non-catheter structures mask which excludes ridge-like structures in the background portion of the first image;

generating, by the computer, a dictionary based on catheter object locations in the first image, wherein sparse coding is
used to represent the non-catheter structures mask as a plurality of basis vectors in the dictionary;

identifying, by the computer, one or more catheter object landmark candidates in the sequence of images;
generating, by the computer, a plurality of tracking hypothesis for the catheter object landmark candidates;
generating, by the computer, a voting score for the catheter object landmark candidates based on a voting contribution of
each of a plurality of image patches used to localize the catheter object locations in the first image; and

selecting, by the computer, a first tracking hypothesis from the plurality of tracking hypothesis based on the dictionary
and the voting score.

US Pat. No. 9,406,134

IMAGE SYSTEM FOR SUPPORTING THE NAVIGATION OF INTERVENTIONAL TOOLS

1. An image system for supporting a navigation of an interventional tool when performing an imaging controlled invasive intervention
within a body of a patient in an intervention plane, comprising:
a recording system that records a 2D projection recording representing a current position of the interventional tool from
two different projection planes running normally to the intervention plane;

an imaging processing system that processes the 2D projection recording; and
an input/output interface that receives the recorded 2D projection recording from the recording system and supplies the recorded
2D projection recording to the imaging processing system,

wherein the imaging processing system is configured to:
register a shortened length of the interventional tool represented in the 2D projection recording;
capture a directional deviation of an actual course of the interventional tool from a predetermined desired course that lies
within the intervention plane from the registration;

generate a 3D data record of a target zone of the patient;
define a spatial coordinate of a puncture target in the 3D data record with respect to a 3D Cartesian coordinate system;
define a spatial coordinate of an insertion point in the 3D Cartesian coordinate system;
identify a position of a tip of the interventional tool in the 2D projection recording;
calculate a location coordinate of the position in the 3D Cartesian coordinate system based on the identified position in
the 2D projection recording;

select a further spatial point of the intervention tool in the 3D Cartesian coordinate system;
estimate a position of the further spatial point of the interventional tool in the 2D projection recording;
calculate a 3D location coordinate of the 2D estimated position of the further spatial point in the 3D Cartesian coordinate
system;

adjust the further spatial point until a deviation between a direction of a line connecting the identified position of the
tip and the estimated position of the further spatial point in the 2D projection recording and a projected direction of the
predetermined desired course in the 2D projection recording being within a predetermined deviation value; and

convert the directional deviation of the interventional tool into an actuating variable for triggering an actuator system
to compensate the directional deviation by a reverse control,

wherein the intervention plane is defined by the position of the tip of the interventional tool, the further spatial point
of the interventional tool, and the puncture target when the intervention tool is properly aligned with a desired path of
the intervention tool, and

wherein the image system further comprises a robot that guides the interventional tool introduced from the insertion point
to the puncture target based on the actuating variable.

US Pat. No. 9,760,807

DEEP IMAGE-TO-IMAGE NETWORK LEARNING FOR MEDICAL IMAGE ANALYSIS

Siemens Healthcare GmbH, ...

1. A method for automatically performing a medical image analysis task on a medical image of a patient, comprising:
receiving an input medical image of a patient; and
automatically generating an output image that provides a result of a target medical image analysis task on the input medical
image using a trained deep image-to-image network (DI2IN), wherein the DI2IN uses a conditional random field (CRF) energy
function to estimate the output image based on the input medical image and uses a trained deep learning network to model unary
and pairwise terms of the CRF energy function, wherein automatically generating the output image that provides the result
of the target medical image analysis task on the input medical image using the DI2IN comprises:

generating an image pyramid with a plurality of reduced resolution images of the input medical image at an original resolution;
generating a respective output image that provides a result of the target medical image analysis task on each of the reduced
resolution images of the input medical image using a sequence of trained DI2INs;

dividing the input medical image at the original resolution into a plurality of parts;
generating a respective output image that provides a result of the target medical image analysis task on each of the plurality
of parts of the original resolution input medical image using a respective trained DI2IN for each of the plurality of parts;
and

aggregating the output images that provide the results of the target medical image analysis task on each of the plurality
of parts to generate a final output image that provides the result of the target medical image analysis task on the input
medical image.

US Pat. No. 9,754,404

METHOD FOR GENERATING DISPLAY IMAGE DATA

Siemens Healthcare GmbH, ...

1. A method for generating a 3D image data set of a volume to be examined, in which at least part of a foreign object is positioned,
which comprises the steps of:
recording a set of 2D projection images;
detecting image regions having the foreign object in at least two 2D projection images of the set of 2D projection images;
segmenting the image regions having the foreign object in the at least two 2D projection images resulting in segmented image
regions;

incorporating a marking assigned to the segmented image regions in the at least two 2D projection images; and
using the 2D projection images, including the at least two 2D projection images each having the marking, for a reconstruction
of the 3D image data set containing the marking.

US Pat. No. 9,684,982

ISOTROPIC VOLUME RECONSTRUCTION FROM MULTIPLE 2D SCANS USING SUPER-RESOLUTION TECHNIQUES

Siemens Healthcare GmbH, ...

1. A computer-implemented method for performing isotropic reconstruction of Magnetic Resonance Imaging (MRI) data, the method
comprising:
receiving a stack of slices acquired by an MRI device in two or more directions;
reslicing the stack of slices into:
an acquired view stack comprising high-resolution slices acquired in-plane, and
a reslice stack comprising degraded slices acquired out of plane;
generating an estimated slice profile based on the stack of slices;
convolving the acquired view stack with the estimated slice profile to yield a simulated distorted slice stack;
subtracting the simulated distorted slice stack from the acquired view stack to yield a high-frequency band estimate; and
combining the high-frequency band estimate with the reslice stack to yield isotropic reconstruction results,
wherein the estimated slice profile is based on a division of a Fourier transformation of the acquired view stack and a Fourier
transformation of the reslice stack.

US Pat. No. 9,665,687

ADAPTIVE IMAGING SYSTEM WORKFLOW AND USER INTERFACE SYSTEM

Siemens Healthcare GmbH, ...

12. A computer-implemented method for configuring a medical imaging system using utilization information, comprising:
using an imaging controller to control operation of an imaging device to perform particular imaging system functions according
to a task sequence to acquire imaging data;

storing records in at least one repository, indicating usage and an associated time of usage, of said particular imaging system
functions performed on the imaging device;

analyzing, by a usage processor of a computer, said records to determine,
(a) frequency of usage of particular imaging system functions, and
(b) a sequence of usage of said particular imaging system functions and provide utilization data, by identifying in said records
particular text strings using predetermined information associating predetermined text strings with corresponding imaging
system functions;

using, by the usage processor, the utilization data to create an adapted task sequence which minimizes user interactions and
time to perform said particular imaging system functions wherein creation of the adapted task sequence is performed by at
least one of,

(i) changing a sequence of tasks a user is prompted with,
(ii) adding a task to a task sequence of a user,
(iii) deleting a task of a task sequence of a user, and
(iv) modifying a task of a task sequence of a user; and
presenting at least one image corresponding to the adapted task sequence on a user interface device, and
in response to receiving user-selection of the adapted task sequence, performing the particular imaging system functions according
to the adapted task sequence on the imaging device.

US Pat. No. 9,824,491

DATA DRIVEN FRAMEWORK FOR OPTIMIZING ARTIFICIAL ORGAN PRINTING AND SCAFFOLD SELECTION FOR REGENERATIVE MEDICINE

Siemens Healthcare GmbH, ...

1. A method for generating a personalized organ model for an individual, the method comprising:
acquiring images of an anatomy of interest corresponding to an organ;
acquiring test results related to the anatomy of interest;
determining one or more current functional specifications based on the images and test results;
identifying a mapping function which describes a relationship between the one or more current functional specifications and
printer parameters corresponding to a three-dimensional bio-printer;

selecting one or more desired output characteristics;
generating a set of optimal printer parameters by optimizing the mapping function according to the one or more desired output
characteristics; and

using the three-dimensional bio-printer to print a personalized organ replacement according to the set of optimal printer
parameters.

US Pat. No. 9,730,643

METHOD AND SYSTEM FOR ANATOMICAL OBJECT DETECTION USING MARGINAL SPACE DEEP NEURAL NETWORKS

Siemens Healthcare GmbH, ...

1. A method for anatomical object detection in a 3D medical image of a patient, comprising:
receiving a 3D medical image of a patient including a target anatomical object; and
detecting a 3D pose of the target anatomical object in the 3D medical image in a series of marginal parameter spaces of increasing
dimensionality using a respective trained sparse deep neural network for each of the marginal parameter spaces, wherein each
respective trained sparse deep neural network inputs hypothesis image patches in the respective marginal parameter space,
samples voxels in each hypothesis image patch in a sparse sampling pattern adaptively learned during training of the respective
trained sparse deep neural network, and calculates, for each hypothesis image patch, a probability that the hypothesis image
patch is an image patch of the target anatomical object in the respective marginal parameter space based on the voxels sampled
in the hypothesis image patch in the sparse sampling pattern.

US Pat. No. 9,750,956

DETERMINING AN IRRADIATION PLAN FOR A PARTICLE IRRADIATION UNIT

SIEMENS HEALTHCARE GMBH, ...

1. A method for determining an irradiation plan for a particle irradiation unit, wherein the particle irradiation unit is
used to irradiate a target volume within an examination object with a particle beam depending on the irradiation plan, the
method comprising:
prescribing the target volume and a predetermined dose distribution; and
determining the irradiation plan in order to apply the particle beam in accordance with the predetermined dose distribution
in the target volume, the target volume comprising a plurality of isoenergy layers,

wherein a boundary condition is prescribed for at least one of the isoenergy layers,
wherein the irradiation plan is determined such that the boundary condition for the at least one isoenergy layer is observed,
wherein the boundary condition comprises at least one of the following conditions:
a minimum peak energy,
a maximum peak energy,
a minimum number of raster points,
a minimum overall number of particles,
a minimum overall dose,
a minimum dose contribution to an overall dose to be applied,
a minimum contribution to a target function calculated for determining the irradiation plan, and
a minimum dose compensation error, wherein the dose compensation error specifies an error that occurs as a result of the non-irradiation
of the respective isoenergy layer despite corresponding compensation by the irradiated isoenergy layers, and

wherein at least one individual boundary condition is prescribed for each isoenergy layer of the plurality of isoenergy layers.

US Pat. No. 9,524,582

METHOD AND SYSTEM FOR CONSTRUCTING PERSONALIZED AVATARS USING A PARAMETERIZED DEFORMABLE MESH

Siemens Healthcare GmbH, ...

1. A method of generating a personalized 3D avatar mesh of a human subject from a depth camera image for medical imaging scan
planning, comprising:
converting a depth camera image of a subject to a 3D point cloud;
detecting a plurality of anatomical landmarks in the 3D point cloud;
initializing a 3D avatar mesh by aligning a template mesh to the 3D point cloud based on the detected anatomical landmarks;
and

generating a personalized 3D avatar mesh of the subject by optimizing the 3D avatar mesh using a trained parametric deformable
model (PDM)
wherein generating a personalized 3D avatar mesh of the subject by optimizing the 3D avatar mesh using a trained parametric
deformable model (PDM) comprises:
optimizing parameters of the trained PDM that control a pose and shape of the 3D avatar mesh and locations of vertices of
the 3D avatar mesh to minimize a cost function, and wherein the cost function includes a table constraint that causes the
optimization to move vertices of the 3D avatar above a table on which the subject is lying.

US Pat. No. 9,510,756

METHOD AND SYSTEM FOR DIAGNOSIS OF ATTENTION DEFICIT HYPERACTIVITY DISORDER FROM MAGNETIC RESONANCE IMAGES

Siemens Healthcare GmbH, ...

1. A method for automated diagnosis of attention deficit hyperactivity disorder (ADHD), comprising:
extracting anatomical features from a structural magnetic resonance image (MRI) of a patient;
extracting functional features from a resting-state functional MRI (rsFMRI) series of the patient, comprising:
extracting an rsFMRI time series for each of a plurality of brain regions by mapping voxels in each of a plurality of image
volumes in the rsFMRI series to a plurality of brain regions and extracting an rsFMRI time series for each brain region based
on the voxels mapped to that brain region in the plurality of image volumes in the rsFMRI series by calculating, for each
of M brain regions, an average of voxels mapped to that brain region in each of N image volumes in the rsFMRI series, resulting
in an M ×N matrix including the rsFMRI time series for each of the brain regions, and

extracting the functional features based on the rsFMRI time series for each of the plurality of brain regions; and
determining an ADHD diagnosis for the patient based on the anatomical features, the functional features, and phenotypic features
of the patient using a trained machine learning classifier.

US Pat. No. 9,746,538

REFERENCE OVERSAMPLING IN SENSE-TYPE MAGNETIC RESONANCE RECONSTRUCTION

Siemens Healthcare GmbH, ...

1. A method for magnetic resonance imaging, the method comprising:
assigning a reduced field of view for regularized sensitivity encoding (SENSE) reconstruction, the reduced field of view being
reduced from an entire patient to a sub-region of the patient along at least one spatial dimension;

performing, with a magnetic resonance system, a reference scan for the regularized sensitivity encoding (SENSE) reconstruction;
oversampling the reference scan during the performing, the oversampling being in a direction of the reduced field of view;
determining coil sensitivity of a coil of the magnetic resonance system from the oversampled reference scan for a field of
view larger than the reduced field of view so that the determined coil sensitivity covers a region greater than the sub-region
along the direction;

performing the regularized SENSE reconstruction as a function of the coil sensitivity; and
generating a magnetic resonance image from the SENSE reconstruction.

US Pat. No. 9,761,042

METHOD FOR STREAMING-OPTIMIZED MEDICAL RAYTRACING

Siemens Healthcare GmbH, ...

1. A method for streaming-optimized volume rendering of a 3D medical volume, comprising:
setting view parameters for a 2D projection of the 3D medical volume based on a received user input;
determining respective optimal rendering parameters for each of a plurality of rendering stages; and
generating output 2D projection images corresponding to the view parameters in each of the plurality of rendering stages by:
performing, by each of one or more rendering contexts, one or more rendering passes of a progressive volume rendering algorithm
on the 3D volume, to generate a respective rendered image, and

compositing, by a display context, the rendered images generated by the one or more rendering contexts,
wherein in each respective one of the plurality of rendering stages, the one or more rendering contexts and the display context
are configured using the respective optimal rendering parameters determined for that rendering stage, wherein the plurality
of rendering stages include an interaction stage, a visual quality refinement stage, and a final assessment stage, and wherein
determining respective optimal rendering parameters for each of a plurality of rendering stages comprises:

setting the optimal rendering parameters for the final assessment stage to configure the one or more rendering contexts to
each perform a plurality of rendering passes of the progressive rendering algorithm per each refinement of the output 2D projection
image and to reduce a frequency of memory transfers between the rendering contexts and the display context.

US Pat. No. 9,629,563

METHOD AND SYSTEM FOR FUNCTIONAL ASSESSMENT OF RENAL ARTERY STENOSIS FROM MEDICAL IMAGES

Siemens Healthcare GmbH, ...

15. An apparatus for assessment of renal artery stenosis, comprising:
a processor; and
a memory storing computer program instructions, which when executed by the processor cause the processor to perform operations
comprising:

generating a patient-specific anatomical model of at least a portion of the renal arteries and aorta from medical image data
of a patient;

estimating patient-specific boundary conditions of a computational model of blood flow in the portion of the renal arteries
and aorta based on the patient-specific anatomical model;

simulating blood flow and pressure in the portion of the renal arteries and aorta using the computational model based on the
patient-specific boundary conditions; and

calculating at least one hemodynamic quantity characterizing functional severity of a renal stenosis region based on the simulated
blood flow and pressure in the portion of the renal arteries and aorta,

wherein the computational model comprises a reduced order stenosis pressure-drop model representing the renal stenosis region
coupled to a one-dimensional computational model representing a renal artery and the reduced order stenosis pressure-drop
model calculates a pressure drop across the renal stenosis region as a sum of a viscous term, a turbulent term, and an inertance
term.

US Pat. No. 10,115,039

METHOD AND SYSTEM FOR MACHINE LEARNING BASED CLASSIFICATION OF VASCULAR BRANCHES

Siemens Healthcare GmbH, ...

1. A method for machine learning based classification of vascular branches to distinguish falsely detected branches from true branches, comprising:sampling a plurality of overlapping fixed size branch segments from one or more branches of a detected centerline tree of a target vessel extracted from a medical image of a patient;
extracting a plurality of 1D profiles along each of the plurality of overlapping fixed size branch segments;
calculating a probability score for each of the plurality of overlapping fixed size branch segments based on the plurality of 1D profiles using a trained deep neural network classifier;
assigning a final probability score to each of a plurality of centerline points in the one or more branches of the detected centerline tree of the target vessel based on the probability scores of the overlapping fixed size branch segments containing that centerline point; and
pruning the one or more branches of the detected centerline tree of the target vessel based on the final probability scores of the plurality of centerline points in the one or more branches of the detected centerline tree of the target vessel to remove falsely detected branches from true branches in the one or more branches of the detected centerline tree of the target vessel.

US Pat. No. 9,846,926

HIGH QUALITY EMBEDDED GRAPHICS FOR REMOTE VISUALIZATION

Siemens Healthcare GmbH, ...

1. A method for rendering embedded graphics for remote visualization, the method comprising:
rendering, by a server, a two-dimensional volume rendered image from three-dimensional data captured for a volume;
rendering, by the server, a two-dimensional graphic rendered image to be embedded in the two-dimensional volume rendered image
from three-dimensional data for a graphical object, the two-dimensional graphic rendered image only containing volume rendered
pixels covered in the two-dimensional volume rendered image by the graphical object;

compressing, by the server, the volume rendered image and the graphic rendered image; and
transmitting, to a workstation over a network, the compressed volume rendered image and the compressed graphic rendered image.

US Pat. No. 9,767,385

MULTI-LAYER AGGREGATION FOR OBJECT DETECTION

Siemens Healthcare GmbH, ...

1. A method for object detection, the method comprising:
obtaining images of an object;
defining an input layer and a plurality of sequential feature layers subsequent to the input layer of a multi-layer feature
learning network, features from the input layer provided directly to a first of the sequential feature layers, features from
each of the sequential feature layers provided directly to a next of the sequential feature layers, the sequential feature
layers comprising hidden layers;

providing an aggregator layer receiving the features directly from multiple layers of the sequential feature layers of the
multi-layer feature learning network, the features from different ones of the sequential feature layers provided to subsequent
ones of the sequential feature layers and also provided directly to the aggregator layer without processing by the subsequent
ones, the aggregator layer aggregating the received features;

optimizing, jointly and by a processor, the multi-layer feature learning network and the aggregator layer using the images
of the object; and

outputting, by the processor, a set of learned features represented by the optimized multi-layer feature learning network
and a detector that makes use of the generated features by the optimized aggregator layer, the set of learned features being
for distinguishing the object and the detector being for classifying the object.

US Pat. No. 10,034,267

METHOD AND APPARATUS FOR LOCALIZING COMPONENTS AND/OR PERSONS ASSIGNED TO AN IMAGE RECORDING SCANNER IN A SPATIAL ENVIRONMENT

Siemens Healthcare GmbH, ...

1. A method for localizing items associated with a medical image recording scanner, said method comprising:providing and uniquely assigning a wireless transmit device to each of a plurality of items, which are associated with operation of a medical image recording scanner, that are separable from but are situated in an environment of the medical image recording scanner, said items being selected from the group consisting of components that are optionally usable in said operation of said medical image recoding scanner, components of said medical image recording scanner that are exchangeable with other components of said medical image recording scanner, and persons to be examined by said operation of said medical image recording scanner;
with at least one receive device situated in said environment receiving at least one localization signal from a respective transmit device that identifies the respective transmit device as a transmitting transmit device;
providing said localization signal from said at least one receive device to a computer and, in said computer, identifying, and determining position information of, the item uniquely associated with the transmitting transmit device;
emitting an output signal from said computer that electronically represents said position information in a form allowing recall of the item uniquely associated with the transmitting transmit device; and
registering said items in said computer and, if a localization signal from an item is not received, emitting a warning signal that indicates an inability to localize that item.

US Pat. No. 9,588,208

METHODS, SYSTEMS AND APPARATUSES FOR RAPID SEGMENTED, ACCELERATED, AND SIMULTANEOUS MULTI-SLICE ECHO PLANAR IMAGING

1. A method for accelerated segmented magnetic resonance (MR) image data acquisition, the method comprising:
using a plurality of Radio Frequency (RF) pulses to excite one or more slices of an anatomical area of interest according
to a predetermined slice acceleration factor;

acquiring a collapsed image of the one or more slices in response to the plurality of RF pulses, wherein each of the one or
more slices is individually acquired using a consecutive segment acquisition process; and

applying a parallel image reconstruction method to the collapsed image to separate the collapsed image into a plurality of
slice images.

US Pat. No. 10,109,050

SPATIOTEMPORAL BACKGROUND PHASE CORRECTION FOR PHASE CONTRAST VELOCITY ENCODED MRI

Siemens Healthcare GmbH, ...

1. A computer-implemented method for performing spatiotemporal background phase correction for phase contrast velocity encoded magnetic resonance imaging, the method comprising:performing, by a magnetic resonance imaging scanner, a phase contrast magnetic resonance imaging scan of a region of interest within a patient to yield a complex image of the region of interest on a display device;
calculating a plurality of filter cut-off frequencies based on physiological limits associated with the patient;
creating a spatiotemporal filter based on the plurality of filter cut-off frequencies;
applying the spatiotemporal filter to the complex image to yield a low-pass filtered complex image; and
performing complex division using the complex image and the low-pass filtered complex image to yield a corrected image of the region of interest on the display device.

US Pat. No. 10,031,197

METHOD AND APPARATUS FOR ACQUIRING MAGNETIC RESONANCE SIGNALS OF AN EXAMINATION OBJECT

Siemens Healthcare GmbH, ...

1. A method for acquiring magnetic resonance signals from an examination subject, comprising:operating a magnetic resonance data acquisition scanner, comprising a radio-frequency (RF) emitter and a gradient coil arrangement, while an examination subject is situated in the scanner, to radiate an RF excitation pulse from said RF emitter while activating a first gradient switching operation with said gradient coil arrangement;
operating said RF emitter to radiate an RE refocusing pulse while activating a second gradient switching operation with said gradient coil arrangement, with said second gradient switching operation having an opposite polarity to said first gradient switching operation, and with at least one of said first gradient switching operation and said second gradient switching operation having an amplitude modulation during radiation of the RF excitation pulse or the RF refocusing pulse said amplitude modulation of said at least one of said first and second gradient switching operations comprising making a value of an amplitude of said at least one of said first and second gradient switching operations to be lower in a temporal central region of said at least one of said first and second gradient switching operations than in a temporal edge region of said at least one of said first and second gradient switching operations; and
operating the scanner to acquire magnetic resonance signals emitted by nuclear spins of said examination object that were excited by said RF excitation pulse and refocused by said RF refocusing pulse.

US Pat. No. 10,031,203

METHOD AND APPARATUS FOR RECONSTRUCTING IMAGE DATA FROM UNDERSAMPLED RAW MAGNETIC RESONANCE DATA AND REFERENCE DATA

Siemens Healthcare GmbH, ...

1. A method for reconstructing image data of an object from undersampled raw data and reference data, said method comprising:providing undersampled raw data to a computer, said undersampled raw data having been acquired from an examination region of an object by operating a magnetic resonance data acquisition scanner with a magnetic resonance control sequence, to which a reconstruction algorithm is assigned for reconstructing image data from the raw data;
also providing said computer with reference data;
in said computer, determining a disturbance variable in said examination region, said disturbance variable being a frequency deviation;
in said computer, establishing a modulation function that describes an influence of the disturbance variable on the magnetic resonance control sequence;
in said computer, generating modulated reference data from the modulation function and the reference data, such that said modulated reference data are subjected to the influence that the disturbance variable has on the raw data;
in said computer, executing a combination algorithm in order to reconstruct image data from said undersampled raw data using said modulated reference data; and
making the image data available in electronic form from the computer as a data file.

US Pat. No. 9,999,399

METHOD AND SYSTEM FOR PIGTAIL CATHETER MOTION PREDICTION

Siemens Healthcare GmbH, ...

1. A method for predicting motion of a pigtail catheter in a fluoroscopic image sequence, comprising:fitting parameters of an autoregressive model based on observed pigtail catheter tip positions in a plurality of previous frames of the fluoroscopic image sequence;
predicting a pigtail catheter tip position in a current frame of the fluoroscopic image sequence using the autoregressive model; and
detecting the pigtail catheter tip position in the current frame based on the predicted pigtail catheter tip position using a trained learning-based pigtail catheter tip detector, wherein the detection of the pigtail catheter tip position in the current frame by the trained learning-based pigtail catheter tip detector is constrained by the predicted pigtail catheter tip position in the current frame and the step of detecting the pigtail catheter tip position in the current frame based on the predicted pigtail catheter tip position using a trained learning-based pigtail catheter tip detector comprises:
detecting pigtail catheter tip position candidates in the current frame using the trained learning-based pigtail catheter tip detector, and
penalizing a detection score calculated for each of the detected pigtail catheter tip position candidates by the trained pigtail catheter tip detector based on a penalty function centered at the predicted pigtail catheter tip position, wherein the penalty function is a 2D Gaussian distribution centered at the predicted pigtail catheter tip position.

US Pat. No. 9,888,889

INTERVENTIONAL IMAGING SYSTEM

Siemens Healthcare GmbH, ...

1. An interventional imaging system, comprising:
an intervention instrument comprising at least two position markings;
an imaging device that repeatedly records intervention data of a body including image projections of the position markings;
a navigation facility that loads pre-intervention data of the body including image projection of an intervention location
and mutually registers the pre-intervention data with the intervention data;

a display apparatus that displays the registered intervention data including the image projection of the intervention location
and the image projections of the position markings of the intervention instrument; and

a robot arm that is controlled by the navigation facility for guiding the intervention instrument until the image projections
of the position markings cover one another and also cover the image projection of the intervention location displayed on the
display apparatus,

wherein the navigation facility repeatedly calculates position and orientation of the intervention instrument from the repeatedly
recorded intervention data based on parameters comprising distance interval between the image projections of the position
markings and/or geometry deformation of the image projections of the position markings in comparison with actually known distance
interval between the position markings and known geometry of the position markings arranged on the intervention instrument,

wherein the navigation facility repeatedly compares the calculated position and orientation of the intervention instrument
with position and orientation of the intervention location,

wherein the navigation facility repeatedly determines a movement proposal for the intervention instrument towards to the intervention
location based on the comparison, and

wherein the robot arm repeatedly guides a movement of the intervention instrument based on the repeatedly determined movement
proposal until a final planned position and orientation of the intervention instrument aligns with the position and orientation
of the intervention location.

US Pat. No. 9,767,557

METHOD AND SYSTEM FOR VASCULAR DISEASE DETECTION USING RECURRENT NEURAL NETWORKS

Siemens Healthcare GmbH, ...

1. A method for vascular disease detection using a recurrent neural network, comprising:
extracting a plurality of 2D cross-section image patches from a 3D computed tomography angiography (CTA) image, wherein each
of 2D cross-section image patches is extracted at a respective one of a plurality of sampling points along a vessel centerline
of a vessel of interest in the 3D CTA image; and

detecting vascular abnormalities in the vessel of interest by classifying each of the plurality of sampling points along the
vessel centerline based on the plurality of 2D cross-section image patches using a trained recurrent neural network (RNN).

US Pat. No. 9,761,004

METHOD AND SYSTEM FOR AUTOMATIC DETECTION OF CORONARY STENOSIS IN CARDIAC COMPUTED TOMOGRAPHY DATA

Siemens Healthcare GmbH, ...

1. A method for detecting coronary stenosis in a cardiac computed tomography (CT) volume, comprising:
obtaining at least one coronary artery centerline in said CT volume, said at least one coronary artery centerline comprising
a plurality of control points;

detecting stenosis regions along said at least one coronary artery centerline in said CT volume by classifying each of said
plurality of control points as a stenosis point or a non-stenosis point using a trained machine learning based classifier;
and

displaying CT images with a visual indication of the control points classified as stenosis points.

US Pat. No. 9,684,979

MRI 3D CINE IMAGING BASED ON INTERSECTING SOURCE AND ANCHOR SLICE DATA

Siemens Healthcare GmbH, ...

1. A method of three-dimensional (3D), cine, magnetic resonance (MR) imaging of a volume undergoing repetitive motion, the
method comprising:
obtaining source MR slice data indicative of a plurality of source slices of the volume during the repetitive motion;
obtaining anchor MR slice data indicative of an anchor slice of the volume during the repetitive motion, the anchor slice
intersecting the plurality of source slices;

reconstructing, with a processor, the source MR slice data and the anchor MR slice data; and
generating, with the processor, for each phase of the repetitive motion, volume data based on a respective subset of the reconstructed
source MR slice data;

wherein, for each phase of the repetitive motion, generating the volume data comprises:
selecting the respective subset of slices of the plurality of source slices based on a correlation of the reconstructed source
MR slice data and the reconstructed anchor MR slice data along a respective intersection between each source slice of the
plurality of source slices and the anchor slice; and

correcting the reconstructed source MR slice data of the selected subset of source slices for misalignment with the reconstructed
anchor MR slice data.

US Pat. No. 9,646,361

INITIALIZATION INDEPENDENT APPROACHES TOWARDS REGISTRATION OF 3D MODELS WITH 2D PROJECTIONS

Siemens Healthcare GmbH, ...

1. A computer implemented method of registering a 3-dimensional (3D) model of a coronary artery tree with two or more 2-dimensional
(2D) images, the method executed by a computer comprising the steps of:
solving for matrices R, Pi, i=1, . . . , N, that minimize a cost function ?i=1N??iRX?IiPi?2,1 subject to constraints that R?conv(SO(3)), Pi?[0,1]ni×m, and Pi1?1, 1TPi=1, for i?{1, N},
wherein N is a number of 2D images, R is a rotation matrix, conv(SO(3)) denotes a convex hull of the special orthogonal group
in 3 dimensions, X denotes a 3D centerline model of a coronary artery tree with m points, Ii denotes the ith 2D image with ni points, ?i denotes a transformation between the 3D centerline model X and the ith 2D image Ii, 1 is an all-ones vector, Pi is a permutation matrix whose values represent a probability of a point in the ith 2D image Ii corresponding to a point in the 3D centerline model X, and the subscript 2,1 refers to a mixed l2/l1 norm; and
rounding a solution R to a nearest orthogonal matrix R* in SO(3);
wherein R* aligns the 3D centerline model X of the coronary artery tree with 2D fluoroscopic images acquired during a percutaneous
coronary intervention procedure.

US Pat. No. 9,642,551

EVALUATING ATRIO-VENTRICULAR CONDUCTION IN A HEART

Siemens Healthcare GmbH, ...

1. A method of evaluating Atrial-Ventricular (A-V) conduction in a heart of an individual, the method comprising:
receiving, from leads, signal data sensed from the heart during an atrial stimulation of the heart, wherein the sensed signal
data comprises data associated signals selected from the group consisting of RAproxy signal, RAdistal signal, Hisproxy signal, Hisdistal signal, RVproxy signal, RVdistal signal and an electro-cardiogram (ECG) signal;

computing, by a processor, an Atrium-Hision (A-H) interval corresponding to an extra-stimulus event during the atrial stimulation
of the heart using the sensed signal data;

determining, by the processor, a difference between the A-H interval corresponding to the extra-stimulus event and an A-H
interval corresponding to a preceding extra-stimulus event; and

automatically determining, by the processor, presence of an A-H jump based on the determined difference and generating an
alert indicating the presence of the A-H jump.

US Pat. No. 10,088,544

TRACTOGRAPHY FRAMEWORK WITH MAGNETIC RESONANCE IMAGING FOR BRAIN CONNECTIVITY ANALYSIS

Siemens Healthcare GmbH, ...

1. A method for tractography with magnetic resonance imaging, the method comprising:scanning a patient with a magnetic resonance imaging system for diffusion weighted data, the scanning providing data without diffusion sensitization and in phase-encoded and reverse phase encoded directions, the diffusion weighted data being in a subject space;
acquiring, with the magnetic resonance imaging system, structural magnetic resonance data;
correcting the diffusion weighted data with field maps estimated from the data acquired in the phase encoding and reverse phase encoding directions;
denoising the corrected diffusion weighted data;
registering a first atlas of tract maps to the subject space;
identifying regions of interest through which tracts of the tract maps pass from a second atlas;
generating a tractogram for the patient from the denoised, corrected diffusion weighted data, the tract maps, and the regions of interest; and
transmitting an image of the tractogram.

US Pat. No. 10,052,033

SYSTEM AND METHOD FOR MOTION-ROBUST 3D MAGNETIC RESONANCE IMAGING OF VESSEL WALLS

Siemens Healthcare GmbH, ...

1. A method for 3D imaging of blood vessels in a magnetic resonance (MR) system, comprising the steps of:(a) generating a 3D image data set from a volume of a subject to be imaged using an imaging pulse sequence, wherein:
(i) the imaging pulse sequence comprises a plurality of imaging series;
(ii) each imaging series comprises a dark-blood sequence, a fat-suppression sequence, and a data readout sequence that follows both the dark-blood sequence and the fat-suppression sequence;
(iii) each data readout sequence samples data along a plurality of lines in k-space, wherein each line of the plurality of lines has a common radial direction in the Kx-Ky plane and a different Kz value, and passes through the Kz axis; and
(iv) data readout sequences corresponding to different series of the imaging pulse sequence sample lines in k-space having different radial directions in the Kx-Ky plane, and
(b) generating an image of at least a portion of the volume based at least in part on the 3D image data set.

US Pat. No. 10,048,334

TEST OF A REORDERING ALGORITHM OF A SPIN ECHO MAGNETIC RESONANCE PULSE SEQUENCE

Siemens Healthcare GmbH, ...

1. A method that evaluates k-space data acquired by the operation of a magnetic resonance (MR) apparatus, said method comprising:operating an MR data acquisition scanner, while a subject is situated therein, in order to execute a spin echo MR data acquisition sequence in which a plurality of individual echoes are acquired from the subject in each of a plurality of echo trains, and in which each echo train is phase-encoded by a phase-encoding gradient, each individual echo having a signal intensity and having a sequence position in the echo train in which that individual echo was acquired;
using a computer to enter said individual echoes into a memory organized as k-space, as k-space data, so that said individual echoes occupy original positions in k-space according to said phase-encoding, thereby producing a signal evolution of said signal intensity of said individual echoes with regard to the respective original positions of said individual echoes in k-space determined by said phase-encoding;
in said computer, executing a reordering algorithm that changes the respective original positions in k-space in to reordered positions respectively occupied by said individual echoes, in order to reduce artifacts in an MR image that is reconstructed from said k-space data, due to said signal intensity impermissibly changing by an amount of change that was calculated in said reordering algorithm over a number of said original positions that were changed in said reordering algorithm, and thereby causing said individual echoes to be situated at said reordered positions in k-space;
in said computer, testing said reordered positions by comparing, for a selected k-space element, a sequence position of the individual echo represented in the selected k-space element to the sequence position of the individual echo represented in a k-space element that is adjacent in k-space, to said selected k-space element, said sequence position of said adjacent k-space element being either a sequence position of the individual echo represented in the adjacent k-space element in a same echo train of, or a different echo train from, the echo train of the individual echo represented in said selected k-space element and, when said selected position of the individual echo represented in said selected k-space element exceeds a predetermined amount of change from the sequence position of the individual echo represented in said adjacent k-space element, generating an error message in said computer;
in said computer, in response to said generated error message, modifying said reordering algorithm and applying the modified reordering algorithm to said original positions of said individual echoes in k-space, and again testing the reordered positions produced by said modified reordering algorithm, and then subsequently repeating said testing and said modifying until said predetermined amount of change is not exceeded; and
making the k-space data, that has been organized in k-space according to the reordering algorithm for which said predetermined amount of change is not exceeded, available as a data file from said computer in a form which allows the reconstruction of said MR image therefrom.

US Pat. No. 9,983,319

DETECTION LAYER COMPRISING PEROVSKITE CRYSTALS

SIEMENS HEALTHCARE GMBH, ...

1. A detector comprising:at least two electrodes and,
at least one detection layer between the at least two electrodes, the at least one detection layer comprising:
perovskite crystals of the type ABX3 and/or AB2X4;
where A comprises at least one monovalent, divalent or trivalent element from the fourth or a higher period in the periodic table and/or mixtures thereof;
B comprises a monovalent cation, the volumetric parameter of which is sufficient, with the respective element A, for perovskite lattice formation; and
X is selected from the group consisting of anions of halides and pseudohalides;
wherein the at least one detection layer has a thickness of at least 10 ?m; and
wherein the perovskite crystals have a crystal size of 1-10 ?m.

US Pat. No. 9,945,919

SYSTEMS AND METHODS FOR REAL TIME GRADIENT TIMING MODIFICATION

Siemens Healthcare GmbH, ...

1. A method for modified gradient timing in a Magnetic Resonance (MR) imaging system, the method comprising:generating radio frequency (RF) excitation pulses in a volume of patient anatomy to provide subsequent acquisition of associated RF echo data;
generating a sequence of gradient waveforms on a static magnetic field in three directions each orthogonal to each other for slice selection, phase encoding and readout RF data acquisition in the volume of patient anatomy;
receiving, by a controller, an indication of the sequence of gradient waveforms to be applied to a plurality of gradient coils;
selecting limits comprising hardware limits of system components and waveform limits;
setting one or more optimization criteria based on the limits, wherein the optimization criteria comprises plurality of optimization parameters and, for each optimization parameter, an indication of whether the optimization parameter (i) cannot be modified during optimization; (ii) can be modified during optimization within a range of values; or (ii) can be modified during optimization within the hardware limits of the system;
selecting an optimization algorithm from a plurality of optimization algorithms based on the optimization criteria;
modifying, via the controller, the sequence of gradient waveforms to be applied to the plurality of gradient coils using the selected optimization algorithm;
calculating a sequence of modified gradient waveforms; and
providing the sequence of modified gradient waveforms to the plurality of gradient coils.

US Pat. No. 9,922,272

DEEP SIMILARITY LEARNING FOR MULTIMODAL MEDICAL IMAGES

Siemens Healthcare GmbH, ...

1. A method for similarity metric learning for multimodal medical image data, the method comprising:
receiving a first set of image data of a volume, wherein the first set of image data is captured with a first imaging modality;
receiving a second set of image data of the volume, wherein the second set of image data is captured with a second imaging
modality;

aligning the first set of image data and the second set of image data;
training a first set of parameters with a multimodal stacked denoising auto encoder to generate a shared feature representation
of the first set of image data and the second set of image data, the multimodal stacked denoising auto encoder comprising
a first layer with independent and parallel denoising auto encoders;

training a second set of parameters with a denoising auto encoder to generate a transformation of the shared feature representation;
initializing, using the first set of parameters and the second set of parameters, a neural network classifier;
training, using training data from the aligned first set of image data and the second set of image data, the neural network
classifier to generate a similarity metric for the first and second imaging modalities, the similarity metric identifying
which voxels from the first set of image data that correspond to the same position in the volume as voxels from the second
set of image data; and

performing image fusion on the first set of image data and the second set of image data using the identified voxels.

US Pat. No. 9,901,312

MEDICAL INSTRUMENT FOR USE WITH A PHASE CONTRAST IMAGING AND X-RAY RECORDING SYSTEM WITH PHASE CONTRAST IMAGING

Siemens Healthcare GmbH, ...

1. A medical instrument for use with a phase contrast imaging, comprising:
at least one component which enables an x-ray image representation,
the at least one component including a tubular base body having a surface;
the tubular base body including a first subarea on a region of the surface that is embodied with a layer of spongy material,
the spongy material including microscopically small porous openings with diameters in the micrometer range defining a structure
of the first subarea;

the tubular base body including a second subarea on another region of the surface that is embodied with a layer of carbon
fiber-reinforced plastic material defining a structure of the second subarea;

the tubular base body including a third subarea inside the tubular base body that is embodied with a foam material, the foam
material including a plurality of gas bubbles defining a structure of the third subarea; and

wherein the structure of each of the first subarea, the second subarea and the third subarea provides a degree of visibility
of the medical instrument in the phase contrast imaging.

US Pat. No. 9,824,302

METHOD AND SYSTEM FOR MODEL-BASED FUSION OF MULTI-MODAL VOLUMETRIC IMAGES

Siemens Healthcare GmbH, ...

1. A method for fusion of multi-modal images, comprising:
receiving a first image acquired using a first imaging modality;
receiving a second image acquired using a second imaging modality; and
jointly estimating a model of a target anatomical structure and a transformation between the first and second images from
the first and second images, wherein both the model of the target anatomical structure and the transformation between the
first and second images are estimated together as a function of both of the first and second images.

US Pat. No. 9,799,135

SEMANTIC CINEMATIC VOLUME RENDERING

Siemens Healthcare GmbH, ...

1. A method for generating a volume rendering, the method comprising:
receiving, by a server over a network, a three-dimensional data set of a volume;
extracting, by the server, semantic information from the three-dimensional data set;
generating, by the server, a volume rendering from the three-dimensional data set and from the extracted semantic information,
wherein generating the volume rendering comprises performing volumetric Monte-Carlo path tracing using the three-dimensional
data set and integrating the extracted semantic information; and

displaying the generated volume rendering.

US Pat. No. 9,754,390

RECONSTRUCTION OF TIME-VARYING DATA

Siemens Healthcare GmbH, ...

1. A non-transitory computer readable medium embodying a program of instructions executable by machine to perform steps for
facilitating iterative data reconstruction, the steps comprising:
(i) receiving a time-varying two-dimensional (2D) image dataset of one or more structures of a biological object of a patient;
(ii) forward projecting temporal volumes in a current estimated time-varying three-dimensional (3D) dataset to obtain 2D attenuation
coefficients, and determining an error between the 2D attenuation coefficients corresponding to the current estimated time-varying
3D dataset and corresponding projection data from the received time-varying 2D image dataset; and

(iii) back projecting the error across the temporal volumes in the current estimated time-varying 3D dataset to adjust the
current estimated time-varying 3D dataset.

US Pat. No. 9,689,949

PHASE UNWRAPPING IN PHASE CONTRAST MR IMAGING

Siemens Healthcare GmbH, ...

1. A method for phase unwrapping in phase contrast magnetic resonance (MR) imaging, the method comprising:
acquiring a sequence of phase contrast MR data representing a patient, the phase contrast MR data comprising first values
representing a location at respective different times, some of the first values being wrapped values and some of the first
values being not wrapped values;

calculating positive and negative values with positive and negative direction unwrapping from the first values for each of
the different times;

determining, for each adjacent pair of the different times, differences between combinations of first, positive, and negative
values between the different times of the adjacent pair;

selecting between the first, positive, and negative values for each of the different times as a function of a minimization
of a sum of the differences across the different times; and

generating an image as a function of the selected first, positive, and negative values.

US Pat. No. 9,576,345

SIMULTANEOUS EDGE ENHANCEMENT AND NON-UNIFORM NOISE REMOVAL USING REFINED ADAPTIVE FILTERING

Siemens Healthcare GmbH, ...

1. A method for denoising magnetic resonance images, the method comprising:
acquiring complex image data from a magnetic resonance imaging device;
generating an inhomogeneous noise-level map representative of an estimated noise level in the complex image data;
using the inhomogeneous noise-level map and the complex image data to compute an adaptive denoising filter;
iteratively applying the adaptive denoising filter to the complex image data and recombine the iterates using polynomial coefficients
to yield a denoised image;

estimating a normalization field;
modulating the inhomogeneous noise-level map by the normalization field prior to applying the adaptive denoising filter to
the complex image data;
selecting a region of interest within the complex image data;
applying a high-pass filter to the complex image data using the region of interest to yield filtered image data;
determining a median absolute deviation of the filtered image data;
applying a noise distribution scaling factor to the median absolute deviation to yield a homogeneous noise level value; and
determining the inhomogeneous noise-level map based on the homogeneous noise level value and the normalization field.

US Pat. No. 9,569,843

PARAMETER-FREE DENOISING OF COMPLEX MR IMAGES BY ITERATIVE MULTI-WAVELET THRESHOLDING

Siemens Healthcare GmbH, ...

1. A method for denoising Magnetic Resonance Imaging (MRI) data, the method comprising:
receiving a noisy image acquired using an MRI imaging device;
determining a noise model comprising a non-diagonal covariance matrix based on the noisy image and calibration characteristics
of the MRI imaging device;

designating the noisy image as a current best image;
performing an iterative denoising process to remove noise from the noisy image, each iteration of the iterative denoising
process comprising:

applying a bank of heterogeneous denoisers to the current best image to generate a plurality of filter outputs,
creating an image matrix comprising the noisy image, the current best image, and the plurality of filter outputs,
finding a linear combination of elements of the image matrix which minimizes a Stein Unbiased Risk Estimation (SURE) value
for the linear combination and the noise model,

designating the linear combination as the current best image,
updating each respective denoiser in the bank of heterogeneous denoisers based on the SURE value; and
following the iterative denoising process, designating the current best image as a final denoised image.

US Pat. No. 9,521,994

SYSTEM AND METHOD FOR IMAGE GUIDED PROSTATE CANCER NEEDLE BIOPSY

Siemens Healthcare GmbH, ...

1. A method, comprising:
a first step of receiving a first image of a prostate in a planning phase, wherein the first image is acquired with a first
imaging modality and is semi-automatically segmented, and wherein a binary mask and contours of the prostate are saved;

a second step of acquiring a second image of the prostate, wherein the second image is acquired with a second imaging modality;
a third step of performing an alignment to compensate for orientation misalignments between the first image and the second
image, wherein the alignment uses user specified point correspondences on the prostate in the first and second images to compute
rough translations and when three or more point correspondences are specified, a rigid registration estimate and an initial
guess for the amount of anatomic deformations is computed automatically;

a fourth step of performing a manual adjustment of the alignment to account for translational misalignments between the first
and second images by dragging slices from the first image to match content of the second image;

a fifth step of acquiring third images of the prostate, wherein the third images are acquired with the second imaging modality
and are compounded into a three-dimensional (3D) image;

a sixth step of using an initial registration between the first and second images resulting from the alignment and the binary
mask from the planning phase to segment the prostate in the compounded 3D image;

a seventh step of performing a second registration and then a third registration different from the second registration on
distance maps generated from boundaries of the segmentations of the prostate in the first and second images;

an eighth step of transforming the first image along with its included annotations and segmentation structures onto the third
images to produce a fourth image;

a ninth step of displaying the fourth image with a region of interest mapped thereon; and
monitoring quality of alignment of the region of interest in the displayed fourth image, and re-running the second step and
the fifth through eighth steps if the quality deteriorates due to patient immobilization or anatomic shifts, or re-running
the second through eighth steps if the quality deteriorates for large misalignments.

US Pat. No. 9,945,964

EVALUATION LOGIC OF AN X-RAY DETECTOR WITH MULTI-LEVEL MULTIPLEXER

SIEMENS HEALTHCARE GMBH, ...

1. An X-ray detector, comprisingan arrangement of detector elements; and
an evaluation logic of the arrangement of detector elements, the evaluation logic including a multi-level first multiplexer, wherein
a plurality of the detector elements are assigned to a first group,
each of the plurality of detector elements of the first group is assigned to an input of a first level of the multi-level first multiplexer,
a total number of the inputs of levels of the multi-level first multiplexer is greater than a total number of outputs of levels of the multi-level first multiplexer, and
a serial output is assigned to an output of a relatively last level of the multi-level first multiplexer.

US Pat. No. 9,915,719

MAGNETIC RESONANCE IMAGING WITH RANDOMLY DISTRIBUTED RECORDING OF RAW DATA

Siemens Healthcare GmbH, ...

1. A method for acquiring magnetic resonance (MR) signals from an examination subject, comprising:
operating an MR scanner to acquire MR signals from a subject in said MR scanner and, during acquisition of said MR signals,
also acquiring movement information representing movement of the subject during the acquisition of said MR signals;

providing said MR signals and said movement information to a processor, and grouping the movement information into different
movement phases of the subject;

from said processor, entering said MR signals into an electronic memory representing raw data space comprised of a plurality
of raw data lines, in order to fill at least a predetermined portion of the raw data space with said MR signals, with said
MR signals for the plurality of raw data lines being acquired according to a temporally randomly distributed sequence;

in said processor, allocating each raw data line in said predetermined portion to one of said movement phases respectively,
by identifying raw data lines in which said subject is in a rest phase of said movement, by identifying the movement phase
comprising the most raw data lines, and reconstructing a reference image of said subject from the MR signals in said raw data
lines in said rest phase, and thereby generating a data file comprising the raw data space filled with said MR signals acquired
according to said temporally randomly distributed sequence; and

making said data file available at an output of said processor in a form allowing reconstruction of an image of the subject
from said MR signals in said data file.

US Pat. No. 9,792,703

GENERATING A SYNTHETIC TWO-DIMENSIONAL MAMMOGRAM

Siemens Healthcare GmbH, ...

1. A method for generating a synthetic two-dimensional mammogram with enhanced contrast for structures of interest, the method
comprising:
acquiring, with a medical scanner, a three-dimensional digital breast tomosynthesis volume having a plurality of voxels;
generating a three-dimensional relevance map that encodes for the plurality of voxels a relevance of an underlying structure
for a diagnosis; and

calculating a synthetic two-dimensional mammogram based on the three-dimensional digital breast tomosynthesis volume and the
three-dimensional relevance map,

wherein calculating the synthetic two-dimensional mammogram is based on ray-casting in the generated three-dimensional relevance
map and the acquired three-dimensional digital breast tomosynthesis volume.

US Pat. No. 9,759,795

SYSTEM FOR REDUCING ARTIFACTS IN IMAGING IN THE PRESENCE OF A SPIN-LOCK RADIO-FREQUENCY FIELD

Siemens Healthcare GmbH, ...

1. A system for acquiring MR imaging data of a portion of patient anatomy associated with spin lattice relaxation time in
a rotating frame, comprising:
an RF (Radio Frequency) signal generator for generating RF excitation pulses in anatomy and enabling subsequent acquisition
of associated RF echo data; and

a magnetic field gradient generator for generating anatomical volume select magnetic field gradients for phase encoding and
readout RF data acquisition in a three dimensional (3D) anatomical volume, said RF signal generator and said gradient generator
using in order,

a saturation pulse,
a T1 spin lattice relaxation rotating frame preparation pulse sequence and
a spoiler gradient, in acquiring image data of the 3D volume showing luminance contrast associated with T1 spin lattice relaxation
in a rotating frame.

US Pat. No. 9,687,172

SYSTEM FOR MOTION CORRECTED MR DIFFUSION IMAGING

National Institute of Hea...

1. A system for determining motion correction data for use in diffusion MR imaging of an anatomical volume, comprising:
an RF (Radio Frequency) signal generator configured to generate RF excitation pulses in an anatomical region of interest to
facilitate subsequent acquisition of associated RF echo data; and

a magnetic field gradient generator configured to generate anatomical slice specific magnetic field gradients for phase encoding
and readout RF data acquisition,

wherein said RF signal generator and said gradient generator are configured to sequentially acquire a first slice set and
a second slice sets in a single first direction through said volume,

wherein each of the first slice set and the second slice set comprises a plurality of individual diffusion image slices,
wherein the slices of the first slice set are spatially interleaved with the slices of the second slice set within said volume,
and

wherein said RF signal generator and said gradient generator are further configured to acquire said second slice set by providing,
a low flip angle RF pulse successively followed by:

a non-diffusion image data readout magnetic field gradient for to facilitate acquisition of data representing a two-dimensional
(2D) non-diffusion image used for motion detection of the first slice set,

a first diffusion imaging RF pulse, and
a first diffusion imaging phase encoding magnetic field gradient for magnetic preparation to facilitate acquisition of data
representing a diffusion image slice of the second slice set.

US Pat. No. 9,684,050

METHOD AND APPARATUS FOR THE RECONSTRUCTION OF MR IMAGES

Siemens Healthcare GmbH, ...

1. A method for producing an image of an object located in the field of view of a Magnetic Resonance (MR) imaging system,
the image being reconstructed from a subset of data elements less than a raw matrix of data elements having N number of rows
of data elements and M number of columns of data elements, the method comprising:
determining a center of an echo expressed as a whole column number, a fractional column number, a whole row number and a fractional
row number of the raw matrix;

shifting the data elements of the raw matrix by whole positions to align the center of the echo, expressed as the whole column
number and the whole row number, with the center of the raw matrix;

multiplying the shifted raw matrix by a low pass filter to provide a filtered matrix;
Fourier transforming the filtered matrix to provide a low resolution complex image and dividing each nonzero pixel of the
low resolution complex image by its magnitude to provide a phase map;

calculating a blending function that compensates for the image artifacts created by fractional misalignment of the echo center
with elements of the raw matrix, said blending function being shifted by the determined fractional echo position, and having
blending coefficient values corresponding to each line of raw matrix data elements;

multiplying each data element of each row of the raw matrix by corresponding blending function coefficient values;
performing a two-dimensional Fourier transform in row directions and column directions to provide a complex image;
multiplying the complex image by a complex conjugate of the phase map to provide a phase corrected image; andextracting the real part of the complex numbers in the phase corrected image to provide the image of the object.

US Pat. No. 9,632,156

EFFICIENT REDUNDANT HAAR MINIMIZATION FOR PARALLEL MRI RECONSTRUCTION

Siemens Healthcare GmbH, ...

1. A method for parallel magnetic resonance imaging (MRI) reconstruction of digital images, comprising:
providing a set of acquired raw k-space MR image data v, a redundant Haar wavelet matrix W satisfying WTW=I, wherein I is an identity matrix, a regularization parameter ??0, and a counter limit k;

obtaining a proximal operator, the proximal operator obtained by the steps of:
initializing a variable z0=Wv, and intermediate quantities p0=q0=0;

calculating yi=arg minz½?z?(pi+zi)?22+??z?1 for 0?i?k, wherein z denotes values of an MR image sought to be reconstructed;

updating pi+1=(pi+zi)?yi;

updating zi+1=arg minz½?z?(qi+zi)?22+g(z), wherein


updating qi+1=(qi+yi)?zi+1,

wherein x=WTz is a solution of

that specifies a reconstruction of the MR image; and
reconstructing a digital MR image by applying the proximal operator to the acquired raw k-space MR image data, the digital
MR image displayable on a computer system display.

US Pat. No. 10,162,037

NAVIGATOR-BASED DATA CORRECTION FOR SIMULTANEOUS MULTISLICE MR IMAGING

Siemens Healthcare GmbH, ...

1. A method for correcting multislice echo planar imaging (EPI) data for B0 drift effects and N/2 ghosting effects in a magnetic resonance (MR) system, comprising the steps of:(a) generating a plurality of EPI MR image data sets from a volume of a subject to be imaged using a plurality of EPI sequences, wherein:
(i) each EPI MR image data set is based on a simultaneous radiofrequency (RF) excitation of a plurality of slices within the volume, and
(ii) each EPI sequence comprises an RF excitation pulse and an associated image data readout sequence;
(b) generating a plurality of navigator sequences, wherein:
(i) each navigator sequence comprises at least three echoes;
(ii) at least one navigator sequence is a first type of navigator sequence that is phase encoded and comprises readout gradients that alternate in polarity for each echo; and
(iii) at least one navigator sequence is a second type of navigator sequence that is phase encoded and comprises a readout gradient for each echo that is opposite in polarity to the corresponding readout gradient for the first type of navigator sequence;
(c) correcting at least one EPI MR image data set for B0 drift effects and N/2 ghosting effects based at least in part on at least one of the first type of navigator sequence and at least one of the second type of navigator sequence; and
(d) generating an image of the volume based at least in part on the at least one corrected EPI MR image data set,
wherein at least one navigator sequence is a third type of navigator sequence that is not phase encoded, and wherein at least one EPI MR image data set is corrected for B0 drift effects based on at least one of the third type of navigator sequence.

US Pat. No. 9,947,503

MAGNETIC SHIELDING OF AN X-RAY EMITTER

SIEMENS HEALTHCARE GMBH, ...

1. An x-ray emitter comprising:a housing, the housing including a diamagnetic or paramagnetic housing material and a plurality of ferromagnetic particles, the ferromagnetic particles being aligned substantially along closed paths.

US Pat. No. 9,910,116

METHOD AND TEST APPARATUS FOR DETERMINING A DEVIATION IN HOMOGENEITY OF A MAGNETIC FIELD OF A MAGNETIC RESONANCE SCANNER

Siemens Healthcare GmbH, ...

1. A method for determining a deviation in homogeneity of a basic magnetic field of a magnetic resonance (MR) apparatus, said
method comprising:
placing at least two test vessels in an MR data acquisition scanner in a test plane that is perpendicular to a direction defined
by an axis in said MR data acquisition scanner;

positioning said test plane at a first position of said axis wherein a first test vessel, of said at least two test vessels,
is situated at a first location of the first test vessel and wherein a second test vessel of said at least two test vessels,
is situated at a first location of the second test vessel;

operating the MR data acquisition scanner, including generating a basic magnetic field having a homogeneity, to record first
measurement data induced by said first and second test vessels at their respective first locations;

repositioning said test plane at a second position of said axis that is different from said first position along one coordinate
of said axis, wherein said first test vessel is situated at a second location of the first test vessel and said second test
vessel is situated at a second location of said second test vessel;

operating said MR data acquisition scanner to record second measurement data induced by said first and second test vessels
at their respective second locations; and

providing said first and second measurement data to a processor and, in said processor, determining a deviation of said homogeneity
of said basic magnetic field based on at least said first and second measurement data.

US Pat. No. 9,911,206

TIME EFFICIENT ASL IMAGING WITH SEGMENTED MULTIBAND ACQUISITION

Siemens Healthcare GmbH, ...

1. A method for generating a perfusion weighted image using arterial spin labeling (ASL) with segmented acquisitions, the
method comprising:
dividing an anatomical area of interest into a plurality of slices;
performing an echo planar imaging (EPI) acquisition process using a magnetic resonance imaging (MRI) system to acquire a control
image dataset representative of the plurality of slices;

performing an ASL preparation process, using the MRI system to magnetically label protons in arterial blood water in an area
upstream from the anatomical area of interest;

following a first post-labeling delay time period, performing a multi-band (MB) EPI acquisition process with a first MB factor
using the MRI system to acquire a first labeled image dataset representative of a first subset of the plurality of slices;

following a second post-labeling delay time period, performing another MB EPI acquisition process with a second MB factor
using the MRI system to acquire a second labeled image dataset representative of a second subset of the plurality of slices,
wherein the second MB factor is higher than the first MB factor; and

generating a perfusion weighted image of anatomical area of interest by subtracting the first labeled image dataset and the
second labeled image dataset from the control image dataset.

US Pat. No. 9,880,297

QUALITY CONTROLLED RECONSTRUCTION FOR ROBOTIC NAVIGATED NUCLEAR PROBE IMAGING

Siemens Healthcare GmbH, ...

1. A system for robotic navigation in nuclear probe imaging, the system comprising:
a nuclear detector for detecting radiation;
a robotic assembly connected with the nuclear detector, the robotic assembly configured to move the nuclear detector in a
first pattern relative to a patient, the first pattern sampling from different measurement lines, the nuclear detector providing
first samples from the sampling of the first pattern;

a processor configured to reconstruct a volume as a first reconstruction from the first samples of the detected radiation
from the different measurement lines, to control the robotic assembly to further move the nuclear detector relative to the
patient after the sampling in the first pattern where a calculated quality of the reconstructed volume is below a threshold
measure, the further movement acquiring second samples of further detected radiation, and to repeat the reconstruction of
the volume as a second reconstruction from both the first samples of the detected radiation and from the second samples of
the further detected radiation from the further movement.

US Pat. No. 9,799,120

METHOD AND APPARATUS FOR ATLAS/MODEL-BASED SEGMENTATION OF MAGNETIC RESONANCE IMAGES WITH WEAKLY SUPERVISED EXAMINATION-DEPENDENT LEARNING

Siemens Healthcare GmbH, ...

1. A method for segmenting a selected region from a set of magnetic resonance (MR) image data, comprising:
providing a computer with an MR image dataset, acquired from a patient by operation of an MR scanner to conduct an MR scan
of a region of the patient, said MR image dataset being comprised of a plurality of image elements including image elements
of said region;

providing said computer with an input data file, which is non-specific for said patient, and which designates attributes of
image elements that are expected in a generalized representation of said region;

in said computer, producing a segmentation mask dependent on the expected attributes of said image elements of said generalized
version of said region in said input data file;

in said computer, applying said segmentation mask to said MR image dataset to extract image elements therefrom that form an
initial segmentation of said region of said patient from said MR image dataset;

in said computer, applying an image element classification, based on said image attributes, to the image elements in said
initial segmentation by executing a classification algorithm, and thereby obtaining an initial classification result of said
image elements in said region in said initial segmentation;

in said computer, evaluating said classification and re-training said classification algorithm in said computer, in a plurality
of iterations, dependent scan-specific on information provided to said computer and, in each iteration, applying each re-trained
classification to a further segmentation of said region, until a termination criterion is satisfied, thereby obtaining a final
segmentation of said region of said patient from said MR image dataset; and

making the final segmentation of said region available in electronic form from said computer, as an output data file.

US Pat. No. 9,704,256

SYSTEMS AND METHOD FOR COMPUTATION AND VISUALIZATION OF SEGMENTATION UNCERTAINTY IN MEDICAL IMAGES

Siemens Healthcare GmbH, ...

1. A method for calculating a clinical measurement of a target anatomical object of a patient, comprising:
generating a surface model of a target anatomical object from medical imaging data of a patient;
determining a probability that each of a plurality of points along a surface normal for each of a plurality of vertices of
the surface model accurately identifies an image boundary;

estimating uncertainty at each respective vertex of the plurality of vertices of the surface model based on the probabilities
determined for the plurality of points along the surface normal for the respective vertex;

visualizing the uncertainty estimated at each of the plurality of vertices on the surface model; and
calculating a clinical measurement of the target anatomical object based on the surface model and the uncertainty.

US Pat. No. 9,687,204

METHOD AND SYSTEM FOR REGISTRATION OF ULTRASOUND AND PHYSIOLOGICAL MODELS TO X-RAY FLUOROSCOPIC IMAGES

Siemens Healthcare GmbH, ...

1. A method for registering an ultrasound image acquired using an ultrasound probe to a fluoroscopic image acquired using
a fluoroscopic image acquisition device, comprising:
detecting a 2D location of the ultrasound probe in the fluoroscopic image using a trained machine learning based probe detector
that extracts features from image patches of the fluoroscopic image, determines a probability score for each image patch,
and selects the image patch having the highest probability score as the 2D location of the ultrasound probe;

estimating an initial machine learning based 3D pose of the ultrasound probe based on the detected 2D location of the ultrasound
probe in the fluoroscopic image by initializing pose estimation using X and Y coordinates estimated from the detected 2D location
of the ultrasound probe, estimating a 3D position of the ultrasound probe including X, Y, and Z coordinates based on the X
and Y coordinates estimated from the detected 2D location by applying a trained machine learning based position classifier
to the fluoroscopic image, and estimating a 3D position and orientation of the ultrasound probe including X, Y, and Z coordinates
and a roll, pitch, and yaw based on the 3D position estimating using the trained machine learning based position classifier
by applying a trained machine learning based position and orientation classifier to the fluoroscopic image;

iteratively refining the estimated initial machine learning based 3D pose of the ultrasound probe using 2D/3D registration
based on the ultrasound and the fluoroscopic image to estimate a final 3D pose of the ultrasound probe;

mapping the ultrasound image to a 3D coordinate system of the fluoroscopic image acquisition device based on the estimated
final 3D pose of the ultrasound probe;

estimating a patient specific physiological model of an anatomical structure in the ultrasound image; and
projecting the patient specific physiological model of the anatomical structure into the fluoroscopic image using a projection
matrix associated with the fluoroscopic image.

US Pat. No. 9,589,379

SYSTEM AND METHOD FOR VISUALIZATION OF CARDIAC CHANGES UNDER VARIOUS PACING CONDITIONS

SIEMENS HEALTHCARE GMBH, ...

1. A method for guiding a cardiac intervention, comprising:
generating a patient-specific anatomical heart model based on medical image data of a patient;
generating a patient-specific computational model of heart function based on the patient-specific anatomical heart model;
performing a virtual intervention at each of a plurality of positions on the patient-specific anatomical heart model using
the patient-specific computational model of heart function to calculate one or more cardiac parameters resulting from the
virtual intervention performed at each of the plurality of positions; and

generating one or more outcome maps visualizing, at each of the plurality of positions on the patient-specific anatomical
heart model, optimal values for the one or more cardiac parameters resulting from the virtual intervention performed at the
that position on the patient-specific anatomical heart model.

US Pat. No. 9,582,934

METHOD AND SYSTEM FOR EFFICIENT EXTRACTION OF A SILHOUETTE OF A 3D MESH

Siemens Healthcare GmbH, ...

1. A method for extracting a silhouette of a 3D mesh representing an anatomical structure, comprising:
projecting the 3D mesh onto a 2D image;
generating silhouette candidate edges in the projected mesh by pruning mesh points and edges of the projected mesh that lie
completely inside a region enclosed by the projected mesh;

splitting each silhouette candidate edge that intersects with another edge in the projected mesh into two silhouette candidate
edges; and

extracting the silhouette using an edge following process on the silhouette candidate edges.

US Pat. No. 9,566,014

SYSTEM FOR CARDIAC MR AND MR CINE IMAGING USING PARALLEL IMAGE PROCESSING

Siemens Healthcare GmbH, ...

1. A method for cardiac imaging that nulls a normal myocardium signal without use of a scout, the method comprising:
for each of a plurality of cardiac cycles within a single breath hold:
applying a non-selective inversion pulse during the cardiac cycle;
identifying a plurality of successive phases of the cardiac cycle that are immediately subsequent to the non-selective inversion
pulse, wherein there is no intervening time between application of the non-selective inversion pulse and the start of the
plurality of successive phases of the cardiac cycle; and

performing single shot imaging to sample MR data along radial trajectories in k-space continuously during each of the successive
phases of the cardiac cycle using a plurality of MR imaging RF coils to simultaneously acquire a plurality of reduced sets
of k-space data elements associated with each of the successive phases of the cardiac cycle;

performing k-t SPARSE-SENSE reconstruction on the plurality of reduced sets of k-space data elements acquired during corresponding
phases of different ones of the plurality of cardiac cycles to generate an image for each of the phases of the cardiac cycle;
and

selecting one image of the plurality of images generated for the plurality of phases of the cardiac cycle in which the normal
myocardium signal is nulled,

wherein the MR data comprises gradient echo imaging data; and
wherein the corresponding phases of different ones of the plurality of cardiac cycles have a same delay time interval from
the non-selective inversion recovery pulse.

US Pat. No. 10,349,505

HIGH-VOLTAGE SUPPLY AND AN X-RAY EMITTER HAVING THE HIGH-VOLTAGE SUPPLY

Siemens Healthcare GmbH, ...

1. A high-voltage supply for an x-ray emitter, including provision of a cathode current and a cathode voltage, the high-voltage supply comprising:a common insulating body;
connector elements configured for electrically conducting contact with corresponding connectors of the x-ray emitter;
at least two electrical conductors incorporated in said common insulating body, each of said at least two electrical conductors being assigned to one of said connector elements; and
a board, said connector elements disposed on said board, and each of said connector elements is connected to an assigned one of said electrical conductors in an electrically conducting manner by way of conduction paths.

US Pat. No. 10,104,752

DETECTION OF X-RAY RADIATION

SIEMENS HEALTHCARE GMBH, ...

1. An X-ray detector, comprising:a detection unit, configured to generate a detection signal for X-ray radiation incident on the detection unit;
a signal analysis module, configured to determine a set of count rates for X-ray radiation incident on the detection unit on the basis of the detection signal and signal analysis parameters for X-ray radiation; and
a switchover control unit, configured to switch between at least first signal analysis parameters and second signal analysis parameters such that when an amount of X-ray radiation is incident on the detection module, a first set of count rates being generated for a first time interval on the basis of first signal analysis parameters, and a second set of count rates being generated for a second time interval on the basis of second signal analysis parameters, different from the first signal analysis parameters, the first and second signal analysis parameters are selected from the group:
energy threshold value,
energy threshold, and
number of assigned energy thresholds, wherein the switchover control unit is further configured to cyclically switchover between first and second energy threshold values the number of energy thresholds checked is increased for at least one projection beyond the number that is limited by the quantity of comparators for energy thresholds present in a detector channel.

US Pat. No. 10,074,037

SYSTEM AND METHOD FOR DETERMINING OPTIMAL OPERATING PARAMETERS FOR MEDICAL IMAGING

Siemens Healthcare GmbH, ...

1. A method for determining optimized imaging parameters for imaging a patient, comprising:learning a model of a relationship between known imaging parameters and a quality measure, the known imaging parameters and the quality measure being determined from training data, wherein the quality measure is based on a signal-to-noise ratio (SNR) determined as a ratio between an average intensity value of pixels in a first region of interest in a target structure in an image and an average intensity value of pixels in a second region of interest outside of the target structure in the image;
determining optimized imaging parameters by optimizing the quality measure using the learned model, the optimized imaging parameters comprising parameters of an image acquisition device and patient parameters for imaging the patient, the optimized imaging parameters being constrained to be within a range of the known imaging parameters; and
acquiring images of the patient using the image acquisition device based on the optimized imaging parameters.

US Pat. No. 10,002,739

X-RAY EMITTER

Siemens Healthcare GmbH, ...

1. An X-ray emitter, comprising:a rotating anode disposed inside an X-ray tube;
a multi-sliding surface bearing rotatably mounting said rotating anode inside said X-ray tube;
said multi-sliding surface bearing having an inner sliding surface and an outer sliding surface that are mounted for rotation relative to each other about an axis of rotation and forming a gap between said inner and outer sliding surfaces;
said inner sliding surface, in a plane running perpendicular to the axis of rotation, having a contour formed at least in certain sections by arc-shaped segments that are each centered around center points arranged so as to be offset from one another.

US Pat. No. 10,002,419

DIRECT COMPUTATION OF IMAGE-DERIVED BIOMARKERS

Siemens Healthcare GmbH, ...

1. A method for computing image-derived biomarkers, the method comprising:receiving image data defining a three-dimensional image volume representative of an anatomical region of interest and comprising a plurality of voxels;
applying an intensity model on a per-voxel basis across the three-dimensional image volume to assign a weighting value for each voxel indicating a likelihood that the voxel includes anatomical features related to a biomarker of interest, wherein the intensity model is a machine learning model trained using intensity features of previously acquired image data; and
deriving information related to the biomarker of interest without prior creation of a segmented mesh from the image data by performing one or more modeling computations directly on the image data, wherein the weighting values are used to limit the modeling computations to voxels comprising the anatomical features related to the biomarker of interest.

US Pat. No. 9,984,772

IMAGE ANALYTICS QUESTION ANSWERING

Siemens Healthcare GmbH, ...

1. A computer-implemented method for predicting answers to questions concerning medical image analytics reports, the method comprising:splitting a medical image analytics report into a plurality of sentences;
generating a plurality of sentence embedding vectors by applying a natural language processing framework to the plurality of sentences;
receiving a question related to subject matter included in the medical image analytics report;
generating a question embedding vector by applying the natural language processing framework to the question;
identifying a subset of the sentence embedding vectors most similar to the question embedding vector by applying a similarity matching process to the sentence embedding vectors and the question embedding vector; and
using a trained recurrent neural network (RNN) to determine a predicted answer to the question based on the subset of the sentence embedding vectors.

US Pat. No. 9,962,129

METHOD AND APPARATUSES FOR ASSISTING A DIAGNOSING PRACTITIONER WITH DESCRIBING THE LOCATION OF A TARGET STRUCTURE IN A BREAST

Siemens Healthcare GmbH, ...

1. A method for assisting a diagnosing practitioner with describing a location of at least one target structure in a tomosynthesis image data record of a compressed breast of a patient, the target structure being localized by means of a first spatial information item, which comprises the steps of:ascertaining a first shape information item describing at least one first compressed breast shape in the tomosynthesis image data record;
determining a second shape information item describing the compressed breast in a non-compressed breast shape, from the first shape information item;
mapping a position of the at least one target structure from the first compressed breast shape and to the non-compressed breast shape using at least the second shape information item for ascertaining a second spatial information item relating to the non-compressed breast shape; and
transforming the second spatial information item into a pictogram information item facilitating an abstracted pictorial representation and/or describing the abstracted pictorial representation, wherein, in a case of a plurality of views of the compressed breast contained in the tomosynthesis image data record, a second spatial information item is ascertained for each view, the second spatial information item to be used is ascertained by statistical combination of preliminary spatial information items, with the second spatial information item being ascertained by forming a mean value, weighted by a reliability value assigned to a respective preliminary spatial information item, from the preliminary spatial information items.

US Pat. No. 9,959,486

VOXEL-LEVEL MACHINE LEARNING WITH OR WITHOUT CLOUD-BASED SUPPORT IN MEDICAL IMAGING

Siemens Healthcare GmbH, ...

1. A method for use of machine-learnt classifier in medical imaging, the method comprising:segmenting, by a processor, gross parts of an anatomic structure of a patient represented in medical imaging data;
locating, by the processor, a region adjacent and separate from the segmented gross parts of the anatomic structure, and locating the gross parts of the anatomic structure from the segmenting, where the region contains relatively smaller parts of the anatomic structure and contains tissue not of the anatomic structure, where the relatively smaller parts of the anatomical structure are smaller than the gross parts of the anatomical structure;
dividing, by the processor, the region represented in the medical imaging data into a plurality of patches;
classifying, with a machine-learnt classifier, each of the patches as including relatively smaller parts of the anatomical structure or not including relatively smaller parts of the anatomical structure, the classifying of each of the patches being independent of classifying the other patches;
merging, by the processor, locations for the patches classified as including relatively smaller parts of the anatomical structure to the gross parts of the anatomical structure; and
outputting, on a display, a segmented image of the anatomical structure including locations from the locating and the merged locations from the patches.

US Pat. No. 9,940,713

MR-BASED NAVIGATORS FOR INTER-SCAN AND INTRA-SCAN MOTION CORRECTION

Siemens Healthcare GmbH, ...

1. A method for using navigators for inter-scan motion correction during imaging of a subject with a magnetic resonance imaging device, the method comprising:performing an anatomical localizer scan of a region of interest within the subject to identify one or more anatomical landmarks defining orientation of a surrounding field-of-view in the region of interest;
performing an inter-scan motion reference scan of the region of interest to acquire a reference inter-scan dataset indicating a location of a reference navigator in the region of interest;
performing a plurality of scans of the region of interest within the subject to acquire k-space data, wherein, prior to one or more of the plurality of scans, a motion correction process is performed comprising:
performing an inter-scan motion tracking scan to acquire a tracking inter-scan dataset indicating an updated location of the reference navigator in the region of interest,
determining an estimation of inter-scan patient motion based on a comparison between the reference inter-scan dataset and the tracking inter-scan dataset, and
updating the field-of-view relative to the one or more anatomical landmarks in the region of interest based on the estimation of inter-scan patient motion; and
generating one or more images of the region of interest using the k-space data acquired with each of the plurality of scans.

US Pat. No. 9,905,042

METHOD AND VISUALIZATION APPARATUS FOR THE VOLUMETRIC VISUALIZATION OF A THREE-DIMENSIONAL OBJECT

SIEMENS HEALTHCARE GMBH, ...

1. A method for a volumetric visualization of a three-dimensional object within a light probe as an illumination source, wherein:
a) the light probe is examined for intensive light sources and at least one intensive light source of the light probe is selected
depending on an intensity thereof;

b) a multiplicity of rays simulated for a respective visualization pixel, wherein, for a respective ray entering into an object
volume:

i) a scattering position is determined,
ii) a scattering direction is selected, with a decision being made depending on a first random process as to whether the respective
ray is scattered in a direction of the at least one selected intensive light source or in a scattering direction to be selected
depending on a second random process,

iii) the respective ray is scattered at the scattering position in the selected scattering direction, and
iv) steps i) to iii) are repeated until the respective ray is absorbed in the object volume or emerges from the object volume
and impinges on the light probe, with an illumination contribution of the respective ray to the respective visualization pixel
being ascertained depending on an intensity value of the light probe; and

c) an intensity value for the respective visualization pixel is ascertained by virtue of the illumination contribution of
the multiplicity of rays being averaged.

US Pat. No. 9,874,642

SCINTILLATORS COMPRISING AN ORGANIC PHOTODETECTION SHELL

SIEMENS HEALTHCARE GMBH, ...

1. A coated scintillator particle, comprising:
a scintillator particle; and
a semiconducting photoactive material coating the scintillator particle;
wherein a thickness of the coating is less than 2.5 times the penetration depth of the radiation emitted by the scintillator
particle.

US Pat. No. 9,867,547

SYSTEM AND METHOD TO CALCULATE CARDIAC CHARACTERISTICS

Siemens Healthcare GmbH, ...

1. A system comprising;
a signal acquisition system including an interface configured to:
receive a hemodynamic signal; and
receive a cardiac impedance signal; and
a processor configured to execute a system control program in a memory, the system control program causing the processor to:
identify by the processor a first peak and a second peak of the cardiac impedance signal;
identify by the processor a first portion of the hemodynamic signal corresponding to a full heart cycle based on the cardiac
impedance signal first peak;

identify by the processor a second portion of the hemodynamic signal corresponding to the full heart cycle based on the cardiac
impedance signal second peak;

calculate a systolic area index (SAI) cardiac characteristic based on the first portion and the second portion of the hemodynamic
signal;

the identification of the first portion of the hemodynamic signal including causing the processor to:
employ an adaptive multi-cycle detection window by identifying at least two complete periods of the hemodynamic signal occurring
within a predetermined time period, wherein the predetermined timed period is centered around the first peak of the cardiac
impedance signal;

create a weighted average of the at least two complete periods of the hemodynamic signal with adaptively controlled coefficients,
wherein the adaptively controlled coefficients represent a time interval between a center of the multi-cycle detection window
and a peak of the hemodynamic signal for each of the at least two complete periods of the hemodynamic signal, wherein the
weighted average acts as a derived hemodynamic cycle;

the calculation of the SAI cardiac characteristic based on the derived hemodynamic cycle;
determine a medical diagnosis based on the calculated SAI cardiac characteristic; and
display on an operator terminal at least one of the medical diagnosis determined by the processor and the SAI cardiac characteristic
calculated by the processor.

US Pat. No. 9,848,785

ANALYSIS AND CHARACTERIZATION OF PATIENT SIGNALS

Siemens Healthcare GmbH, ...

1. A system for patient signal analysis, comprising:
a multi-channel patient monitor including a first sensor configured to acquire over multiple successive cycles a first patient
signal data and a second sensor configured to acquire over multiple successive cycles a second patient signal data;

the first patient signal data is a characterization of one of blood flow information and vessel circulation information;
the second patient signal data is a characterization of one of blood flow information and vessel circulation information that
is different from the first patient signal data characterization;

a computer system communicatively coupled to the multi-channel patient monitor, the computer system including a processor
in communication with a memory device containing non-transitory computer readable program instructions;

the computer readable program instructions configured to cause the processor to perform operations including:
implement a patient signal analysis unit to pre-process the first and the second patient signal data;
segment the pre-processed first and the second patient signal data into respective first and second regions of interest;
extract a respective first and a respective second waveform parameters from the first and the second regions of interest;
generate one or more respective morphology indices based on the respective first and the respective second waveform parameters
over the multiple successive cycles;

compare shapes of the one or more respective morphology indices to detect at least one of a change due to cardiac blood flow
functionality and vessel abnormality;

determine whether an abnormality exists in at least one of the first and the second patient signal data based on the results
of the comparison of the one or more respective morphology indices; and

if an abnormality is determined, generate a patient report alert on the multi-channel patient monitor.

US Pat. No. 9,846,922

METHOD, COMPUTER READABLE MEDIUM AND MRI APPARATUS FOR PERFORMING PHASE-ENCODE GHOSTING DETECTION AND MITIGATION IN MRI

Siemens Healthcare GmbH, ...

1. A computer-implemented method for detecting phase-encoding ghosting in a magnetic resonance (MR) image of an object to
be imaged and mitigating a corresponding artifact in the MR image, the computer-implemented method comprises the steps of:
acquiring magnetic resonance imaging (MRI) raw data of the object by means of a MRI apparatus, the MRI apparatus having multiple
receiver channels for acquiring the MRI raw data;

calculating an artifact map of at least one part of the object to be imaged from the MRI raw data, the step of calculating
the artifact map including:

generating a duplicate k-space based on an original k-space being a fully-sampled centric-ordered and non-interleaved k-space
including the MRI raw data, and

inverse Fourier transforming a subtraction of the duplicate k-space from the original k-space for obtaining the artifact map;
creating an outlier mask representing detected phase-encoding artifacts in the artifact map; and
mitigating phase-encode ghosting in the MR image by using the artifact map and the outlier mask for obtaining an improved
MR image by replacing each image voxel of an inverse Fourier transformed original k-space that is indicated as artefactual
in the outlier mask by a corresponding image voxel of an inverse Fourier transformed duplicate k-space for obtaining the improved
MR image.

US Pat. No. 9,830,427

METHOD FOR INTRACRANIAL ANEURYSM ANALYSIS AND ENDOVASCULAR INTERVENTION PLANNING

Siemens Healthcare GmbH, ...

1. A computer-assisted method of analyzing an intracranial aneurysm and virtually configuring endovascular treatment for the
aneurysm, said method being carried out by a processor associated with an a medical imaging system to carry out the steps
of the method, wherein the medical imaging system includes a medical imaging scanner that acquires image data and is operably
connected to a computer system that controls operation of the scanner and, via a communication channel, to an image processing
system that processes the image data signals and that has an image data archive or database adapted to store the image data
signals that are produced by the image scanner, an application server, and a user workstation, the method comprising the steps
of:
a. receiving, by the processor, a user selected 3D digital subtraction angiographic (DSA) image that includes a parent blood
vessel with an aneurysm;

b. performing vessel segmentation by the processor on the selected 3D DSA image and outputting a segmented digital image of
the parent blood vessel;

c. receiving, by the processor, a proximal point in the parent vessel around the aneurysm selected by a user from the segmented
digital image, a distal point in the parent vessel around the aneurysm selected by a user from the segmented digital image,
and a point in a dome of the aneurysm selected by a user from the segmented digital image;

d. centering, by the processor, the proximal and distal points in the parent vessel in the segmented digital image;
e. extracting, by the processor, the centerline of the parent blood vessel from the segmented digital image using the centered
proximal and distal points as seed points wherein the centerline is identified in the parent blood vessel in the segmented
digital image;

f. separating, by the processor, the aneurysm from the parent blood vessel, based on the proximal point, distal point, and
point in the dome, wherein the separated aneurysm is identified in the segmented digital image as separate from the parent
blood vessel;

g. reconstructing, by the processor, a healthy parent blood vessel in the segmented digital image after separating the aneurysm
from the parent blood vessel;

h. displaying to the user a plurality of characteristic features of the aneurysm calculated after the aneurysm was separated
from the healthy parent blood vessel; and

i. configuring, by the processor, a 3D virtual stent in the segmented digital image from the extracted centerline of the parent
blood vessel and the plurality of characteristic features that fits the reconstructed parent blood vessel.

US Pat. No. 9,824,843

EMITTER WITH DEEP STRUCTURING ON FRONT AND REAR SURFACES

Siemens Healthcare GmbH, ...

1. An emitter, comprising:
a basic unit having at least one emission surface with a front side and a rear side, said emission surface having incisions
formed therein running from two opposite sides of said front side and transverse to a longitudinal direction of the emitter,
said basic unit having deep structuring formed therein in a region of said at least one emission surface on said front side
and on said rear side between said incisions and separate from said incisions.

US Pat. No. 9,823,322

METHOD AND APPARATUS FOR MAGNETIC RESONANCE DATA ACQUISITION USING A MULTIPOINT DIXON TECHNIQUE

Siemens Healthcare GmbH, ...

1. A method for acquiring magnetic resonance data from an examination subject, comprising:
operating a magnetic resonance data acquisition unit, that generates a basic magnetic field in which an examination subject
is situated, according to a bipolar multi-echo data acquisition sequence, to acquire magnetic resonance data from the examination
subject for multiple image points by, for each image point, alternatingly activating positive and negative readout gradient
fields with a gradient system of said acquisition unit, during which magnetic resonance signals are read out during at least
three echo times, said activation of said gradient fields producing eddy currents in said data acquisition unit by interaction
with said basic magnetic field;

providing said magnetic resonance data to a computerized processor and, in said computerized processor, operating on said
magnetic resonance data with a spectral model of a multipoint Dixon technique that relates said magnetic resonance data to
at least two spectral components of said magnetic resonance signals and respective, associated relaxation rates of said at
least two spectral components, and a first phase of said magnetic resonance signals that occurs due to field inhomogeneities
of said basic magnetic field, and a second phase that occurs due to effects of said eddy currents, to implement an at least
partially numerical determination of said at least two spectral components, said relaxation rates, said first phase, and said
second phase; and

making said at least two spectral components available in electronic form at an output of said processor in a format allowing
reconstruction of an in-phase image and two out-of-phase images according to the multipoint Dixon technique that is modeled
by said spectral model.

US Pat. No. 9,805,473

METHOD AND SYSTEM FOR SEGMENTATION OF BRAIN STRUCTURES IN 3D MAGNETIC RESONANCE IMAGES

Siemens Healthcare GmbH, ...

1. A method for segmenting a plurality of brain structures in a 3D magnetic resonance (MR) image, comprising:
detecting a meta-structure including center positions of each of said plurality of brain structures in the 3D MR image; and
individually segmenting at least one of the plurality of brain structures using marginal space learning (MSL) constrained
by the detected meta-structure, wherein said step of detecting a meta-structure comprises:

detecting the meta-structure using MSL to sequentially detect position, position-orientation, and a full similarity transformation
of the meta-structure in the 3D MR image using a set of trained discriminative classifiers.

US Pat. No. 9,689,947

SAMPLING STRATEGIES FOR SPARSE MAGNETIC RESONANCE IMAGE RECONSTRUCTION

Siemens Healthcare GmbH, ...

1. A computer-implemented method of selecting a Magnetic Resonance Imaging (MRI) sampling strategy, the method comprising:
selecting a base variable-density sampling pattern;
determining a scan time associated with the base variable-density sampling pattern;
creating a modified variable-density sampling pattern by modifying one or more parameters of the base variable-density sampling
pattern to maximize a sampled k-space area without increasing the scan time;

performing a scan on an object of interest using the modified variable-density sampling pattern to obtain a sparse MRI dataset;
and

applying a sparse reconstruction process to the sparse MRI dataset to yield an image of the object of interest.

US Pat. No. 9,646,409

GENERATION OF A DISPLAY DATA SET WITH VOLUME RENDERING

Siemens Healthcare GMBH, ...

1. A method for generating a display data set for depicting a three dimensional source data set of at least one display parameter
through volume rendering, wherein a volume-rendering integral with an integrand and with an extinction function that assigns
one extinction value for each distance to a value of the display parameter, and a color function that assigns at least one
chromaticity for each path to the value of the display parameter is evaluated to determine the display data set and wherein
the volume-rendering integral is broken down into contributions from third opacities as integrals dependent upon the extinction
function and third color coefficients as integrals dependent upon the color function and the extinction function, wherein
the color function and the extinction function are described by a front value and a back value of the display parameter and
a desired sampling distance describing a interval used for integration, the method comprising, at least the following acts
for the evaluation of the volume-rendering integral:
subdividing a integration distance into at least two subsections based on at least one subdivision parameter, wherein the
integration distance is based on a fixed predetermined target sampling distance independent of the desired sampling distance;

providing a subsection number corresponding to a number of subsections of pre-integration tables, wherein the subsection number
minus one corresponds to integrations over different subsections wherein the front value and the back value of the display
parameter are assigned a target sampling distance opacity, wherein a contribution of the volume-rendering integral and at
least one target sampling distance color coefficient are based on the target sampling distance opacity;

determining target sampling distance opacities and target sampling distance color coefficients based on pre-integration tables
for each contribution of a plurality of contributions of the volume-rendering integral; calculating third opacities converted
to the desired sampling distance from target sampling distance opacities and the ratio of desired sampling distance to target
sampling distance;

calculating third color coefficients from target sampling distance opacities, target sampling distance color coefficients,
and the ratio of desired sampling distance to target sampling distance; and

determining the volume-rendering integral from the contributions.

US Pat. No. 9,595,089

METHOD AND SYSTEM FOR NON-INVASIVE COMPUTATION OF HEMODYNAMIC INDICES FOR CORONARY ARTERY STENOSIS

SIEMENS HEALTHCARE GMBH, ...

1. A method for hemodynamic assessment of a coronary artery based on medical image data of a patient, comprising:
extracting patient-specific anatomical measurements of the coronary arteries from medical image data of a patient;
calculating patient-specific boundary conditions of a computational model of coronary circulation representing the coronary
arteries based on the patient-specific anatomical measurements of the coronary arteries;

simulating blood flow and pressure in the coronary arteries using the computational model of coronary circulation and the
patient-specific boundary conditions and modeling coronary autoregulation during the simulation of blood flow and pressure
in the coronary arteries, wherein modeling coronary autoregulation during the simulation of blood flow and pressure in the
coronary arteries comprises:

adapting microvascular resistances at outlets of the computational model of coronary circulation downstream of each coronary
artery stenosis in the computational model of coronary circulation based on a simulated pressure drop over the coronary artery
stenosis, a simulated flow rate through the coronary artery stenosis, and flow rate split ratios calculated for branches in
the coronary artery tree downstream of the coronary artery stenosis; and

calculating a hemodynamic index for at least one region in the coronary arteries based on the simulated blood flow and pressure.

US Pat. No. 9,955,890

HEART ELECTROPHYSIOLOGICAL SIGNAL ANALYSIS SYSTEM

Siemens Healthcare GmbH, ...

1. A system for identifying a particular point in an electrophysiological signal representing heart electrical activity, comprising:an interface for receiving an electrical signal waveform comprising T peaks and P peaks associated with heart electrical activity of a patient over a plurality of heart beat cycles; and
a signal processor for processing data representing said electrical signal waveform by
(a) determining exponential values of data samples of said electrical signal waveform lying between a T peak of a heart cycle and a P peak of a subsequent successive heart cycle,
(b) identifying particular samples having a derivative of the determined exponential values below a predetermined threshold value,
(c) determining a baseline portion of said electrical signal waveform in response to the identified particular samples,
(d) computing ST segment variation from the determined baseline portion of said electrical signal waveform, and
(e) in response to the variation exceeding a predetermined threshold value, initiating generation of an alert message.

US Pat. No. 9,955,923

ARRANGEMENT COMPRISING A PATIENT SUPPORT APPARATUS WITH A SUPPORT PLATE AND AN OVERLAY FOR THE SUPPORT PLATE

SIEMENS HEALTHCARE GMBH, ...

1. An arrangement, comprising:a patient support apparatus including a support plate and an overlay for the support plate, the support plate or the overlay including an electrically conductive first layer, wherein the electrically conductive first layer is connected or configured to be connected to a contact-making apparatus via a first electric transmission path,
wherein the contact-making apparatus is connected or configured to be connected to at least one of ground and a mass, via a second electric transmission path,
wherein, in an operating mode of the arrangement, in which a patient is supported on the patient support apparatus, the electrically conductive first layer is connected or configured to be connected to the patient, via a third electric transmission path,
wherein the support plate or the overlay includes an electrically non-conductive second layer,
wherein the electrically non-conductive second layer forms a capacitive coupling section of the third transmission path,
wherein the support plate includes an electrically conductive third layer,
wherein the contact-making apparatus includes the electrically conductive third layer,
wherein the support plate includes an electrically non-conductive fourth layer, and
wherein the electrically non-conductive fourth layer forms a capacitive coupling section of the first transmission path.

US Pat. No. 9,898,858

HUMAN BODY REPRESENTATION WITH NON-RIGID PARTS IN AN IMAGING SYSTEM

Siemens Healthcare GmbH, ...

1. A system for human body representation, the system comprising:
an imaging system configured to image a person having an exterior pose and a shape;
a modeler configured to deform an articulated tree-structured skeleton model having non-rigid parts to the exterior pose,
the deformation including adapting lengths of the non-rigid parts of the articulated tree-structured skeleton to the exterior
pose of the person, and to deform a mesh template to the shape with the adapted lengths normalized; and

a memory configured to store the human body representation of the person based on the deformed skeleton model and the deformed
mesh template.

US Pat. No. 9,872,662

DETERMINING A SPATIAL DISTRIBUTION OF A MATERIAL PROPERTY VALUE ON THE BASIS OF A SINGLE ENERGY IMAGE RECORDING

SIEMENS HEALTHCARE GMBH, ...

1. A method for determining a spatial distribution of a material property value in an examination region of an examination
object, the method comprising:
capturing measurement projection data for the examination region of the examination object using a single-energy CT recording
with a defined measurement energy and using a defined measurement projection geometry;

reconstructing image data based on the measurement projection data;
estimating a distribution of two basic materials, including a first basic material and a second basic material, in the examination
region by classifying image points based upon inclusion of a proportion of the second basic material, using a threshold value;

determining a distribution of thicknesses of the two basic materials based on the distribution of two basic materials and
a general dependency rule, the general dependency rule determined in relation to dependency of the measurement projection
data on the distribution of thicknesses of the two basic materials; and

determining the spatial distribution of a material property value based on the distribution of thicknesses of the two basic
materials and a previously known theoretical relationship between the spatial distribution of a material property value and
the distribution of thicknesses of the two basic materials, the spatial distrubution of a material property value being independent
of the defined measurment energy of the single-energy CT recording.

US Pat. No. 9,875,569

UNIFIED 3D VOLUME RENDERING AND MAXIMUM INTENSITY PROJECTION VIEWING BASED ON PHYSICALLY BASED RENDERING

Siemens Healthcare GmbH, ...

1. A method for rendering in medical imaging, the method comprising:
scanning a volume of a patient with a medical scanner, the scanning providing intensities representing the volume;
receiving a user setting of a rendering variable mapping to relative contribution of maximum intensity projection to volume
rendering;

rendering an image from the intensities representing the volume of the patient with ray tracing, the rendering being a function
of the user setting of the rendering variable and the rendering with ray tracing comprising modeling a probability of absorption,
a probability of scattering, and/or a probability of emission, wherein the user setting of the rendering variable weights
at least one of the probabilities; and

transmitting the image.
US Pat. No. 9,846,765

SYSTEM AND METHOD FOR PATIENT SPECIFIC MODELING OF LIVER TUMOR ABLATION

Siemens Healthcare GmbH, ...

1. A method for planning and guidance of tumor ablation therapy in a target organ based on a patient-specific model, comprising:
generating a patient-specific anatomical model of the target organ and a circulatory system of the target organ from medical
image data of a patient, wherein generating the patient-specific anatomical model of the target organ and the circulatory
system of the target organ comprises generating a patient-specific anatomical model of the liver including a liver parenchyma,
at least one tumor, a hepatic vein, a portal vein, and at least one artery by segmenting the liver parenchyma, the at least
one tumor, the hepatic vein, the portal vein, and the at least one artery in the medical image;

simulating blood flow in vessels and porous regions of the target organ based on the patient-specific anatomical model by:
calculating 3D blood flow and inlet pressures in the hepatic vein over a plurality of time steps using computational fluid
dynamics (CFD) simulation,

calculating portal vein and artery upstream pressures over the plurality of time steps based on the blood flow and the inlet
pressures in the hepatic vein, and

calculating 3D blood flow in the portal vein and the at least one artery over the plurality of time steps based on the portal
vein upstream pressures using CFD simulation;

simulating heat diffusion due to ablation based on a virtual ablation probe position and operating parameters and the simulated
blood flow in the vessels and porous regions of the target organ considering both cooling effects from the blood flow in the
vessels and the porous tissue blood perfusion by calculating, for each of a plurality of points in the patient-specific anatomical
model, a temperature at each of the plurality of time steps using a first bio-heat equation having a first cooling term if
the point belongs to a vessel or an artery, and a second bio-heat equation having a second cooling term if the point belongs
to a porous medium;

simulating cellular necrosis in the target organ based on the simulated heat diffusion; and
generating a patient-specific visualization of a necrosis region in the anatomical model resulting from the simulation of
heat diffusion due to ablation and the simulation of the cellular necrosis in the target organ.

US Pat. No. 9,792,531

INTELLIGENT MULTI-SCALE MEDICAL IMAGE LANDMARK DETECTION

Siemens Healthcare GmbH, ...

1. A method for intelligent multi-scale image parsing, the method comprising:
specifying, by a processor, a state space of an artificial agent for discrete portions of a training image, the state space
specified by a parametric space and a scale space for the discrete portions of the training image;

determining, by the processor, a set of actions, the set of actions comprising parametric actions specifying a possible change
in the parametric space with respect to the training image and scale actions specifying a possible change in the scale space
with respect to the training image;

establishing, by the processor, a reward system based on applying each action of the set of actions and based on at least
one target location of the training image; and

learning, by the processor, an optimal action-value function approximator of the artificial agent specifying the behavior
of the artificial agent to maximize a cumulative future reward value of the reward system, wherein the behavior of the artificial
agent is a sequence of actions moving the agent towards the at least one target location of the training image, the sequence
of actions comprising at least one scale action.

US Pat. No. 9,706,952

SYSTEM FOR VENTRICULAR ARRHYTHMIA DETECTION AND CHARACTERIZATION

Siemens Healthcare GmbH, ...

1. A system for heart performance characterization and abnormality detection, comprising:
an interface for receiving signal data, acquired by one or more sensors, representing oxygen content of blood in a patient
vessel over a plurality of heart beat cycles and electrocardiogram (ECG) signal data representing heart activity of the patient;

a signal processor for:
detecting one or more peaks, a valley and a baseline comprising a substantially zero voltage level of the received signal
data representing oxygen content of blood, wherein a peak of the signal data representing oxygen content of blood is detected
by:

determining a peak in the ECG signal data, wherein the ECG signal data includes a Q wave, an R wave, and a T wave, and wherein
the peak is determined from a search among the Q wave, R wave and T wave;

determining windows of the signal data representing oxygen content of blood in which a peak in the signal data representing
oxygen content of blood is expected, wherein the peak in the ECG signal data is the basis for the determination of the windows
in which the peak in the signal data representing oxygen content of blood is expected;

searching within the windows to identify the peak in the signal data representing the oxygen content of blood;
synchronizing the peak of the signal data representing the oxygen content of blood with the peak in the ECG signal data;
utilizing the synchronized peak of the signal data representing the oxygen content of blood and the peak in the ECG signal
data for detection and characterization of cardiac arrhythmia and pathology;

detecting, with a timing detector, a time duration between the synchronized peak of the ECG signal data and peak of the received
oxygen content signal data of the patient;

determining signal parameters including at least one of
(a) a signal amplitude magnitude between a maximum peak and minimum valley, of the received oxygen content signal data,
(b) a signal amplitude magnitude between the maximum peak and the baseline, of the received oxygen content signal data and
(c) a signal amplitude magnitude between a second highest maximum peak and minimum valley, of the received oxygen content
signal data; and

evaluating a health status of the patient based on the detected time duration between the synchronized peak of the ECG signal
data and peak of the received oxygen content signal data of the patient; and

a comparator for comparing a determined signal parameter or a value derived from the determined signal parameter with a threshold
value to provide a comparison indicator identifying a medical condition of the patient; and

a patient monitor for in response to said comparison indicator, generating an alert message associated with the threshold
value indicating the medical condition of the patient.

US Pat. No. 9,633,306

METHOD AND SYSTEM FOR APPROXIMATING DEEP NEURAL NETWORKS FOR ANATOMICAL OBJECT DETECTION

Siemens Healthcare GmbH, ...

1. A method for anatomical object detection in a medical image comprising:
training a deep neural network to detect the anatomical object in medical images;
calculating an approximation of the trained deep neural network that reduces the computational complexity of the trained deep
neural network; and

detecting the anatomical object in a received medical image of a patient using the approximation of the trained deep neural
network, wherein calculating an approximation of the trained deep neural network that reduces the computational complexity
of the trained deep neural network comprises:

for each of a plurality of nodes in each of a plurality of layers of the trained deep neural network, reconstructing a trained
weight matrix for the node using 1-D Haar wavelet bases and wavelet coefficients.

US Pat. No. 10,028,719

ADJUSTING AN X-RAY PARAMETER OF AN X-RAY UNIT

SIEMENS HEALTHCARE GMBH, ...

1. A method for adjusting an X-ray parameter of an X-ray unit, the X-ray unit including an X-ray source and an X-ray detector, the method comprising:receiving, via an interface, an X-ray projection of a region of interest and an associated X-ray parameter, the X-ray projection including X-ray intensities in a first pixel set and the X-ray parameter relating to at least one X-ray voltage from the X-ray source;
determining scattered radiation intensities in a second pixel set via a computing unit, the second pixel set being a subset of the first pixel set;
calculating, via the computing unit, first exposure parameters in the second pixel set, each of the first exposure parameters in a pixel of the second pixel set being respectively based on the X-ray intensity in the respective pixel and the scattered radiation intensity in the respective pixel;
calculating, via the computing unit, a scalar second exposure parameter based on the first exposure parameters; and
adjusting the X-ray parameter by comparing, via the computing unit, the scalar second exposure parameter with a reference value.

US Pat. No. 9,984,493

METHOD AND SYSTEM FOR VOLUME RENDERING BASED ON 3D IMAGE FILTERING AND REAL-TIME CINEMATIC RENDERING

Siemens Healthcare GmbH, ...

1. A method for volume rendering based filtering of a 3D volume, comprising:receiving, at a cloud computing system, a 3D volume from a client device;
generating, in the cloud computing system, a set of 2D projection images of the 3D volume using cinematic volume rendering, wherein generating the set of 2D projection images of the 3D volume using cinematic volume rendering comprises:
generating the set of 2D projection images of the 3D volume using a non-linear cinematic volume rendering operator; and
generating, in the cloud computing system, a reconstructed 3D volume from the set of 2D projection images using an inverse linear volumetric ray tracing operator, wherein generating the reconstructed 3D volume from the set of 2D projection images using the inverse linear volumetric ray tracing operator comprises:
generating the reconstructed 3D volume by applying the inverse linear volumetric ray tracing operator to the set of 2D projection images of the 3D volume generated using the non-linear cinematic volume rendering operator.

US Pat. No. 9,952,878

SYSTEM WITH A MEDICAL APPARATUS, AND METHOD FOR CONTROLLING STARTUP AND SHUTDOWN OF THE SYSTEM

Siemens Healthcare GmbH, ...

1. A system comprising:a medical apparatus;
an operator console comprising a console computer configured to operate the medical apparatus at least partially in response to entries made by a user into the console computer;
a first input processor assigned exclusively to the operator console and configured to acquire a shutdown command that triggers a shutdown operation of the operator console;
a second input processor assigned exclusively to the medical apparatus and configured to acquire a startup command that triggers a startup operation of the medical device;
a first interface configured to forward the shutdown command acquired by the first input processor from the operator console to the medical apparatus, with the shutdown command forwarded to the medical apparatus triggering a shutdown operation of the medical apparatus; and
a second interface configured to forward the startup command acquired by the second input processor from the medical apparatus to the operator console, with the startup command forwarded to the operator console triggering a startup operation of the operator console.

US Pat. No. 9,931,790

METHOD AND SYSTEM FOR ADVANCED TRANSCATHETER AORTIC VALVE IMPLANTATION PLANNING

Siemens Healthcare GmbH, ...

1. A method for heart valve intervention planning, comprising:estimating an anatomical surface model of a heart valve from medical image data of a patient;
segmenting calcified lesions within the heart valve in the medical image data;
generating a combined volumetric model of the heart valve and calcified lesions, wherein generating the combined volumetric model of the heart valve and calcified lesions comprises:
mapping the segmented calcified lesions to the anatomical surface model of the heart valve, and
extruding the anatomical surface model of the heart valve to a predetermined thickness; and
creating a 3D printed model of the heart valve and calcified lesions using a 3D printer, wherein the heart valve is an aortic valve and extruding the anatomical surface model of the heart valve to a predetermined thickness comprises:
extruding an aortic root surface of the anatomical surface model of the heart valve to a standard thickness associated with the aortic root if the standard thickness associated with the aortic root is greater than or equal to a minimum thickness level associated with the 3D printer;
extruding the aortic root surface of the anatomical surface model of the heart valve to the minimum thickness level associated with the 3D printer if the standard thickness associated with the aortic root is less than the minimum thickness level associated with the 3D printer;
extruding aortic valve leaflet surfaces of the anatomical surface model of the heart valve to a standard thickness associated with the aortic valve leaflets if the standard thickness associated with the aortic valve leaflets is greater than or equal to the minimum thickness level associated with the 3D printer; and
extruding the aortic valve leaflet surfaces of the anatomical surface model of the heart valve to the minimum thickness level associated with the 3D printer if the standard thickness associated with the aortic valve leaflets is less than the minimum thickness level associated with the 3D printer.

US Pat. No. 9,936,187

MULTI-RESOLUTION LIGHTFIELD RENDERING USING IMAGE PYRAMIDS

Siemens Healthcare GmbH, ...

1. A method for generating multi-resolution lightfield image pyramids, the method comprising:receiving, by an image processor, a plurality of image data sets of a volume at different resolutions for each of a plurality of different camera positions, wherein the volume represents an object or a patient;
rendering, by the image processor, an image of the volume for each of the plurality of image data sets, wherein each of the different resolutions corresponds to a level of a plurality of image pyramids; and
storing, by the server, the rendered images for each of the different camera positions together as one of the plurality of lightfield image pyramids.

US Pat. No. 9,931,094

METHOD FOR GENERATING X-RAY IMAGE DATA OF AN EXAMINATION OBJECT WITH SUPPRESSED CALCIUM SIGNAL

SIEMENS HEALTHCARE GMBH, ...

1. A method for generating X-ray image data of an examination object, the X-ray image data being calculated from X-ray projection data including one first and at least one second X-ray projection data record acquired with an energy-selective X-ray detector and each acquired in respect of a respective specific energy window, comprising:determining a calcium content in the X-ray projection data by way of a base material analysis, the calcium content describing a calcium-determined part of the X-ray attenuation caused by the examination object;
generating a mixed X-ray projection data record with calcium content suppressed by way of a weighting factor to less than one; and
reconstructing the X-ray image data from the mixed projection data record by applying a reconstruction algorithm.

US Pat. No. 9,928,986

EMITTER ARRANGEMENT

Siemens Healthcare GmbH, ...

1. An emitter configuration, comprising:at least one emitter having at least one structured emission surface for emitting electrons and formed of a plurality of mutually adjacent and spaced apart partial emission surfaces, said at least one structured emission surface made of at least one first electron emission material and lies at a first potential; and
at least one vaporizer element spaced apart from said at least one emitter, said at least one vaporizer element having at least one evaporation surface made of at least one second electron emission material and lies at a second potential.

US Pat. No. 9,895,131

METHOD AND SYSTEM OF SCANNER AUTOMATION FOR X-RAY TUBE WITH 3D CAMERA

Siemens Healthcare GmbH, ...

1. A method for X-ray tube scanner automation, comprising:
receiving an RGBD image of a patient on a patient table from a 3D camera mounted on an X-ray tube;
calculating a transformation between a coordinate system of the 3D camera and a coordinate system of the patient table;
estimating a patient model from the RGBD image of the patient; and
automatically controlling the X-ray tube to acquire an X-ray image of a region of interest of the patient based on the patient
model,

wherein estimating a patient model from the RGBD image of the patient comprises:
detecting a patient pose in the RGBD image using one or more machine learning-based pose classifiers;
detecting anatomical landmarks of the patient in the RGBD data based on the detected patient pose.

US Pat. No. 9,881,372

METHOD AND SYSTEM FOR VASCULAR DISEASE DETECTION USING RECURRENT NEURAL NETWORKS

Siemens Healthcare GmbH, ...

1. A method for vessel centerline leakage detection using a recurrent neural network, comprising:
extracting a plurality of 2D cross-section image patches from a 3D computed tomography angiography (CTA) image, wherein each
of 2D cross-section image patches is extracted at a respective one of a plurality of sampling points along a vessel centerline
of a vessel of interest in the 3D CTA image; and

detecting false branches of the vessel centerline of the vessel of interest by classifying each of the plurality of sampling
points along the vessel centerline based on the plurality of 2D cross-section image patches using a trained recurrent neural
network (RNN).

US Pat. No. 9,878,178

METHOD AND MAGNETIC RESONANCE APPARATUS FOR QUALITY CONTROL IN PLANNING RADIOTHERAPY OF A PATIENT

Siemens Healthcare GmbH, ...

1. A quality control method for planning radiotherapy of a patient, comprising:
providing a computer with magnetic resonance image data acquired from a planning volume of a patient;
in said computer, using the magnetic resonance data to generate a first electron density map of said planning volume, said
first electron density map having a first value of the electron density for at least one bone region in the planning volume;

in said computer, using said first electron density map to calculate a second electron density map, said second electron density
map having a second value of the electron density for said at least one bone region, that is reduced with respect to said
first value of said electron density for said at least one bone region;

providing said computer with an electronic designation of a radiotherapy plan for implementing radiotherapy of a target volume
situated in said planning volume;

in said computer, using said radiotherapy plan and said first electron density map to determine a first radiation dose distribution
in the planning volume;

in said computer, using said radiotherapy plan and said second electron density map to determine a second radiation dose distribution
in the planning volume;

in said computer, comparing said first radiation dose distribution with said second radiation dose distribution to obtain
a comparison result; and

in said computer, using said comparison result to generate output information related to implementation of said radiotherapy
plan, and making an electronic signal representing said output information available from said computer as an output.

US Pat. No. 9,782,089

WORKSHEET SYSTEM FOR DETERMINING MEASURED PATIENT VALUES FOR USE IN CLINICAL ASSESSMENT AND CALCULATIONS

Siemens Healthcare GmbH, ...

1. A system for determining measured patient values for use in clinical calculations, comprising:
a repository operative to record values of parameters;
an electronic form comprising a single display image including labels for values of parameters including blood pressure, ventricular
assessments and cardiac flows and a plurality of image areas including,

a first area of the single display image including data fields for presenting values of said parameters associated with a
first part of a cardiac catheterization study of a patient; and

a second area of the single display image including data fields for presenting values of said parameters associated with a
different second part of a cardiac catheterization study of said patient, wherein the values presented in the first area of
the single display image and the values presented in the second area are associated with the same parameters and at least
one value presented in the first area and associated with a first parameter is different from a value presented in the second
area and associated with the first parameter;

a user interface enabling a user to copy a second measured value presented in the first area and associated with a second
parameter to said second area of the single display image as associated with the second parameter in the second part of the
cardiac catheterization study, said user interface displaying a visual attribute in said second area to indicate that the
second measured value in the second area is a substitute value which was measured in the first part of the cardiac catheterization
study and was not measured in the second part of the cardiac catheterization study and has been copied to said second area
from said first area, the second measured value to be used as an input in calculations instead of newly measured data; and

a calculation processor for automatically calculating a cardiac flow value for the second part of the cardiac catheterization
study using the second measured value in response to said second measured value being copied to said second area, and automatically
simulating hemodynamic effects in a condition based on the copied second measured value, wherein the calculation processor
includes a non-transitory memory operative to store instructions regarding the automatic calculation of the cardiac flow value.

US Pat. No. 10,297,023

RECONSTRUCTION OF AN IMAGE ON THE BASIS OF ONE OR MORE IMAGING MODALITIES

Siemens Healthcare GmbH, ...

1. A method for reconstructing an image of an examination object, the method comprising:acquiring, by a medical imaging apparatus of a first imaging modality, a first image data record of the examination object, wherein the first image data record comprises measured data from a first field of view, and wherein the first image data record has an undersampling;
providing, by the medical imaging apparatus, at least one further image data record of the examination object of at least one further imaging modality, wherein the at least one further imaging modality is an imaging modality that differs from the first imaging modality, wherein the at least one further image data record comprises measured data from at least one further field of view, and wherein the at least one further field of view comprises at least one additional area that is not comprised by the first field of view;
reconstructing, by the medical imaging apparatus, at least one first image based on the first image data record using the at least one further image data record by a reconstruction unit, wherein the reconstructing comprises an iterative reconstruction with the at least one further image data record of the at least one further imaging modality used as a-priori knowledge for the iterative reconstruction; and
displaying, by a display, the reconstructed at least one first image.