Patents Assigned to Siemens Healthcare GmbH
  • Patent number: 11182925
    Abstract: A correspondence between frames of a set of medical image data is determined where the set of medical image data includes at least one frame acquired without contrast medium and at least one frame acquired with contrast medium. First data representing a first image frame acquired without contrast medium is received. Second data representing a second image frame acquired with contrast medium is received. A position of a feature of a medical device in the second image frame is determined at least partly on the basis of a position of the feature determined from the first image frame.
    Type: Grant
    Filed: October 30, 2018
    Date of Patent: November 23, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Liheng Zhang, Vivek Kumar Singh, Kai Ma, Terrence Chen
  • Patent number: 11181598
    Abstract: A computer-implemented method for reconstructing a MRI image, including: receiving a plurality of MRI measurement data sets ƒ1 to ƒN, wherein each data set is acquired from an examination object based on a different MRI protocol of an MRI system; receiving MRI images u10 to uN0 corresponding to the MRI measurement data sets ƒ1 to ƒN; applying, in at least a first step GD1, trained functions to the MRI images u10 to uN0, using a neural network and a forward-sampling operator, wherein at least one output MRI image uT is generated; and providing the at least one output MRI image uT, wherein the forward-sampling operator determines an agreement between at least one MRI image u10 to uN0 and the corresponding MRI measurement data set ƒ1 to ƒN.
    Type: Grant
    Filed: April 24, 2020
    Date of Patent: November 23, 2021
    Assignees: Siemens Healthcare GmbH, The General Hospital Corporation
    Inventors: Daniel Polak, Kawin Setsompop
  • Patent number: 11179122
    Abstract: A system and method includes detection of a trigger event, automatic injection, in response to detecting the trigger event, of a bolus of contrast medium into a patient volume after expiration of a predetermined injection delay period, automatic acquisition, in response to detecting the trigger event, of a plurality of images after expiration of a predetermined imaging delay period, where two or more of the plurality of images comprise an image of the bolus at respective different locations within vasculature of the patient volume, generation of a composite image based on the plurality of images, the composite image including a representation of the vasculature of the patient volume, and display of the composite image.
    Type: Grant
    Filed: September 25, 2019
    Date of Patent: November 23, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: John Christopher Rauch, Martin Trini
  • Patent number: 11181593
    Abstract: A gradient coil assembly for a magnetic resonant apparatus has a primary coil and a secondary coil, wherein the primary coil has a first primary coil winding and a second primary coil winding, wherein the first primary coil winding and the second primary coil winding are electrically connected to a voltage source and are jointly designed to generate a magnetic field gradient in a direction when the voltage source induces a current in those windings.
    Type: Grant
    Filed: May 18, 2018
    Date of Patent: November 23, 2021
    Assignee: Siemens Healthcare GmbH
    Inventor: Ralph Kimmlingen
  • Patent number: 11181596
    Abstract: A storage medium, a magnetic resonance apparatus, and a method for obtaining an operating parameter of a magnetic resonance apparatus are disclosed herein. The method includes generating of at least one echo train, wherein the generation of an echo train includes: setting a given set of parameters; applying at least one radio frequency excitation pulse; and applying a dephasing gradient in readout direction; and reading out the echo train having at least two echo signals, wherein a readout gradient is applied while reading out the echo signals. The method further includes acquiring at least two echo signals, wherein the set of parameters differs in at least one parameter being used for different echo signals; processing the echo signals line by line to projections; and obtaining the operating parameter using the projections.
    Type: Grant
    Filed: January 9, 2020
    Date of Patent: November 23, 2021
    Assignee: Siemens Healthcare GmbH
    Inventor: Mario Zeller
  • Publication number: 20210358168
    Abstract: A method is for generating a medical result image using a current image, a target image and a reference image. All images depict at least partially the same body region of a patient. In an embodiment, the method includes defining at least one image segment within the target image; registering the reference image with the target image by establishing a registration matrix for each image segment within the target image, the respective registration matrix being specific for the respective image segment; detecting a position of a surgical instrument in the current image, the position corresponding to an image segment of the target image; and generating the medical result image by fusing the current image and the reference image using the registration matrix assigned to the image segment according to the position of the surgical instrument within the current image.
    Type: Application
    Filed: October 24, 2018
    Publication date: November 18, 2021
    Applicant: Siemens Healthcare GmbH
    Inventors: Qi SUN, Jingfeng HAN
  • Publication number: 20210357689
    Abstract: A computer-implemented method for the further training of an artificial-intelligence evaluation algorithm that has already been trained based upon basic training data, wherein the evaluation algorithm ascertains output data describing evaluation results from input data comprising image data recorded with a respective medical imaging facility. In an embodiment, the method includes ascertaining at least one additional training data set containing training input data and training output data assigned thereto; and training the evaluation algorithm using the at least one additional training data set. The additional training data set is ascertained from the input data used during a clinical examination process with a medical imaging facility, which the already-trained evaluation algorithm was used, and output data of the already-trained evaluation algorithm that has been at least partially correctively modified by the user.
    Type: Application
    Filed: May 5, 2021
    Publication date: November 18, 2021
    Applicant: Siemens Healthcare GmbH
    Inventors: Frank ENDERS, Dorothea ROTH, Michael SCHRAPP, Matthias SENN, Michael SUEHLING
  • Publication number: 20210353176
    Abstract: A computer-implemented method is for classifying a body type of at least one person. In an embodiment, the method includes receiving at least one image data record of the respective person, which maps at least one subarea of the person; and ascertaining a body type for the person by an optimization method. A respective person model is used for each of the possible body types, which as a function of at least one person parameter determines an expected person geometry of the person described by the person model. The body type is selected by the optimization method by a similarity measure for the similarity of the image data record or a person geometry ascertained from the image data record being optimized with the expected person geometry by selecting the body type.
    Type: Application
    Filed: May 10, 2021
    Publication date: November 18, 2021
    Applicant: Siemens Healthcare GmbH
    Inventors: Robert LAPP, Andreas KRAUSS
  • Patent number: 11175362
    Abstract: A flexibly and universally applicable method for simultaneous multi-slice nuclear spin tomography is provided. Thereby, a pulse space region to be sampled is specified by means of a processor, wherein a first pulse space dimension (ky) is assigned to a first phase-encoded axis and a second pulse space dimension (kz) is assigned to a second phase-encoded axis and the second phase-encoded axis corresponds to a slice axis. An undersampling scheme is specified by means of the processor, wherein along the second pulse space dimension (kz), an incomplete sampling is provided. Then, a magnetic resonance scan is carried out within the pulse space region to be sampled according to the undersampling scheme and according to respective phase-encodings of the first and second phase-encoded axis.
    Type: Grant
    Filed: February 28, 2020
    Date of Patent: November 16, 2021
    Assignee: Siemens Healthcare GmbH
    Inventor: Thorsten Feiweier
  • Patent number: 11172842
    Abstract: In a method for analyzing acquired magnetic resonance images, an image series is provided that includes acquired magnetic resonance images of a slice of an object, picture elements of the acquired magnetic resonance images of the image series are fitted to generate a parameter map and an error map, the acquired magnetic resonance images are automatically segmented to generate image segments, histograms of the parameter map and the error map are generated based on the image segments, and the histograms are analyzed to generate an output of analysis results and/or generate a visualization including the parameter map, the error map, and the image segments. The acquired magnetic resonance images can have a variation of a contrast-determining acquisition parameter.
    Type: Grant
    Filed: July 24, 2019
    Date of Patent: November 16, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Christoph Forman, Andreas Greiser
  • Patent number: 11173604
    Abstract: The disclosure relates to a method for operating a robot, a data memory with a corresponding program code, the corresponding robot, and a corresponding robot system. Different coordinate system and their relationships to one another are used to position a tool in a target pose. A stationary reference coordinate system originating at a robot foot of the robot and a target coordinate system originating at the tool are specified. Herein, a z-axis of the target coordinate system corresponds to a specified axis of the tool. The orientations of an x-axis and a y-axis of the target coordinate system are calculated by a first cross product of the orientation of the specified axis and a direction vector, that is not parallel thereto, of coordinate axis of the reference coordinate system and by a second cross product of a result of the first cross product and the orientation of the specified axis.
    Type: Grant
    Filed: June 12, 2019
    Date of Patent: November 16, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Holger Mönnich, Rafik Mebarki
  • Patent number: 11172902
    Abstract: The disclosure relates to a method for recording a panorama dataset of an examination object by a movable medical x-ray device, to a medical x-ray device, and to a computer program product for carrying out the method. The medical x-ray device has an x-ray source, which emits a bundle of x-rays, wherein a first image segment, which maps at least one part of the examination object, is recorded at a first point in time. Position data is acquired, which maps the spatial position of the x-ray device at this first point in time. At least one further image segment along an imaging path is recorded after there has been a movement of the x-ray device, wherein the imaging path lies in one plane, wherein a central ray of the bundle of x-rays emitted by the x-ray source does not run in parallel to the plane in which the imaging path lies. Additionally, position data is acquired, which maps the spatial position of the x-ray device at the time of the recording of the at least one further image segment.
    Type: Grant
    Filed: February 7, 2020
    Date of Patent: November 16, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Alexander Gemmel, Björn Kreher, Holger Kunze, Markus Weiten, Jessica Magaraggia, Gerhard Kleinszig, Tobias Lenich, Edgar Zaus
  • Patent number: 11175366
    Abstract: A method for acquiring magnetic resonance imaging data with respiratory motion compensation using one or more motion signals includes acquiring a plurality of gradient-delay-corrected radial readout views of a subject using a free-breathing multi-echo pulse sequence, and sampling a plurality of data points of the gradient-delay-corrected radial readout views to yield a self-gating signal. The self-gating signal is used to determine a plurality of respiratory motion states corresponding to the plurality of gradient-delay-corrected radial readout views. The respiratory motion states are used to correct respiratory motion bias in the gradient-delay-corrected radial readout views, thereby yielding gradient-delay-corrected and motion-compensated multi-echo data. One or more images are reconstructed using the gradient-delay-corrected and motion-compensated multi-echo data.
    Type: Grant
    Filed: February 5, 2020
    Date of Patent: November 16, 2021
    Assignees: Siemens Healthcare GmbH, The Regents of the University of California
    Inventors: Xiaodong Zhong, Holden H. Wu, Vibhas S. Deshpande, Tess Armstrong, Li Pan, Marcel Dominik Nickel, Stephan Kannengiesser
  • Patent number: 11172905
    Abstract: A method, in an embodiment, is for setting an X-ray intensity using a structured anode or a field emitter cathode or a finger-shaped cathode head. Other embodiments include an associated X-ray device, an associated single X-ray tube CT scanner, an associated dual X-ray tube CT scanner, and an associated computer program product.
    Type: Grant
    Filed: May 12, 2020
    Date of Patent: November 16, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Dieter Matuszok, Anja Fritzler, Martin Petersilka
  • Patent number: 11176717
    Abstract: A method for decomposing noise into white and spatially correlated components during MR thermometry imaging includes acquiring a series of MR images of an anatomical object and generating a series of temperature difference maps of the anatomical object. The method further includes receiving a selection of a region of interest (ROI) within the temperature difference map and estimating total noise variance values depicting total noise variance in the temperature difference map. Each total noise variance value is determined using a random sampling of a pre-determined number of voxels from the ROI. A white noise component and a spatially correlated noise component of the total noise variance providing a best fit to the total noise variance values for all of the random samplings are identified. The white noise component and the spatially correlated noise component are displayed on a user interface.
    Type: Grant
    Filed: September 26, 2019
    Date of Patent: November 16, 2021
    Assignees: Siemens Healthcare GmbH, The United States of America, as Represented by the Secretary. Department of Health and Human Services
    Inventors: Waqas Majeed, Sunil Goraksha Patil, Rainer Schneider, Himanshu Bhat, Adrienne Campbell
  • Patent number: 11176188
    Abstract: A visualization framework based on document representation learning is described herein. The framework may first convert a free text document into word vectors using learning word embeddings. Document representations may then be determined in a fixed-dimensional semantic representation space by passing the word vectors through a trained machine learning model, wherein more related documents lie closer than less related documents in the representation space. A clustering algorithm may be applied to the document representations for a given patient to generate clusters. The framework then generates a visualization based on these clusters.
    Type: Grant
    Filed: January 9, 2018
    Date of Patent: November 16, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Halid Ziya Yerebakan, Yoshihisa Shinagawa, Parmeet Singh Bhatia, Yiqiang Zhan
  • Patent number: 11177031
    Abstract: A computer-implemented system to facilitate access to a plurality of automated applications via a healthcare network including a plurality of devices The system is configured to maintain a first association between each of the plurality of automated applications and at least one defined input; and for each of the at least one defined input, a second association between the predefined input and a corresponding action. Responsive to receipt of a first defined input from a first device, the system identifies, based on the first association, at least one automated application. Further, the system triggers, based on the second association, at least one of the identified automated application to perform the action corresponding to the first defined input in order to process medical information associated with the first defined input; and causes at least one of the identified automated application to communicate information relating to the action to the first device.
    Type: Grant
    Filed: September 12, 2018
    Date of Patent: November 16, 2021
    Assignee: SIEMENS HEALTHCARE GMBH
    Inventors: Lutz Dominick, Vladyslav Ukis
  • Publication number: 20210349168
    Abstract: The disclosure relates to techniques for diffusion imaging of an examination region of a patient using a magnetic resonance facility. The technique may include specifying a number, which is at least two, of diffusion gradient pulse sequences for recording diffusion data sets using the magnetic resonance facility such that the diffusion gradient pulse sequences have a b-matrix that describes a planar diffusion encoding. The matrix may have precisely two intrinsic values that differ from zero. The technique may further include recording the diffusion data sets with the specified diffusion gradient sequences, and acquiring a trace-weighted image data set by geometric averaging of the at least two diffusion data sets. The diffusion gradient pulse sequences are determined such that the sum of all the b-matrices results in the unit matrix multiplied by a factor that characterizes the diffusion weighting (e.g. a predetermined b-value) and the number divided by three.
    Type: Application
    Filed: May 5, 2021
    Publication date: November 11, 2021
    Applicant: Siemens Healthcare GmbH
    Inventor: Thorsten Feiweier
  • Patent number: 11166689
    Abstract: A computer-implemented method and system for providing a dynamic mask image, including receiving projection images that image an examination region containing at least one vessel from at least two different projection directions, receiving a static mask image, initializing the dynamic mask image, determining exclusive rays that extend in each case parallel to one of the projection directions and correspond to a respective image value in the associated projection image, wherein at least one of the exclusive rays in each case extends through precisely one of the unmasked image areas of the static mask image, identifying and masking contrasted and uncontrasted vessels in the static mask image, annotating the contrasted and uncontrasted vessels in the dynamic mask image, determining and masking an imaging of the contrasted vessels in the projection images, repeating certain steps until an abort condition occurs, and providing the dynamic mask image.
    Type: Grant
    Filed: April 20, 2021
    Date of Patent: November 9, 2021
    Assignee: Siemens Healthcare GmbH
    Inventor: Michael Manhart
  • Patent number: D935609
    Type: Grant
    Filed: November 19, 2019
    Date of Patent: November 9, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Christian DeBuys, Young-Ho Kim, Ankur Kapoor, Tommaso Mansi