Patents by Inventor Berthold Kiefer

Berthold Kiefer has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11861827
    Abstract: The disclosure relates to techniques for automatically characterizing liver tissue of a patient, comprising receiving morphological magnetic resonance image data set and at least one magnetic resonance parameter map of an imaging region comprising at least partially the liver of the patient, each acquired by a magnetic resonance imaging device, via a first interface. The techniques further include applying a trained function comprising a neural network to input data comprising at least the image data set and the parameter map. At least one tissue score describing the liver tissue is generated as output data, which is provided using a second interface.
    Type: Grant
    Filed: February 5, 2021
    Date of Patent: January 2, 2024
    Assignee: Siemens Healthcare GmbH
    Inventors: Stephan Kannengiesser, Berthold Kiefer, Tommaso Mansi, Marcel Dominik Nickel, Thomas Pheiffer
  • Patent number: 11748878
    Abstract: In a method for generating a surrogate marker based on medical image data mapping an image region, the medical image data is detected using a first interface, a first subregion of the image region is selected by segmenting a first structure included in the image region, a first property of the first subregion is extracted, the surrogate marker is determined based on the first property, and the surrogate marker is provided using a second interface.
    Type: Grant
    Filed: August 13, 2020
    Date of Patent: September 5, 2023
    Assignee: Siemens Healthcare GmbH
    Inventors: Robert Grimm, Berthold Kiefer, Heinrich von Busch
  • Publication number: 20230267611
    Abstract: Systems and methods are provided for optimizing a deep learning model. A multi-site dataset associated with different clinical sites and a deployment dataset associated with a deployment clinical site are received. A deep learning model is trained based on the multi-site dataset. The trained deep learning model is optimized based on the deployment dataset. The optimized trained deep learning model is output.
    Type: Application
    Filed: February 8, 2023
    Publication date: August 24, 2023
    Inventors: Bibo Shi, Ali Kamen, Tongbai Meng, Mamadou Diallo, Bin Lou, Robert Grimm, Heinrich von Busch, Berthold Kiefer
  • Patent number: 11662414
    Abstract: In a computer-implemented method of training a machine learning based processor, the processor can be trained to derive image data from signal data sets of multiple spin echo sequences. The trained processor can be configured to perform image processing for Magnetic Resonance Imaging (MRI) to derive the image data.
    Type: Grant
    Filed: September 30, 2020
    Date of Patent: May 30, 2023
    Assignee: Siemens Healthcare GmbH
    Inventors: Thomas Benkert, Robert Grimm, Berthold Kiefer, Marcel Dominik Nickel
  • Patent number: 11610308
    Abstract: Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.
    Type: Grant
    Filed: June 28, 2022
    Date of Patent: March 21, 2023
    Assignee: Siemens Healthcare GmbH
    Inventors: Ali Kamen, Tongbai Meng, Mamadou Diallo, Bin Lou, Xin Yu, David Jean Winkel, Dorin Comaniciu, Robert Grimm, Berthold Kiefer, Heinrich von Busch
  • Publication number: 20220358648
    Abstract: Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.
    Type: Application
    Filed: June 28, 2022
    Publication date: November 10, 2022
    Inventors: Ali Kamen, Tongbai Meng, Mamadou Diallo, Bin Lou, Xin Yu, David Jean Winkel, Dorin Comaniciu, Robert Grimm, Berthold Kiefer, Heinrich von Busch
  • Patent number: 11403750
    Abstract: Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.
    Type: Grant
    Filed: June 13, 2019
    Date of Patent: August 2, 2022
    Assignee: Siemens Healthcare GmbH
    Inventors: Ali Kamen, Ahmet Tuysuzoglu, Bin Lou, Bibo Shi, Nicolas Von Roden, Kareem Abdelrahman, Berthold Kiefer, Robert Grimm, Heinrich von Busch, Mamadou Diallo, Tongbai Meng, Dorin Comaniciu, David Jean Winkel, Xin Yu
  • Patent number: 11333734
    Abstract: A method of generating biomarker parameters includes acquiring imaging data depicting a patient using a MRI system. The imaging data is acquired for a plurality of contrasts resulting from application of a pulse on the patient's anatomy. A process is executed to generate a MoCoAve image for each contrast. This process includes dividing the imaging data for the contrast into bins corresponding to one of a plurality of respiratory motion phases, and reconstructing the imaging data in each bin to yield bin images. The process further includes selecting a reference bin image from the bin images, and warping the bin images based on the reference bin image. The warped bin images and the reference bin image are averaged to generate the MoCoAve image for the contrast. One or more biomarker parameter maps are calculated based on the MoCoAve images generated for the contrasts.
    Type: Grant
    Filed: May 7, 2020
    Date of Patent: May 17, 2022
    Assignee: Siemens Healthcare GmbH
    Inventors: Xiaodong Zhong, Vibhas S. Deshpande, Marcel Dominik Nickel, Xiaoming Bi, Stephan Kannengiesser, Berthold Kiefer
  • Publication number: 20210349166
    Abstract: A method of generating biomarker parameters includes acquiring imaging data depicting a patient using a MRI system. The imaging data is acquired for a plurality of contrasts resulting from application of a pulse on the patient's anatomy. A process is executed to generate a MoCoAve image for each contrast. This process includes dividing the imaging data for the contrast into bins corresponding to one of a plurality of respiratory motion phases, and reconstructing the imaging data in each bin to yield bin images. The process further includes selecting a reference bin image from the bin images, and warping the bin images based on the reference bin image. The warped bin images and the reference bin image are averaged to generate the MoCoAve image for the contrast. One or more biomarker parameter maps are calculated based on the MoCoAve images generated for the contrasts.
    Type: Application
    Filed: May 7, 2020
    Publication date: November 11, 2021
    Inventors: Xiaodong Zhong, Vibhas S. Deshpande, Marcel Dominik Nickel, Xiaoming Bi, Stephan Kannengiesser, Berthold Kiefer
  • Publication number: 20210248736
    Abstract: Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.
    Type: Application
    Filed: June 13, 2019
    Publication date: August 12, 2021
    Inventors: Ali Kamen, Ahmet Tuysuzoglu, Bin Lou, Bibo Shi, Nicolas Von Roden, Kareem Abdelrahman, Berthold Kiefer, Robert Grimm, Heinrich von Busch, Mamadou Diallo, Tongbai Meng, Dorin Comaniciu, David Jean Winkel, Xin Yu
  • Publication number: 20210248741
    Abstract: The disclosure relates to techniques for automatically characterizing liver tissue of a patient, comprising receiving morphological magnetic resonance image data set and at least one magnetic resonance parameter map of an imaging region comprising at least partially the liver of the patient, each acquired by a magnetic resonance imaging device, via a first interface. The techniques further include applying a trained function comprising a neural network to input data comprising at least the image data set and the parameter map. At least one tissue score describing the liver tissue is generated as output data, which is provided using a second interface.
    Type: Application
    Filed: February 5, 2021
    Publication date: August 12, 2021
    Applicant: Siemens Healthcare GmbH
    Inventors: Stephan Kannengiesser, Berthold Kiefer, Tommaso Mansi, Marcel Dominik Nickel, Thomas Pheiffer
  • Publication number: 20210096204
    Abstract: In a computer-implemented method of training a machine learning based processor, the processor can be trained to derive image data from signal data sets of multiple spin echo sequences. The trained processor can be configured to perform image processing for Magnetic Resonance Imaging (MRI) to derive the image data.
    Type: Application
    Filed: September 30, 2020
    Publication date: April 1, 2021
    Applicant: Siemens Healthcare GmbH
    Inventors: Thomas Benkert, Robert Grimm, Berthold Kiefer, Marcel Dominik Nickel
  • Publication number: 20210088614
    Abstract: In a method for an actuation of a magnetic resonance device for capturing image data from an examination region of an examination object, at least one first control sequence is provisioned, the magnetic resonance device is actuated according to the at least one first control sequence to capture first data from the examination object, the first data is analyzed with respect to a property to generate a result, and, based on the result, a selective performance of one of: a selection of a further control sequence, and termination of the actuation of the magnetic resonance device, is performed.
    Type: Application
    Filed: September 18, 2020
    Publication date: March 25, 2021
    Applicant: Siemens Healthcare GmbH
    Inventors: Robert Grimm, Berthold Kiefer, Heinrich von Busch
  • Publication number: 20210049761
    Abstract: In a method for generating a surrogate marker based on medical image data mapping an image region, the medical image data is detected using a first interface, a first subregion of the image region is selected by segmenting a first structure included in the image region, a first property of the first subregion is extracted, the surrogate marker is determined based on the first property, and the surrogate marker is provided using a second interface.
    Type: Application
    Filed: August 13, 2020
    Publication date: February 18, 2021
    Applicant: Siemens Healthcare GmbH
    Inventors: Robert Grimm, Berthold Kiefer, Heinrich von Busch
  • Patent number: 10768256
    Abstract: In a method for displaying quantitative magnetic resonance image data, and a processor, and a magnetic resonance (MR) apparatus that implement such a method, first quantitative MR image data of an examination object are provided to the processor, the first quantitative MR image having been obtained using an MR scanner with a first basic magnetic field strength. The first quantitative magnetic resonance image data are converted in the processor from the first basic magnetic field strength to a second basic magnetic field strength, thereby generating second quantitative MR image data, which are then displayed.
    Type: Grant
    Filed: April 28, 2017
    Date of Patent: September 8, 2020
    Assignee: Siemens Healthcare GmbH
    Inventors: Berthold Kiefer, Lars Lauer, Heiko Meyer, Edgar Mueller, Elmar Rummert, David Grodzki
  • Patent number: 10748277
    Abstract: Tissue is characterized using machine-learnt classification. The prognosis, diagnosis or evidence in the form of a similar case is found by machine-learnt classification from features extracted from frames of medical scan data. The texture features for tissue characterization may be learned using deep learning. Using the features, therapy response is predicted from magnetic resonance functional measures before and after treatment in one example. Using the machine-learnt classification, the number of measures after treatment may be reduced as compared to RECIST for predicting the outcome of the treatment, allowing earlier termination or alteration of the therapy.
    Type: Grant
    Filed: September 9, 2016
    Date of Patent: August 18, 2020
    Assignees: Siemens Healthcare GmbH, The Johns Hopkins University
    Inventors: Shaohua Kevin Zhou, David Liu, Berthold Kiefer, Atilla Peter Kiraly, Benjamin L. Odry, Robert Grimm, Li Pan, Ihab Kamel
  • Patent number: 10718837
    Abstract: Some aspects of the present disclosure relate to ultrashort-echo-time (UTE) imaging. In one embodiment, a method includes acquiring UTE imaging data associated with an area of interest of a subject. The acquiring comprises applying an imaging pulse sequence with a three-dimensional (3D) spiral acquisition and a nonselective excitation pulse. The method also includes reconstructing at least one image of the area of interest from the acquired UTE imaging data.
    Type: Grant
    Filed: April 21, 2017
    Date of Patent: July 21, 2020
    Assignees: UNIVERSITY OF VIRGINIA PATENT FOUNDATION, SIEMENS HEALTHCARE GMBH
    Inventors: John P. Mugler, III, Samuel W. Fielden, G. Wilson Miller, IV, Craig H. Meyer, Talissa A. Altes, Alto Stemmer, Josef Pfeuffer, Berthold Kiefer
  • Publication number: 20200217915
    Abstract: A magnetic resonance imaging system and method are provided for improved determination of noise bias effects in calculating fitted parameters for quantitative MRI procedures. The system and method includes selecting a range for the SNR and fitted parameter values, and for each of a plurality of base pairs of these values and for a plurality of b values, adding a random noise term to the real and imaginary components of a plurality of corresponding signal terms, fitting magnitudes of the resulting “noisy” signals to determine a “noisy” fitted parameter value, and compare the “noisy” and base fitted parameter values to determine a noise-based error for each pair of base values. The noise-based errors can be used to generate an error map, modify imaging parameters to reduce such errors, or correct fitted parameters directly.
    Type: Application
    Filed: January 8, 2019
    Publication date: July 9, 2020
    Inventors: Xiaodong Zhong, Marcel Dominik Nickel, Stephan Kannengiesser, Brian Dale, Berthold Kiefer, Mustafa R. Bashir
  • Patent number: 10705172
    Abstract: In a method and magnetic resonance (MR) apparatus for performing an adjustment of the MR system, an examination object under is divided into at least one excitation volume. First adjustment parameters for the at least one excitation volume of the object, and second adjustment parameters for the at least one excitation volume of the object, which differ from the first adjustment parameters are determined. First MR signals are acquired from the at least one excitation volume using the first adjustment parameters. Second MR signals are acquired from an excitation volume using the second adjustment parameters. A first MR image of the at least one excitation volume is reconstructed using the first MR signal. A second MR image of the at least one excitation volume is reconstructed using the second MR signal.
    Type: Grant
    Filed: February 24, 2017
    Date of Patent: July 7, 2020
    Assignee: Siemens Healthcare GmbH
    Inventors: Berthold Kiefer, Alto Stemmer
  • Patent number: 10684340
    Abstract: A magnetic resonance imaging system and method are provided for improved determination of noise bias effects in calculating fitted parameters for quantitative MRI procedures. The system and method includes selecting a range for the SNR and fitted parameter values, and for each of a plurality of base pairs of these values and for a plurality of b values, adding a random noise term to the real and imaginary components of a plurality of corresponding signal terms, fitting magnitudes of the resulting “noisy” signals to determine a “noisy” fitted parameter value, and compare the “noisy” and base fitted parameter values to determine a noise-based error for each pair of base values. The noise-based errors can be used to generate an error map, modify imaging parameters to reduce such errors, or correct fitted parameters directly.
    Type: Grant
    Filed: January 8, 2019
    Date of Patent: June 16, 2020
    Assignees: Siemens Healthcare GmbH, Duke University
    Inventors: Xiaodong Zhong, Marcel Dominik Nickel, Stephan Kannengiesser, Brian Dale, Berthold Kiefer, Mustafa R. Bashir