公开(公告)号：US20230368393A1

公开(公告)日：2023-11-16

申请号：US18315298

申请日：2023-05-10

Applicant: Case Western Reserve University

Inventor： Mark A. Griswold ,  Yong Chen ,  Chaitra Badve ,  Rasim Boyacioglu

IPC: G06T7/11 ,  G01R33/56 ,  A61B5/055 ,  G06T7/00 ,  G06T7/136

CPC classification number: G06T7/11 ,  G01R33/5608 ,  A61B5/055 ,  G06T7/0012 ,  G06T7/136 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/20221 ,  G06T2207/30016 ,  G06T2207/30096

Abstract: The present application provides an automated system and method for improving and generating annotated magnetic resonance (MRI) images based on magnetic resonance fingerprinting (MRF) data. The present disclosure also provides an automated method for generating the automated system for improving annotated MRI images. In some aspects, the method comprises accessing MRF data, MRI data, and images annotated with bulk-pixel labels that identify a tissue class for a group of patients. The annotated images can be used to train a machine learning system based on MRF data. The system can be trained to assign pixel labels to pixels outside the bulk-pixel labels to create an automated system. The automated system provided may be used to determine disease states using MRF data and generate machine-annotated images that include labels that indicate a tissue class. In this way, the present disclosure provides an automated system and method for improving incomplete annotations.

公开(公告)号：US20230039004A1

公开(公告)日：2023-02-09

申请号：US17758138

申请日：2020-12-30

Applicant: Case Western Reserve University ,  Vanderbilt University

Inventor： Mark A. Griswold ,  William A. Grissom

IPC: G01R33/565 ,  G01R33/483

Abstract: The present application provides a system and method for using a nuclear magnetic resonance (NMR) system. The method includes performing a pulse sequence using the NMR system that spatially encodes NMR signal evolutions to be acquired from a subject using an aggregated radio-frequency (B1) field incoherence and resolving the NMR signal evolutions acquired from the subject using at least one of a dictionary of known magnetic resonance fingerprinting (MRF) signal evolutions to determine matches in the NMR signal evolutions to the known MRF signal evolutions or an optimization process. The method also includes generating at least two spatially-resolved measurements indicating quantitative tissue parameters of the subject in at least two locations.

公开(公告)号：US11519987B2

公开(公告)日：2022-12-06

申请号：US17301509

申请日：2021-04-05

Applicant: Case Western Reserve University ,  Government of the United States, as represented by the Secretary of Commerce ,  The Regents of the University of Colorado, a body corporate

Inventor： Kathryn Keenan ,  Megan Poorman ,  Rasim Boyacioglu ,  Mark A. Griswold

IPC: G01R33/50 ,  G01R33/56 ,  A61B5/055 ,  A61B5/00 ,  G01R33/385

Abstract: A method for temperature quantification using magnetic resonance fingerprinting (MRF) includes acquiring MRF data from a region of interest in a subject using an MRF pulse sequence with smoothly varying RF phase for MR resonant frequencies that is played out continuously. For each of a plurality of time intervals during acquisition of the MRF data the method further includes comparing a set of the MRF data associated with the time interval to an MRF dictionary to determine at least one quantitative parameter of the acquired MRF data, determining a temperature change based on the at least one quantitative parameter and generating a quantitative map of the temperature change in the region of interest. The region of interest can include aqueous and adipose tissue.

公开(公告)号：US20200341092A1

公开(公告)日：2020-10-29

申请号：US16859175

申请日：2020-04-27

Applicant: Case Western Reserve University

Inventor： Yun Jiang ,  Mark A. Griswold ,  Gregor Korzdorfer ,  Mathias Nittka

IPC: G01R33/50 ,  G01R33/56 ,  G01R33/54 ,  G01R33/48 ,  G01R33/561 ,  A61B5/055

Abstract: A system and method is provided for acquisition of magnetic resonance fingerprinting (“MRF”) data that includes determining a non-locally sequential sampling pattern for a Cartesian grid of k-space, performing a series of sequence blocks using acquisition parameters that vary between sequence blocks to acquire MRF data from a subject using the Cartesian grid of k-space and the determined non-locally sequential sampling pattern, assembling the MRF data into a series of signal evolutions, comparing the series of signal evolutions to a dictionary of known signal evolutions to determine tissue properties of the subject, and generating a report indicating the tissue properties of the subject.

公开(公告)号：USD888074S1

公开(公告)日：2020-06-23

申请号：US29671634

申请日：2018-11-28

Applicant: Case Western Reserve University

Designer： Mark A. Griswold

公开(公告)号：US10670680B2

公开(公告)日：2020-06-02

申请号：US15947558

申请日：2018-04-06

Applicant: Case Western Reserve University

Inventor： Bhairav Bipin Mehta ,  Mark A. Griswold

IPC: G01V3/00 ,  G01R33/56 ,  G01R33/48 ,  G01R33/54 ,  G01R33/565 ,  G01R33/50

Abstract: Methods for magnetic resonance fingerprinting (“MRF”) that are more robust to patient motion than conventional MRF techniques are described. The methods described in the present disclosure provide an image reconstruction algorithm for MRF that decreases the motion sensitivity of MRF.

公开(公告)号：US20190353736A1

公开(公告)日：2019-11-21

申请号：US16416707

申请日：2019-05-20

Applicant: Case Western Reserve University

Inventor： Vikas Gulani ,  Satyam Ghodasara ,  Katherine Wright ,  Nicole Seiberlich ,  Mark A. Griswold

IPC: G01R33/56 ,  G01R33/563

Abstract: The present application provides a system and method for quantifying perfusion using a dictionary matching approach. In some aspects, the method comprises performing a predetermined pulse sequence using an MRI system to acquire MRI data from the subject after having delivered a dose of a contrast agent to the subject. The method also includes comparing the MRI data to a dictionary to determine perfusion information, and generating, using the perfusion information, a report indicative of perfusion within the subject.

公开(公告)号：US20190353730A1

公开(公告)日：2019-11-21

申请号：US16387264

申请日：2019-04-17

Applicant: Case Western Reserve University

Inventor： Mark A. Griswold ,  Mingrui Yang

IPC: G01R33/48 ,  G01R33/56 ,  G06N20/00

Abstract: A method for creating a dictionary for a magnetic resonance fingerprinting (MRF) reconstruction includes training a semi-supervised learning system based on at least a set of MRF data and a set of control variables and generating a plurality of signal evolutions using the trained semi-supervised learning system. The method also includes generating an MRF dictionary using the plurality of signal evolutions generated using the trained semi-supervised learning system and storing the MRF dictionary in a memory. In one embodiment, the semi-supervised learning system is a MRF generative adversarial network (GAN).

公开(公告)号：US20190353718A1

公开(公告)日：2019-11-21

申请号：US16461549

申请日：2017-11-15

Applicant: Case Western Reserve University

Inventor： Mark A. Griswold ,  Anagha Deshmane

IPC: G01R33/24 ,  G01R33/50 ,  G01R33/48 ,  G01R33/565 ,  A61B5/055 ,  A61B5/00

Abstract: A system and method is provided for correcting receiver bias during quantitative proton density mapping with magnetic resonance fingerprinting (MRF). The method comprises acquiring MRF data from a region of interest in a subject by performing a pulse sequence using a series of varied sequence blocks to elicit a series of signal evolutions. The method further comprises comparing the MRF data to a MRF dictionary to simultaneously map proton density and another tissue property from the region of interest, the proton density map having a proton density signal and a receiver sensitivity profile signal. The method also includes quantifying the proton density signal and the receiver sensitivity profile signal using parameters provided by the proton density map and the tissue property map, and generating a quantitative map from the region of interest based on the proton density signal.

公开(公告)号：US10459055B2

公开(公告)日：2019-10-29

申请号：US15945594

申请日：2018-04-04

Applicant: Case Western Reserve University

Inventor： Mark A. Griswold ,  Yun Jiang

IPC: G01R33/561 ,  G01R33/56 ,  G01R33/50 ,  G06T7/00 ,  G01R33/483 ,  G01R33/54

Abstract: The present disclosure provides systems and methods for magnetic resonance fingerprinting (MRF). The method including steps comprising acquiring a plurality of MRF signals from a plurality of excitation volumes within a subject, wherein at least two of the plurality of excitation volumes differ in location within the subject, and wherein each of the excitation volumes partially overlap to form an overlap volume. The method also includes comparing the plurality of MRF signals acquired from the overlap volume with a dictionary of signal evolutions, determining one or more physical parameters of the overlap volume within the subject, and generating a report at least indicating the one or more physical parameters of the overlap volume within the subject.