System and Method for Quantitative Magnetic Resonance Imaging Using a Deep Learning Network

    公开(公告)号:US20240230810A1

    公开(公告)日:2024-07-11

    申请号:US18554397

    申请日:2022-04-11

    Abstract: A method for generating magnetic resonance imaging (MRI) quantitative parameter maps includes receiving at least one multi-contrast magnetic resonance (MR) image of a subject, providing the image to an artifact suppression deep learning network of a two-stage deep learning network and generating at least one multi-contrast MR image with suppressed undersampling artifacts using the artifact suppression deep learning network. The method further includes providing the at least one multi-contrast MR image with suppressed undersampling artifacts to a parameter mapping deep learning network of the two-stage deep learning network, generating at least one quantitative MR parameter map and generating an uncertainty estimation map for the at least one quantitative MR parameter map using the parameter mapping deep learning network. The method further includes displaying at least one multicontrast MR image with suppressed undersampling artifacts, at least one quantitative MR parameter map, and the corresponding uncertainty estimation map on a display.

    Systems and methods for magnetic resonance imaging

    公开(公告)号:US11977140B2

    公开(公告)日:2024-05-07

    申请号:US17807855

    申请日:2022-06-20

    CPC classification number: G01R33/485 G01R33/243 G01R33/4828 G01R33/5616

    Abstract: The present disclosure provides a system for MRI. The system may obtain a plurality of echo signals relating to a subject that are excited by an MRI pulse sequence applied to the subject. The system may perform a quantitative measurement on the subject based on the plurality of echo signals. The MRI pulse sequence may include a CEST module configured to selectively excite exchangeable protons or exchangeable molecules in the subject, an RF excitation pulse applied after the CEST module configured to excite a plurality of gradient echoes, and one or more refocusing pulses applied after the RF excitation pulse. Each of the refocusing pulses may be configured to excite one or more spin echoes. The one or more spin echoes excited by at least one of the one or more refocusing pulses may include a symmetric spin echo and one or more asymmetric spin echoes.

    DIXON-TYPE WATER/FAT SEPARATION MR IMAGING
    4.
    发明公开

    公开(公告)号:US20240094320A1

    公开(公告)日:2024-03-21

    申请号:US18275816

    申请日:2022-02-08

    Inventor: Holger Eggers

    Abstract: The invention relates to a method of Dixon-type MR imaging. The object (10) is subjected to a dual- or multi-acquisition imaging sequence comprising a series of temporally equidistant RF pulses. An echo signal is generated in the presence of a readout magnetic field gradient in each time interval (TR) between successive RF pulses, with the echo time varying between at least a first value (TE1) associated with a first acquisition (ACQ1) and a second value (TE2) associated with a second acquisition (ACQ2). The invention proposes that at least one of the magnetic field gradients preceding and/or succeeding the readout magnetic field gradient in each time interval (TR) is temporally shifted, varied in duration and/or varied in amplitude between time intervals (TR). In this way, a reduction of the acoustic noise generated by the multi-acquisition Dixon sequence and, thus, of the discomfort for patients undergoing a corresponding examination is achieved. The echo signals are recorded and an MR image is reconstructed with separating signal contributions from water and fat based on the recorded echo signals of the at least two acquisitions (ACQ1, ACQ2). Moreover the invention relates to an MR device (1) and to a computer program to be run on an MR device (1).

Patent Agency Ranking