US 12,265,145 B2
Systems and methods of deep learning for large-scale dynamic magnetic resonance image reconstruction
Anthony Christodoulou, Los Angeles, CA (US); Debiao Li, Los Angeles, CA (US); and Yuhua Chen, Los Angeles, CA (US)
Assigned to CEDARS-SINAI MEDICAL CENTER, Los Angeles, CA (US)
Appl. No. 17/642,016
Filed by Cedars-Sinai Medical Center, Los Angeles, CA (US)
PCT Filed Sep. 10, 2020, PCT No. PCT/US2020/050247
§ 371(c)(1), (2) Date Mar. 10, 2022,
PCT Pub. No. WO2021/050765, PCT Pub. Date Mar. 18, 2021.
Claims priority of provisional application 62/900,279, filed on Sep. 13, 2019.
Prior Publication US 2023/0194640 A1, Jun. 22, 2023
Int. Cl. G01R 33/56 (2006.01); G01R 33/483 (2006.01); G06N 3/08 (2023.01)
CPC G01R 33/5608 (2013.01) [G01R 33/483 (2013.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for performing magnetic resonance (MR) imaging on a subject, the method comprising:
obtaining undersampled imaging data from a region of interest of the subject, the undersampled imaging data corresponding to an image sequence having a plurality of image frames;
extracting one or more temporal basis functions from the undersampled imaging data, each of the one or more temporal basis functions corresponding to at least one time-varying dimension of the subject;
extracting one or more preliminary spatial weighting functions from the undersampled imaging data, each of the one or more preliminary spatial weighting functions corresponding to a spatially-varying dimension of the subject;
inputting the one or more preliminary spatial weighting functions into a neural network to produce one or more final spatial weighting functions, each of the final spatial weighting functions corresponding to a respective one of the one or more preliminary spatial weighting functions; and
multiplying the one or more final spatial weighting functions by the one or more temporal basis functions to generate the image sequence.