US 12,013,452 B2
Multi-contrast MRI sampling and image reconstruction
Xiao Chen, Cambridge, MA (US); Zhang Chen, Brookline, MA (US); Yikang Liu, Cambridge, MA (US); Shanhui Sun, Lexington, MA (US); Terrence Chen, Lexington, MA (US); and Lin Zhao, Athens, GA (US)
Assigned to Shanghai United Imaging Intelligence Co., Ltd., Shanghai (CN)
Filed by Shanghai United Imaging Intelligence Co., Ltd., Shanghai (CN)
Filed on May 10, 2022, as Appl. No. 17/741,307.
Prior Publication US 2023/0366964 A1, Nov. 16, 2023
Int. Cl. G01R 33/56 (2006.01); G01R 33/561 (2006.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01)
CPC G01R 33/5608 (2013.01) [G01R 33/5611 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An apparatus, comprising:
one or more processors configured to:
obtain first under-sampled magnetic resonance imaging (MRI) data associated with a first contrast, wherein the first under-sampled MRI data is derived based on a first sampling pattern;
reconstruct a first MRI image associated with the first contrast using an artificial neural network (ANN), wherein the reconstruction of the first MRI image comprises determining a first plurality of characteristics of the first under-sampled MRI data and predicting the first MRI image based on the first plurality of characteristics of the first under-sampled MRI data;
obtain second under-sampled MRI data associated with a second contrast, wherein the second under-sampled MRI data is derived based on a second sampling pattern; and
reconstruct, using the ANN, a second MRI image associated with the second contrast, wherein the first sampling pattern and the second sampling pattern are jointly determined, and wherein the reconstruction of the second MRI image comprises determining a second plurality of characteristics of the second under-sampled MRI data and predicting the second MRI image based on the second plurality of characteristics of the second under-sampled MRI data and at least a subset of the first plurality of characteristics of the first under-sampled MRI data.