Data-Consistent non-Cartesian deep subspace learning for efficient dynamic MR image reconstruction.
Data-Consistent non-Cartesian deep subspace learning for efficient dynamic MR image reconstruction.
复制标题
DOI:
10.1109/isbi52829.2022.9761497
复制
发表时间:
2022-03
期刊:
影响因子:
--
通讯作者:
Christodoulou, Anthony G.
中科院分区:
文献类型:
--
作者:
Chen, Zihao;Chen, Yuhua;Xie, Yibin;Li, Debiao;Christodoulou, Anthony G.
Non-Cartesian sampling with subspace-constrained image reconstruction is a popular approach to dynamic MRI, but slow iterative reconstruction limits its clinical application. Data-consistent (DC) deep learning can accelerate reconstruction with good image quality, but has not been formulated for non-Cartesian subspace imaging. In this study, we propose a DC non-Cartesian deep subspace learning framework for fast, accurate dynamic MR image reconstruction. Four novel DC formulations are developed and evaluated: two gradient decent approaches, a directly solved approach, and a conjugate gradient approach. We applied a U-Net model with and without DC layers to reconstruct T1-weighted images for cardiac MR Multitasking (an advanced multidimensional imaging method), comparing our results to the iteratively reconstructed reference. Experimental results show that the proposed framework significantly improves reconstruction accuracy over the U-Net model without DC, while significantly accelerating the reconstruction over conventional iterative reconstruction.
登录
查看更多内容
影响因子:
3.3
作者:
Huang, Chuan;Graff, Christian G.;Clarkson, Eric W.;Bilgin, Ali;Altbach, Maria I.
通讯作者:
Altbach, Maria I.
影响因子:
3.3
作者:
Sandino CM;Lai P;Vasanawala SS;Cheng JY
通讯作者:
Cheng JY
影响因子:
3.8
作者:
Kofler, Andreas;Haltmeier, Markus;Kolbitsch, Christoph
通讯作者:
Kolbitsch, Christoph
影响因子:
3.3
作者:
Zhang, Yufei;She, Huajun;Du, Yiping P.
通讯作者:
Du, Yiping P.
影响因子:
10.6
作者:
Schlemper, Jo;Caballero, Jose;Rueckert, Daniel
通讯作者:
Rueckert, Daniel