Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Low-rank plus Sparse Network for Dynamic MR Imaging

About

In dynamic magnetic resonance (MR) imaging, low-rank plus sparse (L+S) decomposition, or robust principal component analysis (PCA), has achieved stunning performance. However, the selection of the parameters of L+S is empirical, and the acceleration rate is limited, which are common failings of iterative compressed sensing MR imaging (CS-MRI) reconstruction methods. Many deep learning approaches have been proposed to address these issues, but few of them use a low-rank prior. In this paper, a model-based low-rank plus sparse network, dubbed L+S-Net, is proposed for dynamic MR reconstruction. In particular, we use an alternating linearized minimization method to solve the optimization problem with low-rank and sparse regularization. Learned soft singular value thresholding is introduced to ensure the clear separation of the L component and S component. Then, the iterative steps are unrolled into a network in which the regularization parameters are learnable. We prove that the proposed L+S-Net achieves global convergence under two standard assumptions. Experiments on retrospective and prospective cardiac cine datasets show that the proposed model outperforms state-of-the-art CS and existing deep learning methods and has great potential for extremely high acceleration factors (up to 24x).

Wenqi Huang, Ziwen Ke, Zhuo-Xu Cui, Jing Cheng, Zhilang Qiu, Sen Jia, Leslie Ying, Yanjie Zhu, Dong Liang• 2020

Related benchmarks

TaskDatasetResultRank
MRI ReconstructionOCMR AF=4x (test)
PSNR (dB)34.55
14
MRI ReconstructionOCMR AF=6x (test)
PSNR (dB)31.97
14
MRI ReconstructionOCMR AF=8x (test)
PSNR (dB)28.32
14
Showing 3 of 3 rows

Other info

Follow for update