Alternating unrolling network using jointly low-rank and sparse tensor prior for accelerating dynamic MRI

Motivation: The unrolling networks that combine low-rank (LR) and sparse priors have the potential to enhance the reconstruction performance. However, the underlying iterative algorithm for solving the model of joint LR and sparse constraint is complicated, resulting in redundant network structure. Goal(s): To propose a simple yet effective alternating unrolling framework that exploits jointly LR and sparse prior for robust reconstruction of highly accelerated dynamic MRI data. Approach: Instead of strictly unrolling the iterative algorithm, we propose a novel "DC-LowRank-DC-Sparse" alternating framework. Results: The proposed network (AlteRS-Net) outperforms the SOTA unrolling networks regarding both visualization and quantitative evaluation of PSNR and SSIM. Impact: A novel alternating framework for unrolling network of jointly low-rank and sparse prior is established for accelerating dynamic MRI. This alternating concept could serve as an inspiration for the design of unrolling networks that combine other priors in various applications.