High-Throughput Deep Unfolding Network for Compressive Sensing MRI

Deep unfolding network (DUN) has become the mainstream for compressive sensing MRI (CS-MRI) due to its good interpretability and high performance. Different optimization algorithms are usually unfolded into deep networks with different architectures, in which one iteration corresponds to one stage of DUN. However, there are few works discussing the following two questions: Which optimization algorithm is better after being unfolded into a DUN? What are the bottlenecks in existing DUNs? This paper attempts to answer these questions and give a feasible solution. For the first question, our mathematical and empirical analysis verifies the similarity of DUNs unfolded by alternating minimization (AM), alternating iterative shrinkage-thresholding algorithm (ISTA) and alternating direction method of multipliers (ADMM). For the second question, we point out that one major bottleneck of existing DUNs is that the input and output of each stage are just images of one channel, which greatly limits the transmission of network information. To break the information bottleneck, this paper proposes a novel, simple yet powerful high-throughput deep unfolding network (HiTDUN), which is not constrained by any optimization algorithm and can transmit multi-channel information between adjacent network stages. The developed multi-channel fusion strategy can also be easily incorporated into existing DUNs to further boost their performance. Extensive CS-MRI experiments on three benchmark datasets demonstrate that the proposed HiTDUN outperforms existing state-of-the-art DUNs by large margins while maintaining fast computational speed.(1) (1) For reproducible research, the source codes and training models of our HiTDUN. [Online]. Available: https://github.com/jianzhangcs/HiTDUN.

Automated summary

This paper discusses the application of deep unfolding network (DUN) in compressive sensing MRI (CS-MRI) and addresses two questions: which optimization algorithm is better when unfolded into a DUN, and what are the bottlenecks in existing DUNs. The research finds the similarity between DUNs unfolded by different optimization algorithms and identifies one major bottleneck in existing DUNs. To overcome the information bottleneck, a novel high-throughput deep unfolding network (HiTDUN) is proposed, which can transmit multi-channel information and significantly improve performance.