Deep unfolding networks (DUNs) are the foremost methods in the realm of compressed sensing MRI, as they can employ learnable networks to facilitate interpretable forward-inference operators. However, several daunting issues still exist, including the heavy dependency on the first-order optimization algorithms, the insufficient information fusion mechanisms, and the limitation of capturing long-range relationships. To address the issues, we propose a Generically Accelerated Half-Quadratic Splitting (GA-HQS) algorithm that incorporates second-order gradient information and pyramid attention modules for the delicate fusion of inputs at the pixel level. Moreover, a multi-scale split transformer is also designed to enhance the global feature representation. Comprehensive experiments demonstrate that our method surpasses previous ones on single-coil MRI acceleration tasks.
@article{arxiv.2304.02883,
title = {GA-HQS: MRI reconstruction via a generically accelerated unfolding approach},
author = {Jiawei Jiang and Yuchao Feng and Honghui Xu and Wanjun Chen and Jianwei Zheng},
journal= {arXiv preprint arXiv:2304.02883},
year = {2023}
}