Wang Yunqi, Zeng Tianjiao, Liu Furui, Dou Qi, Cao Peng, Chang Hing-Chiu, Deng Qiao, Hui Edward S
Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Hong Kong Special Administrative Region of China; CU Lab for AI in Radiology (CLAIR), The Chinese University of Hong Kong, Hong Kong Special Administrative Region of China.
School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.
Med Image Anal. 2025 Apr;101:103459. doi: 10.1016/j.media.2025.103459. Epub 2025 Jan 16.
Deep learning methods have shown promise in accelerated MRI reconstruction but face significant challenges under domain shifts between training and testing datasets, such as changes in image contrasts, anatomical regions, and acquisition strategies. To address these challenges, we present the first domain generalization framework specifically designed for accelerated MRI reconstruction to robustness across unseen domains. The framework employs progressive strategies to enforce domain invariance, starting with image-level fidelity consistency to ensure robust reconstruction quality across domains, and feature alignment to capture domain-invariant representations. Advancing beyond these foundations, we propose a novel approach enforcing mechanism-level invariance, termed GenCA-MRI, which aligns intrinsic causal relationships within MRI data. We further develop a computational strategy that significantly reduces the complexity of causal alignment, ensuring its feasibility for real-world applications. Extensive experiments validate the framework's effectiveness, demonstrating both numerical and visual improvements over the baseline algorithm. GenCA-MRI presents the overall best performance, achieving a PSNR improvement up to 2.15 dB on fastMRI and 1.24 dB on IXI dataset at 8× acceleration, with superior performance in preserving anatomical details and mitigating domain-shift problem.
