Frequency-spatial synergistic network for accelerated multi-contrast MRI reconstruction

Abstract

To accelerate the Magnetic Resonance Imaging (MRI) process, multi-contrast MRI reconstruction has emerged as a mainstream approach. This technique leverages readily available auxiliary modality information to guide the high-quality reconstruction of the target modality. The core challenge of this task lies in effectively capturing the global dependencies across different contrasts and efficiently integrating complementary information from multiple contrasts. To address these challenges, we propose the Multi-Contrast Dual-Domain (MCDD) network. It leverages frequency-domain information to capture global dependencies. Specifically, the network employs the Single-Contrast Learning (SCL) module as a prior to guide the Multi-Contrast Learning (MCL) module. Both modules extract complementary global and local features through Frequency (Fre) and Spatial (Spa) extraction blocks, which are fused via an Adaptive Fusion Mechanism (AFM). Experiments on BraTS, MRBrainS, and fastMRI demonstrate that MCDD outperforms state-of-the-art methods, achieving PSNR improvements of 2.42 dB ($4\times$), 2.11 dB ($8\times$), 1.63 dB ($16\times$), and 0.82 dB ($32\times$). Qualitative results further confirm enhanced structural fidelity and reduced artifacts, validating MCDD as an effective solution for accelerated MRI reconstruction.