Center-to-Edge Denoising Diffusion Probabilistic Models with Cross-domain Attention for Undersampled MRI Reconstruction

Integrating dual-domain (i.e. frequency domain and spatial domain) information for magnetic resonance imaging (MRI) reconstruction from undersampled measurements greatly improves imaging efficiency. However, it is still a challenging task using the denoising diffusion probabilistic models (DDPM)-based method, due to the lack of an effective fusion module to integrate dual-domain information, and there is no work exploring the effect that comes from denoising diffusion strategy on dual-domain. In this study, we propose a novel center-to-edge DDPM (C2E-DDPM) for fully-sampled MRI reconstruction from undersampled measurements (i.e. undersampled k-space and undersampled MR image) by improving the learning ability in the frequency domain and cross-domain information attention. Different from previous work, C2E-DDPM provides a C2E denoising diffusion strategy for facilitating frequency domain learning and designs an attention-guided cross-domain junction for integrating dual-domain information. Experiments indicated that our proposed C2E-DDPM achieves state-of-the-art performances in the dataset fastMRI (i.e. The scores of PSNR/SSIM of 33.26/88.43 for 4 \(\times \) acceleration and 31.67/81.94 for 8 \(\times \) acceleration).