DDC-Net: Dual-Domain Cascaded Network With POCS Prior for Fast MRI Reconstruction

Magnetic resonance imaging (MRI) is a powerful diagnostic tool that provides high-resolution images, but it requires a time-consuming scanning procedure. To reduce the acquisition time, various methods have been proposed to reconstruct images from undersampled <tex-math notation="LaTeX">k </tex-math> -space. However, most dual-domain learning-based methods have two primary limitations: 1) using the same reconstruction network for different domains may hinder the learning of targeted information for each domain and 2) the reconstruction network uses only highly undersampled data as input, leaving the use of prior as complementary information highly underexplored. To alleviate the above issues, we propose a dual-domain cascaded network with projection onto convex set (POCS) prior for fast MRI, called DDC-Net. It consists of cascaded blocks with image-domain subnetwork (I-Net) and frequency-domain subnetwork (K-Net) reconstruction subnetworks. Specifically, the customized I-Net for the image domain uses a two-encoder-one-decoder architecture to enrich detailed structures. On the other hand, the customized K-Net for the frequency ( <tex-math notation="LaTeX">k </tex-math> -space) domain replaces the traditional encoder–decoder with a cross-domain encoder–decoder to alleviate the difficult modeling problem of <tex-math notation="LaTeX">k </tex-math> -space data. In addition, the POCS prior as complementary information is deeply embedded in the dual domain to simultaneously guide the <tex-math notation="LaTeX">k </tex-math> -space and image reconstructions. Extensive experiments on the fastMRI and CC359 datasets demonstrate that our proposed DDC-Net achieves state-of-the-art qualitative and quantitative reconstruction results, outperforming previous deep learning (DL)-based methods.