A Hybrid Frequency-domain/Image-domain Deep Network for Magnetic Resonance Image Reconstruction

Decreasing magnetic resonance (MR) image acquisition times can potentially make MR examinations more accessible. Compressed sensing (CS)-based image reconstruction methods decrease MR acquisition time by reconstructing high-quality images from data that were originally sampled at rates inferior to the Nyquist-Shannon sampling theorem. Deep-learning methods have been used to solve the CS MR reconstruction problem. These proposed methods are able to quickly reconstruct images in a single pass using an appropriately trained network. A variety of different network architectures (e.g., U-nets and Residual U-nets) have been proposed to tackle the CS reconstruction problem. A drawback of these architectures is that they typically only work on image domain data. For undersampled data, the images computed by applying the inverse Fast Fourier Transform (iFFT) are aliased. In this work we propose a hybrid architecture, termed W-net, that works both in the k-space (or frequency-domain) and the image (or spatial) domains. Our network is composed of a complex-valued residual U-net in the k-space domain, an iFFT operation, and a real-valued U-net in the image domain. Our experiments demonstrated, using MR raw k-space data, that the proposed hybrid approach can potentially improve CS reconstruction compared to deep-learning networks that operate only in the image domain. In this study we compare our method with four previously published deep neural networks and examine their ability to reconstruct images that are subsequently used to generate regional volume estimates. Our technique was ranked second in the quantitative analysis, but qualitative analysis indicated that our reconstruction performed the best in hard to reconstruct regions, such as the cerebellum. All images reconstructed with our method were successfully post-processed, and showed good volumetry agreement compared with the fully sampled reconstruction measures.