Dual-domain Cascade of U-nets for Multi-channel Magnetic Resonance Image Reconstruction

TL;DR

This paper evaluates dual-domain U-net cascades for multi-channel MRI reconstruction, showing that image-domain networks excel for individual channels, while dual-domain approaches are better for simultaneous multi-channel reconstruction, outperforming previous models.

Contribution

It introduces and compares various dual-domain U-net cascade configurations for multi-channel MRI reconstruction, demonstrating their advantages over existing state-of-the-art models.

Findings

Image-domain networks perform better for single-channel reconstruction.

Dual-domain networks excel in multi-channel simultaneous reconstruction.

Proposed models outperform previous Deep Cascade models in most experiments.

Abstract

The U-net is a deep-learning network model that has been used to solve a number of inverse problems. In this work, the concatenation of two-element U-nets, termed the W-net, operating in k-space (K) and image (I) domains, were evaluated for multi-channel magnetic resonance (MR) image reconstruction. The two element network combinations were evaluated for the four possible image-k-space domain configurations: a) W-net II, b) W-net KK, c) W-net IK, and d) W-net KI were evaluated. Selected promising four element networks (WW-nets) were also examined. Two configurations of each network were compared: 1) Each coil channel processed independently, and 2) all channels processed simultaneously. One hundred and eleven volumetric, T1-weighted, 12-channel coil k-space datasets were used in the experiments. Normalized root mean squared error, peak signal to noise ratio, visual information fidelity and visual inspection were used to assess the reconstructed images against the fully sampled reference images. Our results indicated that networks that operate solely in the image domain are better suited when processing individual channels of multi-channel data independently. Dual domain methods are more advantageous when simultaneously reconstructing all channels of multi-channel data. Also, the appropriate cascade of U-nets compared favorably (p < 0.01) to the previously published, state-of-the-art Deep Cascade model in in three out of four experiments.