Dual-Domain Cross-Iteration Squeeze-Excitation Network for Sparse Reconstruction of Brain MRI

TL;DR

This paper introduces a novel dual-domain cross-iteration squeeze-excitation network that effectively reconstructs high-quality brain MRI images from sparsely sampled data, significantly reducing scan time while maintaining diagnostic accuracy.

Contribution

The study proposes a new dual Squeeze-Excitation Network with cross-iteration residual connections for MRI reconstruction, outperforming existing methods in accuracy.

Findings

Average reconstruction error of 2.28% on 120 test cases

Outperforms existing image-domain and k-space methods significantly

Validated on 720 clinical brain MRI cases from open-source dataset

Abstract

Magnetic resonance imaging (MRI) is one of the most commonly applied tests in neurology and neurosurgery. However, the utility of MRI is largely limited by its long acquisition time, which might induce many problems including patient discomfort and motion artifacts. Acquiring fewer k-space sampling is a potential solution to reducing the total scanning time. However, it can lead to severe aliasing reconstruction artifacts and thus affect the clinical diagnosis. Nowadays, deep learning has provided new insights into the sparse reconstruction of MRI. In this paper, we present a new approach to this problem that iteratively fuses the information of k-space and MRI images using novel dual Squeeze-Excitation Networks and Cross-Iteration Residual Connections. This study included 720 clinical multi-coil brain MRI cases adopted from the open-source deidentified fastMRI Dataset. 8-folder downsampling rate was applied to generate the sparse k-space. Results showed that the average reconstruction error over 120 testing cases by our proposed method was 2.28%, which outperformed the existing image-domain prediction (6.03%, p<0.001), k-space synthesis (6.12%, p<0.001), and dual-domain feature fusion (4.05%, p<0.001).