Unsupervised MR Motion Artifact Deep Learning using Outlier-Rejecting Bootstrap Aggregation

TL;DR

This paper introduces an unsupervised deep learning method for MR motion artifact correction that uses outlier-rejecting bootstrap aggregation, eliminating the need for paired training data and effectively handling transient severe motion artifacts.

Contribution

The novel unsupervised scheme leverages outlier rejection and bootstrap aggregation, enabling MR motion artifact correction without paired datasets, and employs cycleGAN to prevent smoothing bias.

Findings

Outperforms existing deep learning methods in artifact correction

Effective on both simulated and real motion artifacts

Does not require paired artifact-free and corrupted images

Abstract

Recently, deep learning approaches for MR motion artifact correction have been extensively studied. Although these approaches have shown high performance and reduced computational complexity compared to classical methods, most of them require supervised training using paired artifact-free and artifact-corrupted images, which may prohibit its use in many important clinical applications. For example, transient severe motion (TSM) due to acute transient dyspnea in Gd-EOB-DTPA-enhanced MR is difficult to control and model for paired data generation. To address this issue, here we propose a novel unsupervised deep learning scheme through outlier-rejecting bootstrap subsampling and aggregation. This is inspired by the observation that motions usually cause sparse k-space outliers in the phase encoding direction, so k-space subsampling along the phase encoding direction can remove some outliers and the aggregation step can further improve the results from the reconstruction network. Our method does not require any paired data because the training step only requires artifact-free images. Furthermore, to address the smoothing from potential bias to the artifact-free images, the network is trained in an unsupervised manner using optimal transport driven cycleGAN. We verify that our method can be applied for artifact correction from simulated motion as well as real motion from TSM successfully, outperforming existing state-of-the-art deep learning methods.