A Novel Approach for Correcting Multiple Discrete Rigid In-Plane Motions Artefacts in MRI Scans

TL;DR

This paper introduces a deep learning method that effectively corrects multiple in-plane motion artefacts in MRI scans, even with under-sampled data, improving scan quality and reducing the need for re-scans.

Contribution

A novel neural network architecture that discriminates patient poses using motion timing and corrects multiple in-plane motions in MRI, including under-sampled data scenarios.

Findings

Effective correction of multiple motion artefacts demonstrated on simulated data.

Improved MRI scan quality with reduced re-scan rates.

Applicable to under-sampled k-space data, saving scan time.

Abstract

Motion artefacts created by patient motion during an MRI scan occur frequently in practice, often rendering the scans clinically unusable and requiring a re-scan. While many methods have been employed to ameliorate the effects of patient motion, these often fall short in practice. In this paper we propose a novel method for removing motion artefacts using a deep neural network with two input branches that discriminates between patient poses using the motion's timing. The first branch receives a subset of the $k$-space data collected during a single patient pose, and the second branch receives the remaining part of the collected $k$-space data. The proposed method can be applied to artefacts generated by multiple movements of the patient. Furthermore, it can be used to correct motion for the case where $k$-space has been under-sampled, to shorten the scan time, as is common when using methods such as parallel imaging or compressed sensing. Experimental results on both simulated and real MRI data show the efficacy of our approach.