Unsupervised Adversarial Correction of Rigid MR Motion Artifacts

TL;DR

This paper presents an unsupervised adversarial framework for correcting severe rigid motion artifacts in brain MRI scans, eliminating the need for paired training data and improving image quality.

Contribution

It introduces a novel generator architecture and loss function for unsupervised correction of MR motion artifacts, advancing beyond previous supervised methods.

Findings

Enhanced correction performance compared to existing methods

Effective in severe rigid motion artifact scenarios

Qualitative and quantitative validation of results

Abstract

Motion is one of the main sources for artifacts in magnetic resonance (MR) images. It can have significant consequences on the diagnostic quality of the resultant scans. Previously, supervised adversarial approaches have been suggested for the correction of MR motion artifacts. However, these approaches suffer from the limitation of required paired co-registered datasets for training which are often hard or impossible to acquire. Building upon our previous work, we introduce a new adversarial framework with a new generator architecture and loss function for the unsupervised correction of severe rigid motion artifacts in the brain region. Quantitative and qualitative comparisons with other supervised and unsupervised translation approaches showcase the enhanced performance of the introduced framework.