Motion Artifact Reduction in Quantitative Susceptibility Mapping using Deep Neural Network

TL;DR

This paper introduces a deep learning method to effectively reduce motion artifacts in Quantitative Susceptibility Mapping images, improving image quality in both simulated and real patient data.

Contribution

It presents a novel supervised learning approach using simulated motion profiles to train a neural network for artifact reduction in QSM images.

Findings

Successful suppression of ringing and ghosting artifacts.

Effective on both simulated and real patient data.

Applicable to healthy and Parkinson's disease subjects.

Abstract

An approach to reduce motion artifacts in Quantitative Susceptibility Mapping using deep learning is proposed. We use an affine motion model with randomly created motion profiles to simulate motion-corrupted QSM images. The simulated QSM image is paired with its motion-free reference to train a neural network using supervised learning. The trained network is tested on unseen simulated motion-corrupted QSM images, in healthy volunteers and in Parkinson's disease patients. The results show that motion artifacts, such as ringing and ghosting, were successfully suppressed.