Retrospective correction of Rigid and Non-Rigid MR motion artifacts using GANs

TL;DR

This paper introduces MedGAN, an adversarial framework that effectively corrects both rigid and non-rigid MR motion artifacts retrospectively, without requiring reference images, improving image quality and diagnostic reliability.

Contribution

The paper presents a novel GAN-based approach, MedGAN, for joint retrospective correction of diverse motion artifacts in MR images, eliminating the need for reference images and reducing computational costs.

Findings

MedGAN outperforms existing adversarial methods in artifact correction.

The approach effectively handles both rigid and non-rigid motion artifacts.

Quantitative and qualitative results demonstrate improved image quality.

Abstract

Motion artifacts are a primary source of magnetic resonance (MR) image quality deterioration with strong repercussions on diagnostic performance. Currently, MR motion correction is carried out either prospectively, with the help of motion tracking systems, or retrospectively by mainly utilizing computationally expensive iterative algorithms. In this paper, we utilize a new adversarial framework, titled MedGAN, for the joint retrospective correction of rigid and non-rigid motion artifacts in different body regions and without the need for a reference image. MedGAN utilizes a unique combination of non-adversarial losses and a new generator architecture to capture the textures and fine-detailed structures of the desired artifact-free MR images. Quantitative and qualitative comparisons with other adversarial techniques have illustrated the proposed model performance.