Annealed Score-Based Diffusion Model for MR Motion Artifact Reduction

TL;DR

This paper introduces an annealed score-based diffusion model that effectively reduces motion artifacts in MRI images without requiring paired corrupted data, outperforming existing deep learning methods.

Contribution

The proposed method trains solely on motion-free images and employs diffusion processes to remove artifacts, addressing limitations of supervised models.

Findings

Successfully reduces simulated and real motion artifacts

Outperforms state-of-the-art deep learning methods

Operates without paired training data

Abstract

Motion artifact reduction is one of the important research topics in MR imaging, as the motion artifact degrades image quality and makes diagnosis difficult. Recently, many deep learning approaches have been studied for motion artifact reduction. Unfortunately, most existing models are trained in a supervised manner, requiring paired motion-corrupted and motion-free images, or are based on a strict motion-corruption model, which limits their use for real-world situations. To address this issue, here we present an annealed score-based diffusion model for MRI motion artifact reduction. Specifically, we train a score-based model using only motion-free images, and then motion artifacts are removed by applying forward and reverse diffusion processes repeatedly to gradually impose a low-frequency data consistency. Experimental results verify that the proposed method successfully reduces both simulated and in vivo motion artifacts, outperforming the state-of-the-art deep learning methods.