An Unsupervised Framework for Joint MRI Super Resolution and Gibbs Artifact Removal

TL;DR

This paper introduces an unsupervised learning framework that simultaneously enhances MRI image resolution and removes Gibbs artifacts, overcoming limitations of previous methods that tackled these issues separately and requiring high-resolution ground truth.

Contribution

The proposed framework is the first to jointly perform MRI super resolution and Gibbs artifact removal in an unsupervised manner, improving generalizability across diverse datasets.

Findings

Achieves superior super resolution performance compared to state-of-the-art methods.

Effectively reduces Gibbs ringing artifacts in MRI images.

Demonstrates strong generalization across different MRI datasets.

Abstract

The k-space data generated from magnetic resonance imaging (MRI) is only a finite sampling of underlying signals. Therefore, MRI images often suffer from low spatial resolution and Gibbs ringing artifacts. Previous studies tackled these two problems separately, where super resolution methods tend to enhance Gibbs artifacts, whereas Gibbs ringing removal methods tend to blur the images. It is also a challenge that high resolution ground truth is hard to obtain in clinical MRI. In this paper, we propose an unsupervised learning framework for both MRI super resolution and Gibbs artifacts removal without using high resolution ground truth. Furthermore, we propose regularization methods to improve the model's generalizability across out-of-distribution MRI images. We evaluated our proposed methods with other state-of-the-art methods on eight MRI datasets with various contrasts and anatomical structures. Our method not only achieves the best SR performance but also significantly reduces the Gibbs artifacts. Our method also demonstrates good generalizability across different datasets, which is beneficial to clinical applications where training data are usually scarce and biased.