Stacked U-Nets with Self-Assisted Priors Towards Robust Correction of Rigid Motion Artifact in Brain MRI

TL;DR

This paper introduces a deep learning approach using stacked U-Nets with self-assisted priors to effectively correct rigid motion artifacts in brain MRI, leveraging image priors from corrupted images without extra contrast data.

Contribution

It proposes a novel network architecture that incorporates self-assisted priors from the same corrupted images, improving artifact correction without additional scans.

Findings

Effective correction of motion artifacts demonstrated.

Self-assisted priors outperform other priors in experiments.

No extra contrast data needed for training.

Abstract

In this paper, we develop an efficient retrospective deep learning method called stacked U-Nets with self-assisted priors to address the problem of rigid motion artifacts in MRI. The proposed work exploits the usage of additional knowledge priors from the corrupted images themselves without the need for additional contrast data. The proposed network learns missed structural details through sharing auxiliary information from the contiguous slices of the same distorted subject. We further design a refinement stacked U-Nets that facilitates preserving of the image spatial details and hence improves the pixel-to-pixel dependency. To perform network training, simulation of MRI motion artifacts is inevitable. We present an intensive analysis using various types of image priors: the proposed self-assisted priors and priors from other image contrast of the same subject. The experimental analysis proves the effectiveness and feasibility of our self-assisted priors since it does not require any further data scans.