Unsupervised CT Metal Artifact Reduction by Plugging Diffusion Priors in Dual Domains

TL;DR

This paper introduces an unsupervised deep learning method for metal artifact reduction in CT images, leveraging diffusion models in both sinogram and image domains to improve clinical image quality without relying on paired training data.

Contribution

It proposes a novel dual-domain unsupervised MAR approach using diffusion priors, outperforming existing methods in synthetic and clinical datasets.

Findings

Outperforms existing unsupervised MAR methods in synthetic data.

Achieves superior visual quality on clinical datasets.

Demonstrates effectiveness of dual-domain diffusion priors.

Abstract

During the process of computed tomography (CT), metallic implants often cause disruptive artifacts in the reconstructed images, impeding accurate diagnosis. Several supervised deep learning-based approaches have been proposed for reducing metal artifacts (MAR). However, these methods heavily rely on training with simulated data, as obtaining paired metal artifact CT and clean CT data in clinical settings is challenging. This limitation can lead to decreased performance when applying these methods in clinical practice. Existing unsupervised MAR methods, whether based on learning or not, typically operate within a single domain, either in the image domain or the sinogram domain. In this paper, we propose an unsupervised MAR method based on the diffusion model, a generative model with a high capacity to represent data distributions. Specifically, we first train a diffusion model using CT images without metal artifacts. Subsequently, we iteratively utilize the priors embedded within the pre-trained diffusion model in both the sinogram and image domains to restore the degraded portions caused by metal artifacts. This dual-domain processing empowers our approach to outperform existing unsupervised MAR methods, including another MAR method based on the diffusion model, which we have qualitatively and quantitatively validated using synthetic datasets. Moreover, our method demonstrates superior visual results compared to both supervised and unsupervised methods on clinical datasets.