TriDoNet: A Triple Domain Model-driven Network for CT Metal Artifact Reduction

TL;DR

TriDoNet is a novel deep learning framework that leverages triple domain knowledge and contrastive regularization to significantly improve metal artifact reduction in CT images.

Contribution

It introduces a triple domain model-driven approach and a contrastive regularization technique for enhanced CT metal artifact reduction.

Findings

Superior artifact reduction performance demonstrated in experiments

Effective encoding of metal artifacts using sparse representation

Enhanced image quality with contrastive regularization

Abstract

Recent deep learning-based methods have achieved promising performance for computed tomography metal artifact reduction (CTMAR). However, most of them suffer from two limitations: (i) the domain knowledge is not fully embedded into the network training; (ii) metal artifacts lack effective representation models. The aforementioned limitations leave room for further performance improvement. Against these issues, we propose a novel triple domain model-driven CTMAR network, termed as TriDoNet, whose network training exploits triple domain knowledge, i.e., the knowledge of the sinogram, CT image, and metal artifact domains. Specifically, to explore the non-local repetitive streaking patterns of metal artifacts, we encode them as an explicit tight frame sparse representation model with adaptive thresholds. Furthermore, we design a contrastive regularization (CR) built upon contrastive learning to exploit clean CT images and metal-affected images as positive and negative samples, respectively. Experimental results show that our TriDoNet can generate superior artifact-reduced CT images.