Dense Transformer based Enhanced Coding Network for Unsupervised Metal Artifact Reduction

TL;DR

This paper introduces DTEC-Net, a novel unsupervised deep learning model using dense transformers and hierarchical encoding to effectively reduce metal artifacts in CT images without ground truth data.

Contribution

It proposes a new Dense Transformer based Enhanced Coding Network with hierarchical disentangling and second-order methods for improved unsupervised metal artifact reduction.

Findings

Outperforms previous state-of-the-art methods on benchmark datasets.

Effectively reduces metal artifacts while restoring texture details.

Demonstrates robustness and effectiveness through extensive experiments.

Abstract

CT images corrupted by metal artifacts have serious negative effects on clinical diagnosis. Considering the difficulty of collecting paired data with ground truth in clinical settings, unsupervised methods for metal artifact reduction are of high interest. However, it is difficult for previous unsupervised methods to retain structural information from CT images while handling the non-local characteristics of metal artifacts. To address these challenges, we proposed a novel Dense Transformer based Enhanced Coding Network (DTEC-Net) for unsupervised metal artifact reduction. Specifically, we introduce a Hierarchical Disentangling Encoder, supported by the high-order dense process, and transformer to obtain densely encoded sequences with long-range correspondence. Then, we present a second-order disentanglement method to improve the dense sequence's decoding process. Extensive experiments and model discussions illustrate DTEC-Net's effectiveness, which outperforms the previous state-of-the-art methods on a benchmark dataset, and greatly reduces metal artifacts while restoring richer texture details.