Orientation-Shared Convolution Representation for CT Metal Artifact Learning

TL;DR

This paper introduces an orientation-shared convolution approach for CT metal artifact reduction, leveraging physical prior knowledge to improve artifact separation and enhance image quality in clinical and synthetic datasets.

Contribution

It proposes a novel orientation-shared convolution representation that models rotationally symmetrical artifacts using Fourier-series-expansion-based filters, improving generalization and artifact removal.

Findings

Outperforms existing MAR methods in detail preservation

Demonstrates robustness on both synthetic and clinical datasets

Enhances separation of artifacts from anatomical tissues

Abstract

During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts in the captured CT images and then impair the clinical treatment. Against this metal artifact reduction (MAR) task, the existing deep-learning-based methods have gained promising reconstruction performance. Nevertheless, there is still some room for further improvement of MAR performance and generalization ability, since some important prior knowledge underlying this specific task has not been fully exploited. Hereby, in this paper, we carefully analyze the characteristics of metal artifacts and propose an orientation-shared convolution representation strategy to adapt the physical prior structures of artifacts, i.e., rotationally symmetrical streaking patterns. The proposed method rationally adopts Fourier-series-expansion-based filter parametrization in artifact modeling, which can better separate artifacts from anatomical tissues and boost the model generalizability. Comprehensive experiments executed on synthesized and clinical datasets show the superiority of our method in detail preservation beyond the current representative MAR methods. Code will be available at \url{https://github.com/hongwang01/OSCNet}