GraphMAR: Geometry-Aware Graph Learning Framework for Spatially Adaptive CT Metal Artifact Reduction

2026-05-17

AI Summary

Metal implants in CT imaging induce severe streaking artifacts that significantly hinder diagnostic accuracy, yet existing image-domain methods struggle to remove these artifacts precisely due to the absence of geometric guidance. This work proposes GraphMAR, a novel framework that introduces graph-structured modeling to metal artifact reduction for the first time. By constructing a geometric density map to coarsely localize artifact regions and employing a GraphMoE module to generate polar-coordinate artifact maps in feature space, GraphMAR enables spatially adaptive artifact suppression. The method explicitly incorporates projection geometry cues directly in the image domain, offering both interpretability and region-adaptive restoration capabilities. Extensive experiments demonstrate that GraphMAR consistently outperforms state-of-the-art approaches on both simulated and real clinical datasets.

Abstract

Computed tomography (CT) metal artifact reduction (MAR) aims to reduce the severe streaking artifacts induced by metallic implants and other high-density objects. Effective MAR generally requires both accurate artifact localization and artifact removal. Sinogram-domain methods can exploit explicit geometric cues, such as metal traces, to identify metal-corrupted measurements, while requiring raw projection data, which is often unavailable in clinical and practical scenarios. Image-domain methods are more flexible and widely applicable, yet they usually lack comparable geometric guidance, limiting their ability to localize artifacts and leading to suboptimal results. To address this limitation, we propose GraphMAR, a geometry-aware learning framework for explicit artifact identification and spatially adaptive MAR in the image domain. The key idea is to introduce graph-based geometric modeling as an image-domain analogue of sinogram metal traces. Specifically, we first construct a geometric graph from the metal mask and derive a geometric density graph that coarsely localizes artifact-prone regions according to inter-implant geometry. We then design GraphMoE, a graph-routed mixture-of-experts module that builds a polar-coordinate artifact graph in feature space and adaptively routes different experts to different spatial regions for MAR. By aligning the learned routing maps with the geometric density graph, GraphMAR provides explicit and interpretable artifact localization while enabling region-adaptive artifact reduction. Experiments on both simulated and real-world datasets demonstrate that GraphMAR achieves superior MAR performance compared with existing methods. To the best of our knowledge, this is the first work to introduce graph-based modeling for CT MAR and to enable explicit artifact identification in the image domain, improving both restoration quality and interpretability.

Problem

• metal artifact reduction
• CT imaging
• image-domain MAR
• artifact localization
• geometric guidance

Innovation

• graph-based modeling
• geometry-aware learning
• metal artifact reduction
• mixture-of-experts
• spatially adaptive restoration