Diffusion Model Regularized Implicit Neural Representation for CT Metal Artifact Reduction

TL;DR

This paper introduces a novel CT metal artifact reduction method combining diffusion models with implicit neural representations, effectively incorporating physical constraints and prior knowledge to improve clinical image quality.

Contribution

It proposes a diffusion model regularized implicit neural representation framework that enhances metal artifact reduction by integrating physical constraints and prior knowledge.

Findings

Effective artifact reduction on simulated and clinical data

Demonstrates strong generalization ability

Outperforms existing methods in quality and stability

Abstract

Computed tomography (CT) images are often severely corrupted by artifacts in the presence of metals. Existing supervised metal artifact reduction (MAR) approaches suffer from performance instability on known data due to their reliance on limited paired metal-clean data, which limits their clinical applicability. Moreover, existing unsupervised methods face two main challenges: 1) the CT physical geometry is not effectively incorporated into the MAR process to ensure data fidelity; 2) traditional heuristics regularization terms cannot fully capture the abundant prior knowledge available. To overcome these shortcomings, we propose diffusion model regularized implicit neural representation framework for MAR. The implicit neural representation integrates physical constraints and imposes data fidelity, while the pre-trained diffusion model provides prior knowledge to regularize the solution. Experimental results on both simulated and clinical data demonstrate the effectiveness and generalization ability of our method, highlighting its potential to be applied to clinical settings.