Physically-Grounded Manifold Projection Model for Generalizable Metal Artifact Reduction in Dental CBCT

TL;DR

This paper introduces PGMP, a novel framework combining physics simulation, a deterministic diffusion approach, and semantic alignment to improve metal artifact reduction in dental CBCT, achieving high accuracy and clinical reliability.

Contribution

The paper presents a physically-grounded, deterministic manifold projection method that enhances generalization and efficiency in dental CBCT metal artifact reduction.

Findings

Outperforms state-of-the-art methods on unseen anatomy.

Achieves real-time, single-pass artifact correction.

Sets new benchmarks in clinical reliability and efficiency.

Abstract

Metal artifacts in Dental CBCT severely obscure anatomical structures, hindering diagnosis. Current deep learning for Metal Artifact Reduction (MAR) faces limitations: supervised methods suffer from spectral blurring due to "regression-to-the-mean", while unsupervised ones risk structural hallucinations. Denoising Diffusion Models (DDPMs) offer realism but rely on slow, stochastic iterative sampling, unsuitable for clinical use. To resolve this, we propose the Physically-Grounded Manifold Projection (PGMP) framework. First, our Anatomically-Adaptive Physics Simulation (AAPS) pipeline synthesizes high-fidelity training pairs via Monte Carlo spectral modeling and patient-specific digital twins, bridging the synthetic-to-real gap. Second, our DMP-Former adapts the Direct x-Prediction paradigm, reformulating restoration as a deterministic manifold projection to recover clean anatomy in a single forward pass, eliminating stochastic sampling. Finally, a Semantic-Structural Alignment (SSA) module anchors the solution using priors from medical foundation models (MedDINOv3), ensuring clinical plausibility. Experiments on synthetic and multi-center clinical datasets show PGMP outperforms state-of-the-art methods on unseen anatomy, setting new benchmarks in efficiency and diagnostic reliability. Code and data: https://github.com/ricoleehduu/PGMP.