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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Zhi, Wang, Yaqi, Ma, Bingtao, Zhang, Yifan, Zhou, Huiyu, Wang, Shuai
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912799466192896
author Li, Zhi
Wang, Yaqi
Ma, Bingtao
Zhang, Yifan
Zhou, Huiyu
Wang, Shuai
author_facet Li, Zhi
Wang, Yaqi
Ma, Bingtao
Zhang, Yifan
Zhou, Huiyu
Wang, Shuai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physically-Grounded Manifold Projection Model for Generalizable Metal Artifact Reduction in Dental CBCT
Li, Zhi
Wang, Yaqi
Ma, Bingtao
Zhang, Yifan
Zhou, Huiyu
Wang, Shuai
Computer Vision and Pattern Recognition
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.
title Physically-Grounded Manifold Projection Model for Generalizable Metal Artifact Reduction in Dental CBCT
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.24260