3D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Schaub, Susanne, Bieder, Florentin, Oliveira, Matheus L., Wang, Yulan, Dagassan-Berndt, Dorothea, Bornstein, Michael M., Cattin, Philippe C.
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917318479577088
author Schaub, Susanne
Bieder, Florentin
Oliveira, Matheus L.
Wang, Yulan
Dagassan-Berndt, Dorothea
Bornstein, Michael M.
Cattin, Philippe C.
author_facet Schaub, Susanne
Bieder, Florentin
Oliveira, Matheus L.
Wang, Yulan
Dagassan-Berndt, Dorothea
Bornstein, Michael M.
Cattin, Philippe C.
contents Cone-beam computed tomography (CBCT) is a widely used 3D imaging technique in dentistry, offering high-resolution images while minimising radiation exposure for patients. However, CBCT is highly susceptible to artefacts arising from high-density objects such as dental implants, which can compromise image quality and diagnostic accuracy. To reduce artefacts, implant inpainting in the sequence of projections plays a crucial role in many artefact reduction approaches. Recently, diffusion models have achieved state-of-the-art results in image generation and have widely been applied to image inpainting tasks. However, to our knowledge, existing diffusion-based methods for implant inpainting operate on independent 2D projections. This approach neglects the correlations among individual projections, resulting in inconsistencies in the reconstructed images. To address this, we propose a 3D dental implant inpainting approach based on perpendicular score-based diffusion models, each trained in two different planes and operating in the projection domain. The 3D distribution of the projection series is modelled by combining the two 2D score-based diffusion models in the sampling scheme. Our results demonstrate the method's effectiveness in producing high-quality, artefact-reduced 3D CBCT images, making it a promising solution for improving clinical imaging.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06300
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle 3D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Models
Schaub, Susanne
Bieder, Florentin
Oliveira, Matheus L.
Wang, Yulan
Dagassan-Berndt, Dorothea
Bornstein, Michael M.
Cattin, Philippe C.
Computer Vision and Pattern Recognition
Machine Learning
Cone-beam computed tomography (CBCT) is a widely used 3D imaging technique in dentistry, offering high-resolution images while minimising radiation exposure for patients. However, CBCT is highly susceptible to artefacts arising from high-density objects such as dental implants, which can compromise image quality and diagnostic accuracy. To reduce artefacts, implant inpainting in the sequence of projections plays a crucial role in many artefact reduction approaches. Recently, diffusion models have achieved state-of-the-art results in image generation and have widely been applied to image inpainting tasks. However, to our knowledge, existing diffusion-based methods for implant inpainting operate on independent 2D projections. This approach neglects the correlations among individual projections, resulting in inconsistencies in the reconstructed images. To address this, we propose a 3D dental implant inpainting approach based on perpendicular score-based diffusion models, each trained in two different planes and operating in the projection domain. The 3D distribution of the projection series is modelled by combining the two 2D score-based diffusion models in the sampling scheme. Our results demonstrate the method's effectiveness in producing high-quality, artefact-reduced 3D CBCT images, making it a promising solution for improving clinical imaging.
title 3D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Models
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2603.06300