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

TL;DR

This paper introduces a novel 3D diffusion model approach for dental implant inpainting in CBCT images, effectively reducing artefacts and improving image quality by modeling correlations across projections.

Contribution

It presents a perpendicular score-based diffusion model that operates in the projection domain, capturing 3D correlations for improved artefact removal in CBCT imaging.

Findings

Effective artefact reduction in CBCT images

High-quality 3D image reconstruction

Outperforms existing 2D projection-based methods

Abstract

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.