Deep Generative Models: 5th MICCAI Workshop, DGM4MICCAI 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings

2026-03-06

DGM4MICCAI@MICCAI

AI Summary

This study addresses the severe artifacts in cone-beam computed tomography (CBCT) images caused by high-density dental implants, which compromise diagnostic accuracy. Existing projection-domain correction methods often neglect inter-view correlations, leading to inconsistent reconstructions. To overcome this limitation, the authors propose a novel fractional diffusion model that jointly models two orthogonal cross-sectional planes in the projection domain and fuses them during sampling to capture 3D spatial dependencies. This work represents the first effort to cooperatively apply two-dimensional fractional diffusion models for CBCT projection completion, effectively modeling cross-view dependencies and significantly improving both reconstruction consistency and image quality. Experimental results demonstrate that the generated CBCT images exhibit fewer artifacts, superior visual fidelity, and enhanced clinical applicability compared to existing approaches that process projections independently in 2D.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Web Mining and Content Analysis: Content-based information diffusion
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

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.

Problem

• CBCT artefacts
• dental implants
• 3D inpainting
• projection consistency
• diffusion models

Innovation

• score-based diffusion models
• 3D CBCT artefact removal
• perpendicular diffusion
• dental implant inpainting
• projection domain modeling