Tooth-Diffusion: Guided 3D CBCT Synthesis with Fine-Grained Tooth Conditioning

2025-08-19

AI Summary

To address the challenge of fine-grained anatomical control in dental CBCT image synthesis, this paper proposes a tooth-level conditional-guided 3D diffusion model. Methodologically, we introduce binary attributes encoding tooth presence and spatial arrangement as novel fine-grained conditioning signals—first of their kind in dental image synthesis—and integrate wavelet-domain denoising, FiLM-based conditional modulation, and mask-weighted loss to enable precise anatomical modeling and localized controllable editing. Quantitative evaluation demonstrates superior performance over state-of-the-art methods: significantly reduced FID scores and SSIM > 0.91. The model achieves high fidelity, strong generalization across diverse anatomical configurations, and robust inpainting capability for missing or corrupted regions. These attributes collectively support clinical diagnosis, personalized treatment planning, and effective small-sample data augmentation in dental imaging.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Despite the growing importance of dental CBCT scans for diagnosis and treatment planning, generating anatomically realistic scans with fine-grained control remains a challenge in medical image synthesis. In this work, we propose a novel conditional diffusion framework for 3D dental volume generation, guided by tooth-level binary attributes that allow precise control over tooth presence and configuration. Our approach integrates wavelet-based denoising diffusion, FiLM conditioning, and masked loss functions to focus learning on relevant anatomical structures. We evaluate the model across diverse tasks, such as tooth addition, removal, and full dentition synthesis, using both paired and distributional similarity metrics. Results show strong fidelity and generalization with low FID scores, robust inpainting performance, and SSIM values above 0.91 even on unseen scans. By enabling realistic, localized modification of dentition without rescanning, this work opens opportunities for surgical planning, patient communication, and targeted data augmentation in dental AI workflows. The codes are available at: https://github.com/djafar1/tooth-diffusion.

Problem

• Generating anatomically realistic dental CBCT scans
• Achieving fine-grained control over tooth presence
• Enabling realistic localized dentition modification without rescanning

Innovation

• Conditional diffusion framework for 3D dental synthesis
• Tooth-level binary attributes enable precise control
• Wavelet-based denoising with FiLM conditioning integration