CrownGen: Patient-customized Crown Generation via Point Diffusion Model

2025-12-26

AI Summary

Digital crown design in clinical restoration remains heavily manual, resulting in low efficiency and poor standardization. To address this, we propose the first tooth-level point cloud denoising diffusion generative framework for fully automatic, single-shot inference of patient-specific crowns. Methodologically: (1) we introduce a novel diffusion modeling paradigm tailored to tooth-level point clouds; (2) we design a boundary-aware spatial prior network that jointly predicts anatomical boundaries and generates multi-tooth configurations; and (3) we embed 3D geometric constraints to ensure both high-fidelity reconstruction and clinical deployability. Evaluated on 496 external intraoral scan cases, our method achieves significantly higher geometric accuracy than state-of-the-art methods. Clinical validation on 26 cases demonstrates non-inferior crown quality compared to technician-designed crowns (p > 0.05), with an average 92% reduction in design time.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Digital crown design remains a labor-intensive bottleneck in restorative dentistry. We present extbf{CrownGen}, a generative framework that automates patient-customized crown design using a denoising diffusion model on a novel tooth-level point cloud representation. The system employs two core components: a boundary prediction module to establish spatial priors and a diffusion-based generative module to synthesize high-fidelity morphology for multiple teeth in a single inference pass. We validated CrownGen through a quantitative benchmark on 496 external scans and a clinical study of 26 restoration cases. Results demonstrate that CrownGen surpasses state-of-the-art models in geometric fidelity and significantly reduces active design time. Clinical assessments by trained dentists confirmed that CrownGen-assisted crowns are statistically non-inferior in quality to those produced by expert technicians using manual workflows. By automating complex prosthetic modeling, CrownGen offers a scalable solution to lower costs, shorten turnaround times, and enhance patient access to high-quality dental care.

Problem

• Automates patient-customized dental crown design
• Generates high-fidelity tooth morphology via diffusion model
• Reduces labor-intensive manual design time and costs

Innovation

• Uses denoising diffusion model on point clouds
• Integrates boundary prediction and generative modules
• Automates crown design for multiple teeth simultaneously