Towards Generalist Intelligence in Dentistry: Vision Foundation Models for Oral and Maxillofacial Radiology

2025-10-16

AI Summary

Oral and maxillofacial radiology faces dual challenges: a critical shortage of specialized professionals and poor generalizability of existing AI models. Current approaches are predominantly single-task and single-modality, requiring large-scale, pixel-level annotations. To address this, we introduce DentVFM—the first dental vision foundation model—trained on DentVista, a self-constructed, million-scale, multi-center, multimodal imaging dataset. DentVFM employs a unified 2D/3D Vision Transformer architecture and integrates self-supervised and weakly supervised pretraining. We further propose DentBench, a comprehensive evaluation benchmark spanning eight dental subspecialties. Extensive experiments demonstrate that DentVFM significantly outperforms state-of-the-art supervised and self-supervised methods across diverse tasks—including disease diagnosis, anatomical landmark localization, and biomarker identification. Notably, its cross-modal reasoning capability enables diagnostic performance surpassing that of experienced clinicians even under modality dropout (e.g., missing CBCT or panoramic views), substantially improving label efficiency and clinical generalizability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Oral and maxillofacial radiology plays a vital role in dental healthcare, but radiographic image interpretation is limited by a shortage of trained professionals. While AI approaches have shown promise, existing dental AI systems are restricted by their single-modality focus, task-specific design, and reliance on costly labeled data, hindering their generalization across diverse clinical scenarios. To address these challenges, we introduce DentVFM, the first family of vision foundation models (VFMs) designed for dentistry. DentVFM generates task-agnostic visual representations for a wide range of dental applications and uses self-supervised learning on DentVista, a large curated dental imaging dataset with approximately 1.6 million multi-modal radiographic images from various medical centers. DentVFM includes 2D and 3D variants based on the Vision Transformer (ViT) architecture. To address gaps in dental intelligence assessment and benchmarks, we introduce DentBench, a comprehensive benchmark covering eight dental subspecialties, more diseases, imaging modalities, and a wide geographical distribution. DentVFM shows impressive generalist intelligence, demonstrating robust generalization to diverse dental tasks, such as disease diagnosis, treatment analysis, biomarker identification, and anatomical landmark detection and segmentation. Experimental results indicate DentVFM significantly outperforms supervised, self-supervised, and weakly supervised baselines, offering superior generalization, label efficiency, and scalability. Additionally, DentVFM enables cross-modality diagnostics, providing more reliable results than experienced dentists in situations where conventional imaging is unavailable. DentVFM sets a new paradigm for dental AI, offering a scalable, adaptable, and label-efficient model to improve intelligent dental healthcare and address critical gaps in global oral healthcare.

Problem

• Addressing dental AI limitations in generalization across clinical scenarios
• Overcoming shortage of professionals for radiographic image interpretation
• Developing adaptable vision models for multi-modal dental applications

Innovation

• Self-supervised learning on multi-modal dental images
• Task-agnostic vision foundation models for dentistry
• Comprehensive benchmark covering eight dental subspecialties