OralGPT-Omni: A Versatile Dental Multimodal Large Language Model

2025-11-26

AI Summary

Dental medicine lacks dedicated research on multimodal large language models (MLLMs), hindered by scarce annotated data, fragmented modality modeling, and insufficient clinical trustworthiness. Method: We introduce TRACE-CoT, a clinical chain-of-thought reasoning dataset, and a four-stage progressive training paradigm to construct MMOral-Uni—the first unified multimodal dental evaluation benchmark—supporting joint modeling of five imaging modalities (e.g., X-ray, CBCT) and clinical tasks (e.g., diagnosis, segmentation). Our approach innovatively integrates chain-of-thought supervision, cross-modal alignment, and expert-annotated data augmentation. Contribution/Results: This framework significantly enhances model interpretability and generalization. On MMOral-Uni and MMOral-OPG benchmarks, our method achieves 51.84 and 45.31 points, respectively—substantially outperforming prior approaches—and advances dental AI toward clinical deployment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Multimodal Large Language Models (MLLMs) have exhibited immense potential across numerous medical specialties; yet, dentistry remains underexplored, in part due to limited domain-specific data, scarce dental expert annotations, insufficient modality-specific modeling, and challenges in reliability. In this paper, we present OralGPT-Omni, the first dental-specialized MLLM designed for comprehensive and trustworthy analysis across diverse dental imaging modalities and clinical tasks. To explicitly capture dentists' diagnostic reasoning, we construct TRACE-CoT, a clinically grounded chain-of-thought dataset that mirrors dental radiologists' decision-making processes. This reasoning supervision, combined with our proposed four-stage training paradigm, substantially strengthens the model's capacity for dental image understanding and analysis. In parallel, we introduce MMOral-Uni, the first unified multimodal benchmark for dental image analysis. It comprises 2,809 open-ended question-answer pairs spanning five modalities and five tasks, offering a comprehensive evaluation suite to date for MLLMs in digital dentistry. OralGPT-Omni achieves an overall score of 51.84 on the MMOral-Uni benchmark and 45.31 on the MMOral-OPG benchmark, dramatically outperforming the scores of GPT-5. Our work promotes intelligent dentistry and paves the way for future advances in dental image analysis. All code, benchmark, and models will be made publicly available.

Problem

• Dentistry lacks specialized multimodal AI models for comprehensive dental image analysis.
• Limited dental data and expert annotations hinder reliable AI applications in dentistry.
• No unified benchmark exists to evaluate multimodal AI performance across dental tasks.

Innovation

• Developed OralGPT-Omni, a multimodal model for dental image analysis
• Created TRACE-CoT dataset to mimic dentists' diagnostic reasoning processes
• Introduced MMOral-Uni benchmark for evaluating dental multimodal models