Academic Journal
Vision-Language Model as a 'Zero-Shot' Assistant for Evaluating Condylar Osseous Changes in Cone-beam Computed Tomography.
| Τίτλος: | Vision-Language Model as a 'Zero-Shot' Assistant for Evaluating Condylar Osseous Changes in Cone-beam Computed Tomography. |
|---|---|
| Συγγραφείς: | Chen K; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: dentistfrankchen@outlook.com., Zhang A; Department of Biophysics, Johns Hopkins University, Baltimore, Maryland, USA., Xie X; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: dentistxxj@mail.ccmu.edu.cn., Bai Y; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: byuxing@ccmu.edu.cn. |
| Πηγή: | International dental journal [Int Dent J] 2026 Oct; Vol. 76 (5), pp. 109817. Date of Electronic Publication: 2026 Aug 13. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Elsevier Country of Publication: England NLM ID: 0374714 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1875-595X (Electronic) Linking ISSN: 00206539 NLM ISO Abbreviation: Int Dent J Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2021- : London : Elsevier Original Publication: London : FDI World Dental |
| Ιατρικοί όροι (MeSH): | Cone-Beam Computed Tomography*/methods , Mandibular Condyle*/diagnostic imaging , Radiographic Image Interpretation, Computer-Assisted*/methods , Artificial Intelligence*, Humans ; Large Language Models ; Sensitivity and Specificity ; Generative Artificial Intelligence |
| Περίληψη: | Introduction and Aims: Interpreting condylar osseous changes on CBCT is challenging for general practitioners. This study evaluated the 'zero-shot' diagnostic performance and utility of Vision-Language Models (VLMs) as AI assistants for detecting condylar abnormalities. Methods: We analysed 72 CBCT images from the EHPN study for internal validation and constructed a balanced sample of 70 images from the MMDental dataset for external validation, with dual-radiologist consensus as the ground truth. Three frontier VLMs (Gemini-3, GPT-5.2, and Qwen3-VL) were used to evaluate representative sagittal slices without prior fine-tuning. Performance was measured by diagnostic accuracy, sensitivity, specificity, and balanced accuracy, while the Quality Assessment of Medical AI-generated Information (QAMAI) framework assessed the quality of AI-generated structured reports. This study was reported following STARD-AI and CLAIM guidelines as primary checklists, with TRIPOD-LLM as a supplementary framework. Results: Gemini-3 achieved the highest diagnostic accuracy (90.3%; 95% CI: 81.0%-95.5%), outperforming GPT-5.2 (75.0%) and Qwen3-VL (55.6%). External validation on a constructed balanced sample from the MMDental dataset confirmed these findings, with Gemini-3 achieving 90.00% accuracy. Regarding report generation, Gemini-3 surpassed the other models across five QAMAI dimensions, providing more accurate, clear, and clinically useful justifications aligned with diagnostic standards. Conclusion: VLMs, particularly Gemini-3, exhibit zero-shot capabilities in identifying condylar changes and generating high-quality diagnostic reports. While these models maintain a conservative diagnostic tendency, they demonstrate potential as preliminary, training-free screening aids in oral maxillofacial radiology. Further multicentre validation is warranted to establish clinical utility. Clinical Relevance: Cloud-based VLMs could offer accessible screening assistance by allowing general practitioners to query condylar findings via simple web interfaces without specialized hardware. These tools may contribute to structured reporting workflows, though their diagnostic consistency in routine practice remains to be established, and they should complement rather than replace expert clinical judgment. (Copyright © 2026 The Authors. Published by Elsevier Inc. All rights reserved.) |
| Competing Interests: | Conflict of interest None disclosed. No author has received consulting fees, honoraria, or other payments from AI model providers (Google, OpenAI, Alibaba) or related entities. |
| Contributed Indexing: | Keywords: Artificial Intelligence; Cone-beam computed tomography; LLM; Temporomandibular Joint; Vision-language model |
| Entry Date(s): | Date Created: 20260813 Date Completed: 20260916 Latest Revision: 20260916 |
| Update Code: | 20260916 |
| PubMed Central ID: | PMC13499149 |
| DOI: | 10.1016/j.identj.2026.109817 |
| PMID: | 42594712 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1875-595X |
|---|---|
| DOI: | 10.1016/j.identj.2026.109817 |