{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T21:15:39Z","timestamp":1790198139711,"version":"4.1.0"},"reference-count":50,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003803","name":"HKU URC Seed Fund for Basic Research for New Staff at the University of Hong Kong","doi-asserted-by":"publisher","award":["103036002"],"award-info":[{"award-number":["103036002"]}],"id":[{"id":"10.13039\/501100003803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Objectives: The aim of this study was to evaluate the performance of GPT-4o in identifying nine common dental conditions on panoramic radiographs, both overall and at specific tooth sites, and to assess whether the use of different tooth numbering systems (FDI and Universal) in prompts would affect its diagnostic accuracy. Methods: Fifty panoramic radiographs exhibiting various common dental conditions including missing teeth, impacted teeth, caries, endodontically treated teeth, teeth with restorations, periapical lesions, periodontal bone loss, tooth fractures, cracks, retained roots, dental implants, osteolytic lesions, and osteosclerosis were included. Each image was evaluated twice by GPT-4o in May 2025, using structured prompts based on either the FDI or Universal tooth numbering system, to identify the presence of these conditions at specific tooth sites or regions. GPT-4o responses were compared to a consensus reference standard established by an oral-maxillofacial radiology team. GPT-4o\u2019s performance was evaluated using balanced accuracy, sensitivity, specificity, and F1 score both at the patient and tooth levels. Results: A total of 100 GPT-4o responses were generated. At the patient level, balanced accuracy ranged from 46.25% to 98.83% (FDI) and 49.75% to 92.86% (Universal), with the highest accuracies for dental implants (92.86\u201398.83%). F1-scores and sensitivities were highest for implants, missing, and impacted teeth, but zero for caries, periapical lesions, and fractures. Specificity was generally high across conditions. Notable discrepancies were observed between patient- and tooth-level performance, especially for implants and restorations. GPT-4o\u2019s performance was similar between using the two numbering systems. Conclusions: GPT-4o demonstrated superior performance in detecting dental implants and treated or restored teeth but inferior performance for caries, periapical lesions, and fractures. Diagnostic accuracy was higher at the patient level than at the tooth level, with similar performances for both numbering systems. Future studies with larger, more diverse datasets and multiple models are needed.<\/jats:p>","DOI":"10.3390\/diagnostics15182315","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T07:52:28Z","timestamp":1757663548000},"page":"2315","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Performance of a Vision-Language Model in Detecting Common Dental Conditions on Panoramic Radiographs Using Different Tooth Numbering Systems"],"prefix":"10.3390","volume":"15","author":[{"given":"Zekai","family":"Liu","sequence":"first","affiliation":[{"name":"Oral and Maxillofacial Radiology, Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1155-4389","authenticated-orcid":false,"given":"Qi Yong H.","family":"Ai","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong SAR 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3672-357X","authenticated-orcid":false,"given":"Andy Wai Kan","family":"Yeung","sequence":"additional","affiliation":[{"name":"Oral and Maxillofacial Radiology, Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ray","family":"Tanaka","sequence":"additional","affiliation":[{"name":"Oral and Maxillofacial Radiology, Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Nalley","sequence":"additional","affiliation":[{"name":"Oral and Maxillofacial Radiology, Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3971-3484","authenticated-orcid":false,"given":"Kuo Feng","family":"Hung","sequence":"additional","affiliation":[{"name":"Oral and Maxillofacial Radiology, Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"100858","DOI":"10.1016\/j.identj.2025.100858","article-title":"Ai-powered problem- and case-based learning in medical and dental education: A systematic review and meta-analysis","volume":"75","author":"Wei","year":"2025","journal-title":"Int. Dent. J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1093\/dmfr\/twad001","article-title":"Deep learning for tooth identification and numbering on dental radiography: A systematic review and meta-analysis","volume":"53","author":"Sadr","year":"2024","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Hao, J., Wong, L.M., Shan, Z., Ai, Q.Y.H., Shi, X., Tsoi, J.K.H., and Hung, K.F. (2024). A semi-supervised transformer-based deep learning framework for automated tooth segmentation and identification on panoramic radiographs. Diagnostics, 14.","DOI":"10.3390\/diagnostics14171948"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105526","DOI":"10.1016\/j.jdent.2024.105526","article-title":"A novel ai model for detecting periapical lesion on cbct: Cbct-sam","volume":"153","author":"Chau","year":"2025","journal-title":"J. Dent."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1093\/dmfr\/twae070","article-title":"Detection of periodontal bone loss and periodontitis from 2d dental radiographs via machine learning and deep learning: Systematic review employing appraise-ai and meta-analysis","volume":"54","author":"Khubrani","year":"2025","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s41746-025-01818-5","article-title":"Characteristics, licensing, and ethical considerations of openly accessible oral-maxillofacial imaging datasets: A systematic review","volume":"8","author":"Hao","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e64","DOI":"10.1016\/S2589-7500(21)00252-1","article-title":"Characteristics of publicly available skin cancer image datasets: A systematic review","volume":"4","author":"Wen","year":"2022","journal-title":"Lancet Digit. Health"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e51","DOI":"10.1016\/S2589-7500(20)30240-5","article-title":"A global review of publicly available datasets for ophthalmological imaging: Barriers to access, usability, and generalisability","volume":"3","author":"Khan","year":"2021","journal-title":"Lancet Digit. Health"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1650","DOI":"10.1109\/JBHI.2021.3117575","article-title":"Tufts dental database: A multimodal panoramic x-ray dataset for benchmarking diagnostic systems","volume":"26","author":"Panetta","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1038\/s41597-023-02237-5","article-title":"Children\u2019s dental panoramic radiographs dataset for caries segmentation and dental disease detection","volume":"10","author":"Zhang","year":"2023","journal-title":"Sci. Data"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhou, W., Lu, X., Zhao, D., Jiang, M., Fan, L., Zhang, W., Li, F., Wang, D., Yin, W., and Liu, X. (2024). A dual-labeled dataset and fusion model for automatic teeth segmentation, numbering, and state assessment on panoramic radiographs. BMC Oral Health, 24.","DOI":"10.1186\/s12903-024-04984-2"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"105737","DOI":"10.1016\/j.oraloncology.2022.105737","article-title":"Scarcity of publicly available oral cancer image datasets for machine learning research","volume":"126","author":"Sengupta","year":"2022","journal-title":"Oral Oncol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"109128","DOI":"10.1016\/j.dib.2023.109128","article-title":"Ndb-ufes: An oral cancer and leukoplakia dataset composed of histopathological images and patient data","volume":"48","author":"Soares","year":"2023","journal-title":"Data Brief"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1007\/s10278-024-01041-w","article-title":"Oralepitheliumdb: A dataset for oral epithelial dysplasia image segmentation and classification","volume":"37","author":"Silva","year":"2024","journal-title":"J. Imaging Inform. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1002\/hcs2.61","article-title":"Large language models in health care: Development, applications, and challenges","volume":"2","author":"Yang","year":"2023","journal-title":"Health Care Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1001\/jama.2024.21700","article-title":"Testing and evaluation of health care applications of large language models: A systematic review","volume":"333","author":"Bedi","year":"2025","journal-title":"JAMA"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s13677-020-00218-2","article-title":"Cloud-based intelligent self-diagnosis and department recommendation service using chinese medical bert","volume":"10","author":"Wang","year":"2021","journal-title":"J. Cloud Comput. Adv. Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104717","DOI":"10.1016\/j.ijnurstu.2024.104717","article-title":"Assessing question characteristic influences on chatgpt\u2019s performance and response-explanation consistency: Insights from taiwan\u2019s nursing licensing exam","volume":"153","author":"Su","year":"2024","journal-title":"Int. J. Nurs. Stud."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e230364","DOI":"10.1148\/ryai.230364","article-title":"Performance of an open-source large language model in extracting information from free-text radiology reports","volume":"6","author":"Geay","year":"2024","journal-title":"Radiol. Artif. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hirosawa, T., Harada, Y., Yokose, M., Sakamoto, T., Kawamura, R., and Shimizu, T. (2023). Diagnostic accuracy of differential-diagnosis lists generated by generative pretrained transformer 3 chatbot for clinical vignettes with common chief complaints: A pilot study. Int. J. Environ. Res. Public Health, 20.","DOI":"10.3390\/ijerph20043378"},{"key":"ref_21","unstructured":"OpenAI (2025, September 11). Gpt-4o System Card. Available online: https:\/\/openai.com\/index\/gpt-4o-system-card\/."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1016\/j.jds.2023.12.007","article-title":"Evaluating gpt-4v\u2019s performance in the japanese national dental examination: A challenge explored evaluating gpt-4v\u2019s performance in the japanese national dental examination: A challenge explored","volume":"19","author":"Masaki","year":"2024","journal-title":"J. Dent. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"A\u015far, E.M., \u0130pek, \u0130., and Lge, K.B. (2025). Customized gpt-4v(ision) for radiographic diagnosis: Can large language model detect supernumerary teeth?. BMC Oral Health, 25.","DOI":"10.1186\/s12903-025-06163-3"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e56110","DOI":"10.2196\/56110","article-title":"Chatgpt with gpt-4 outperforms emergency department physicians in diagnostic accuracy: Retrospective analysis","volume":"26","author":"Hoppe","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1016\/j.jdent.2012.04.018","article-title":"A study to determine the added value of 740 screening panoramic radiographs compared to intraoral radiography in the management of adult (>18 years) dentate patients in a primary care setting","volume":"40","author":"Rushton","year":"2012","journal-title":"J. Dent."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1148\/rg.2021200112","article-title":"Pediatric panoramic radiography: Techniques, artifacts, and interpretation","volume":"41","author":"Sams","year":"2021","journal-title":"Radiographics"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e10","DOI":"10.1016\/j.bjoms.2007.07.135","article-title":"Inferior alveolar nerve injury and surgical difficulty prediction in third molar surgery: The role of dental panoramic tomography","volume":"45","author":"Jerjes","year":"2007","journal-title":"Br. J. Oral Maxillofac. Surg."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zheng, J., Ding, X., Pu, J.J., Chung, S.M., Ai, Q.Y.H., Hung, K.F., and Shan, Z. (2024). Unlocking the potentials of large language models in orthodontics: A scoping review. Bioengineering, 11.","DOI":"10.3390\/bioengineering11111145"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Mao, K., Wong, L.M., Zhang, R., So, T.Y., Shan, Z., Hung, K.F., and Ai, Q.Y.H. (2023). Radiomics analysis in characterization of salivary gland tumors on mri: A systematic review. Cancers, 15.","DOI":"10.3390\/cancers15204918"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/dmfr\/twae055","article-title":"Temporomandibular joint assessment in mri images using artificial intelligence tools: Where are we now? A systematic review","volume":"54","author":"Manek","year":"2025","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1093\/dmfr\/twaf027","article-title":"Performance of artificial intelligence in evaluating maxillary sinus mucosal alterations in imaging examinations: Systematic review","volume":"54","author":"Moreira","year":"2025","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Querrer, R., Vieira, L.S., Teodoro, A.B., Melo, N.S., Mesquita, C.R.M., Silva, M.A.G., Figueiredo, P.T.S., and Leite, A.F. (2025). Deep learning for osteoporosis screening in dental practice: A systematic review. Dentomaxillofacial Radiol., twaf052.","DOI":"10.1093\/dmfr\/twaf052"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"100883","DOI":"10.1016\/j.identj.2025.100883","article-title":"Artificial intelligence in detecting periodontal disease from intraoral photographs: A systematic review","volume":"75","author":"Mao","year":"2025","journal-title":"Int. Dent. J."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Nalley, A., Hao, J., QY, H.A., Yeung, A.W.K., Tanaka, R., and Hung, K.F. (2025). The performance of large language models in dentomaxillofacial radiology: A systematic review. Dentomaxillofacial Radiol., twaf060.","DOI":"10.1093\/dmfr\/twaf060"},{"key":"ref_35","first-page":"e42133","article-title":"The potential usefulness of chatgpt in oral and maxillofacial radiology","volume":"15","author":"Mago","year":"2023","journal-title":"Cur\u0113us"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Machado, V., Proen\u00e7a, L., Morgado, M., Mendes, J.J., and Botelho, J. (2020). Accuracy of panoramic radiograph for diagnosing periodontitis comparing to clinical examination. J. Clin. Med., 9.","DOI":"10.3390\/jcm9072313"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e70042","DOI":"10.1002\/cre2.70042","article-title":"Evaluation of panoramic radiography diagnostic accuracy in the assessment of interdental alveolar bone loss using cbct","volume":"10","author":"Anbiaee","year":"2024","journal-title":"Clin. Exp. Dent. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"20220244","DOI":"10.1259\/dmfr.20220244","article-title":"Automated detection of dental restorations using deep learning on panoramic radiographs","volume":"51","year":"2022","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lee, D.W., Kim, S.Y., Jeong, S.N., and Lee, J.H. (2021). Artificial intelligence in fractured dental implant detection and classification: Evaluation using dataset from two dental hospitals. Diagnostics, 11.","DOI":"10.3390\/diagnostics11020233"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e70000","DOI":"10.1111\/cid.70000","article-title":"Artificial intelligence-based detection and numbering of dental implants on panoramic radiographs","volume":"27","author":"Balel","year":"2025","journal-title":"Clin. Implant. Dent. Relat. Res."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zadro\u017cny, \u0141., Regulski, P., Brus-Sawczuk, K., Czajkowska, M., Parkanyi, L., Ganz, S., and Mijiritsky, E. (2022). Artificial intelligence application in assessment of panoramic radiographs. Diagnostics, 12.","DOI":"10.3390\/diagnostics12010224"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zhu, J., Chen, Z., Zhao, J., Yu, Y., Li, X., Shi, K., Zhang, F., Yu, F., Shi, K., and Sun, Z. (2023). Artificial intelligence in the diagnosis of dental diseases on panoramic radiographs: A preliminary study. BMC Oral Health, 23.","DOI":"10.1186\/s12903-023-03027-6"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"550","DOI":"10.31128\/AJGP-07-20-5536","article-title":"Interpreting an orthopantomogram","volume":"49","author":"Cosson","year":"2020","journal-title":"Aust. J. Gen. Pract."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"20200154","DOI":"10.1259\/dmfr.20200154","article-title":"Effect of computer-assisted-learning and simulation clinics on dental students\u2019 cognitive and performance skills: Panoramic image errors related to patient\u2019s head position","volume":"49","author":"Wenzel","year":"2020","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1007\/s12663-020-01473-1","article-title":"Prevalence of mandibular third molars according to the pell & gregory and winter classifications","volume":"21","author":"Santos","year":"2022","journal-title":"J. Maxillofac. Oral Surg."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1007\/s11282-024-00799-7","article-title":"Evaluation of the effectiveness of panoramic radiography in impacted mandibular third molars on deep learning models developed with findings obtained with cone beam computed tomography","volume":"41","author":"Kumbasar","year":"2025","journal-title":"Oral Radiol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.csbj.2025.04.010","article-title":"Decoding wisdom: Evaluating chatgpt\u2019s accuracy and reproducibility in analyzing orthopantomographic images for third molar assessment","volume":"28","author":"Arena","year":"2025","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.ajodo.2025.02.017","article-title":"Performance of chat generative pretrained transformer-4.0 in determining labiolingual localization of maxillary impacted canine and presence of resorption in incisors through panoramic radiographs: A retrospective study","volume":"168","author":"Salmanpour","year":"2025","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1007\/s00784-024-05587-5","article-title":"Performance of a commercially available generative pre-trained transformer (gpt) in describing radiolucent lesions in panoramic radiographs and establishing differential diagnoses","volume":"28","author":"Silva","year":"2024","journal-title":"Clin. Oral Investig."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Owusu-Adjei, M., Hayfron-Acquah, J.B., Frimpong, T., and Abdul-Salaam, G. (2023). Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems. PLoS Digit. Health, 2.","DOI":"10.1371\/journal.pdig.0000290"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/18\/2315\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:44:20Z","timestamp":1760035460000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/18\/2315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":50,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["diagnostics15182315"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15182315","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]}}}