{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:02:43Z","timestamp":1775624563614,"version":"3.50.1"},"reference-count":22,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T00:00:00Z","timestamp":1775347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"EyeTech Co., Ltd.","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Vision-language models (VLMs) such as GPT (Generative Pre-Trained Transformer) have shown potential for medical image interpretation; however, challenges remain in generating reliable radiological findings in clinical practice, as exemplified by dental pathologies. This study proposes a Self-correction Loop with Structured Output (SLSO) framework as an integrated processing methodology to enhance the accuracy and reliability of AI-generated findings for jaw cysts in dental panoramic radiographs. Methods: Dental panoramic radiographs with jaw cysts were used to implement a 10-step integrated processing framework incorporating image analysis, structured data generation, tooth number extraction, consistency checking, and iterative regeneration. The framework functioned as an external validation mechanism for GPT outputs. Performance was compared against the conventional Chain-of-Thought (CoT) method across seven evaluation items: transparency, internal structure, borders, root resorption, tooth displacement, relationships with other structures, and tooth number. Results: The SLSO framework improved output accuracy for multiple items compared to the CoT method, with the most notable improvements observed in tooth number identification, tooth displacement detection, and root resorption assessment. In successful cases, consistently structured outputs were achieved after up to five regenerations. The framework enforced explicit negative finding descriptions and suppressed hallucinations, although accurate identification of extensive lesions spanning multiple teeth remained limited. Conclusions: This investigation established the feasibility of the proposed integrated processing methodology and provided a foundation for future validation studies with larger, more diverse datasets.<\/jats:p>","DOI":"10.3390\/diagnostics16071096","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T00:19:32Z","timestamp":1775434772000},"page":"1096","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with a Structured Output (SLSO) Framework"],"prefix":"10.3390","volume":"16","author":[{"given":"Nanaka","family":"Hosokawa","sequence":"first","affiliation":[{"name":"Graduate School of Natural Science and Technology, Gifu University, Gifu 501-1193, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4759-522X","authenticated-orcid":false,"given":"Ryo","family":"Takahashi","sequence":"additional","affiliation":[{"name":"EyeTech Co., Ltd., Tokyo 113-0033, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5383-319X","authenticated-orcid":false,"given":"Tomoya","family":"Kitano","sequence":"additional","affiliation":[{"name":"School of Dentistry, Asahi University, Mizuho 501-0296, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5274-4077","authenticated-orcid":false,"given":"Yukihiro","family":"Iida","sequence":"additional","affiliation":[{"name":"School of Dentistry, Asahi University, Mizuho 501-0296, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chisako","family":"Muramatsu","sequence":"additional","affiliation":[{"name":"Faculty of Data Science, Shiga University, Hikone 522-8522, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuro","family":"Hayashi","sequence":"additional","affiliation":[{"name":"EyeTech Co., Ltd., Tokyo 113-0033, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3993-7146","authenticated-orcid":false,"given":"Yuta","family":"Seino","sequence":"additional","affiliation":[{"name":"Division for Oral Dental Informatics, The University of Osaka Dental Hospital, Osaka 565-0871, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5838-5885","authenticated-orcid":false,"given":"Xiangrong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Gifu University, Gifu 501-1193, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0235-238X","authenticated-orcid":false,"given":"Takeshi","family":"Hara","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Gifu University, Gifu 501-1193, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akitoshi","family":"Katsumata","sequence":"additional","affiliation":[{"name":"School of Dentistry, Asahi University, Mizuho 501-0296, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2936-9296","authenticated-orcid":false,"given":"Hiroshi","family":"Fujita","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Gifu University, Gifu 501-1193, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,5]]},"reference":[{"key":"ref_1","unstructured":"Ye, J., and Tang, H. (2025). Multimodal Large Language Models for Medicine: A Comprehensive Survey. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1038\/s44387-025-00011-z","article-title":"Large Language Models for Disease Diagnosis: A Scoping Review","volume":"1","author":"Zhou","year":"2025","journal-title":"NPJ Artif. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1016\/j.sdentj.2024.11.006","article-title":"An Exploratory Assessment of GPT-4o and GPT-4 Performance on the Japanese National Dental Examination","volume":"36","author":"Morishita","year":"2024","journal-title":"Saudi Dent. J."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ramlogan, S., Raman, V., and Ramlogan, S. (2025). A Pilot Study of the Performance of ChatGPT and Other Large Language Models on a Written Final Year Periodontology Exam. BMC Med. Educ., 25.","DOI":"10.1186\/s12909-025-07195-7"},{"key":"ref_5","first-page":"e68813","article-title":"GPT-4o vs. Human Candidates: Performance Analysis in the Polish Final Dentistry Examination","volume":"16","author":"Jaworski","year":"2024","journal-title":"Cureus"},{"key":"ref_6","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","volume":"19","author":"Morishita","year":"2024","journal-title":"J. Dent. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Dasanayaka, C., Dandeniya, K., Dissanayake, M.B., Gunasena, C., and Jayasinghe, R. (2025). Multimodal AI and Large Language Models for Orthopantomography Radiology Report Generation and Q&A. Appl. Syst. Innov., 8.","DOI":"10.3390\/asi8020039"},{"key":"ref_8","first-page":"100364","article-title":"A Deep Learning Vision-Language Model for Diagnosing Pediatric Dental Diseases","volume":"13","author":"Pham","year":"2026","journal-title":"Intell. Med."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"A\u015far, E.M., \u0130pek, \u0130., and Bilge, K. (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_10","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ai, Q.Y.H., Yeung, A.W.K., Tanaka, R., Nalley, A., and Hung, K.F. (2025). Performance of a Vision-Language Model in Detecting Common Dental Conditions on Panoramic Radiographs Using Different Tooth Numbering Systems. Diagnostics, 15.","DOI":"10.3390\/diagnostics15182315"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Camlet, A., Kusiak, A., Ossowska, A., and \u015awietlik, D. (2025). Advances in Periodontal Diagnostics: Application of MultiModal Language Models in Visual Interpretation of Panoramic Radiographs. Diagnostics, 15.","DOI":"10.3390\/diagnostics15151851"},{"key":"ref_12","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_13","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhao, Y., and Parnell, L.A. (2024). Factuality of Large Language Models: A Survey. arXiv.","DOI":"10.18653\/v1\/2024.emnlp-main.1088"},{"key":"ref_14","first-page":"e35179","article-title":"Artificial Hallucinations in ChatGPT: Implications in Scientific Writing","volume":"15","author":"Alkaissi","year":"2023","journal-title":"Cureus"},{"key":"ref_15","unstructured":"Chang, A., Huang, L., Bhatia, P., Kass-Hout, T., Ma, F., and Xiao, C. (2025). MedHEval: Benchmarking Hallucinations and Mitigation Strategies in Medical Large Vision-Language Models. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"20200185","DOI":"10.1259\/dmfr.20200185","article-title":"Automatic Diagnosis for Cysts and Tumors of Both Jaws on Panoramic Radiographs Using a Deep Convolution Neural Network","volume":"49","author":"Kwon","year":"2020","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yang, H., Jo, E., Kim, H.J., Cha, I.H., Jung, Y.S., Nam, W., Kim, J.Y., Kim, J.W., Kim, J.H., and Lee, J.H. (2020). Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs. J. Clin. Med., 9.","DOI":"10.3390\/jcm9061839"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Li, B., Cheng, Y., and Kim, J. (2024). Odontogenic Cystic Lesion Segmentation on Cone-Beam CT Using an Auto-Adapting Multi-Scaled UNet. Front. Oncol., 14.","DOI":"10.3389\/fonc.2024.1379624"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.oooo.2023.09.012","article-title":"Automatic Detection and Classification of Nasopalatine Duct Cyst and Periapical Cyst on Panoramic Radiographs Using Deep Convolutional Neural Networks","volume":"138","author":"Lee","year":"2024","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1007\/s12194-025-00936-9","article-title":"Detection and Dual-Label Classification of Tooth Number and Condition in Dental Panoramic Radiographs Including Deciduous Teeth","volume":"18","author":"Sakai","year":"2025","journal-title":"Radiol. Phys. Technol."},{"key":"ref_21","unstructured":"Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., and Yang, Y. (2023). Self-Refine: Iterative Refinement with Self-Feedback. Advances in Neural Information Processing Systems 36 (NeurIPS 2023), Neural Information Processing Systems Foundation."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3968","DOI":"10.1038\/s41591-025-04008-8","article-title":"The Fragile Intelligence of GPT-5 in Medicine","volume":"31","author":"Handler","year":"2025","journal-title":"Nat. Med."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/7\/1096\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T04:24:01Z","timestamp":1775622241000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/7\/1096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,5]]},"references-count":22,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["diagnostics16071096"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16071096","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,5]]}}}