{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:29:20Z","timestamp":1787027360917,"version":"build-2736575974"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Accurate classification of pediatric dental diseases from panoramic radiographs is essential for early diagnosis and effective treatment planning. While deep learning models traditionally operate directly on image data, text-based representations generated from radiographs may provide an alternative strategy for disease classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposed a text-driven framework in which a natural language transformer was used to generate structured textual descriptions from panoramic radiographs. These descriptions were subsequently classified for binary disease detection using three deep learning architectures: a one-dimensional convolutional neural network (1D-CNN), a long short-term memory (LSTM) network, and a pretrained Bidirectional Encoder Representations from Transformer (BERT) model. Model performance was evaluated and compared against three pretrained convolutional neural networks trained directly on radiographic images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The 1D-CNN achieved the highest performance with 84% accuracy, demonstrating balanced classification across disease categories. The BERT model reached 77% accuracy, showing strong performance in detecting periapical infections but comparatively lower sensitivity for caries identification. The LSTM model performed substantially worse, achieving 57% accuracy. Both the 1D-CNN and BERT text-based approaches outperformed the three image-based pretrained CNN models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings suggest that text-based classification of panoramic radiographs is a potential alternative to conventional image-based deep learning methods. Language-driven models show promise for radiographic interpretation; however, challenges remain in achieving consistent generalizability across disease types. Future research should focus on improving radiograph-to-text generation quality, developing hybrid architectures that integrate textual and visual features, and validating performance on larger and more diverse datasets to strengthen clinical applicability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1754498","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:25:56Z","timestamp":1773829556000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Classification of pediatric dental diseases from panoramic radiographs using natural language transformer and deep learning models"],"prefix":"10.3389","volume":"9","author":[{"given":"Tuan D.","family":"Pham","sequence":"first","affiliation":[{"name":"Barts and The London School of Medicine and Dentistry, Queen Mary University of London","place":["London, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seba","family":"Al-Hebshi","sequence":"additional","affiliation":[{"name":"Barts and The London School of Medicine and Dentistry, Queen Mary University of London","place":["London, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e48291","DOI":"10.2196\/48291","article-title":"Large language models in medical education: opportunities, challenges, and future directions","volume":"9","author":"Abd-Alrazaq","year":"2023","journal-title":"JMIR Med Educ"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3649","DOI":"10.3390\/diagnostics13243649","article-title":"Detection, diagnosis, and monitoring of early caries: the future of individualized dental care","volume":"13","author":"Abdelaziz","year":"2023","journal-title":"Diagnostics"},{"key":"B3","first-page":"4171","article-title":"\u201cBERT pre-training of deep bidirectional transformers for language understanding,\u201d","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin","year":"2019"},{"key":"B4","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1308\/rcsbull.2023.132","article-title":"Artificial intelligence in dentistry: current state and future directions","volume":"105","author":"Dhingra","year":"2023","journal-title":"Bullet. Royal College Surg. Engl"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1085251","DOI":"10.3389\/fdmed.2023.1085251","article-title":"Artificial intelligence in dentistry\u2013A review","volume":"4","author":"Ding","year":"2023","journal-title":"Front. Dent. Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"657518","DOI":"10.3389\/froh.2021.657518","article-title":"Evidence-based caries management for all ages\u2013practical guidelines","volume":"2","author":"Featherstone","year":"2021","journal-title":"Front Oral Health"},{"key":"B7","doi-asserted-by":"publisher","first-page":"100081","DOI":"10.1016\/j.dentre.2024.100081","article-title":"review of advancements of artificial intelligence in dentistry","volume":"4","author":"Ghaffari","year":"2024","journal-title":"Dentist. Rev"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.2196\/51580","article-title":"Evaluation of the performance of generative AI large language models ChatGPT, Google Bard, and Microsoft Bing Chat in supporting evidence-based dentistry: comparative mixed methods study","author":"Giannakopoulos","year":"2023","journal-title":"J. Med. Internet Res"},{"key":"B9","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"survey on vision transformer","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B11","doi-asserted-by":"publisher","first-page":"303","DOI":"10.3233\/XST-230271","article-title":"Multimodal feature fusion in deep learning for comprehensive dental condition classification","volume":"32","author":"Hsieh","year":"2024","journal-title":"J. Xray. Sci. Technol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1038\/s41368-023-00239-y","article-title":"ChatGPT for shaping the future of dentistry: the potential of multi-modal large language model","author":"Huang","year":"2023","journal-title":"Int. J. Oral Sci"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1602.07360","article-title":"SqueezeNet: AlexNet-level accuracy with 50 \u00d7 fewer parameters and < 0.5MB model size","author":"Iandola","year":"2016","journal-title":"arXiv"},{"key":"B14","doi-asserted-by":"publisher","first-page":"275","DOI":"10.5624\/isd.20220050","article-title":"A deep learning approach to permanent tooth germ detection on pediatric panoramic radiographs","volume":"52","author":"Kaya","year":"2022","journal-title":"Imaging Sci. Dent"},{"key":"B15","doi-asserted-by":"publisher","first-page":"9819","DOI":"10.3390\/app12199819","article-title":"Performance of artificial intelligence (AI) models designed for application in pediatric dentistry\u2013a systematic review","volume":"12","author":"Khanagar","year":"2022","journal-title":"Appl. Sci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.3390\/healthcare12131311","article-title":"The implications of artificial intelligence in pedodontics: a scoping review of evidence-based literature","volume":"12","author":"La Rosa","year":"2024","journal-title":"Healthcare"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.2196\/preprints.60412","article-title":"Applications of ChatGPT in critical care medicine: opportunities, challenges, and future prospects","author":"Lin","year":"2024","journal-title":"JMIR Preprints"},{"key":"B20","doi-asserted-by":"publisher","first-page":"7","DOI":"10.4103\/jdrr.jdrr_199_22","article-title":"Artificial intelligence in pediatric dentistry\u2013a systematic review","volume":"10","author":"Mahajan","year":"2023","journal-title":"J. Dental Res. Rev"},{"key":"B21","doi-asserted-by":"publisher","first-page":"137","DOI":"10.15386\/cjmed-401","article-title":"Modern management of dental decay in children and adolescents \u2013 a review","volume":"88","author":"Muntean","year":"2015","journal-title":"Clujul Med"},{"key":"B22","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1186\/s12903-024-04160-6","article-title":"Fully automated deep learning approach to dental development assessment in panoramic radiographs","volume":"24","author":"Ong","year":"2024","journal-title":"BMC Oral Health"},{"key":"B23","unstructured":"ChatGPT; Large Language Model, 14 March 2023 Version\n          \n          2023"},{"key":"B24","unstructured":"Section 2A, Oral Health Across the Lifespan: Children\n          \n          Bethesda (MD)\n          National Institute of Dental and Craniofacial Research (US)\n          \n          2021"},{"key":"B25","doi-asserted-by":"publisher","first-page":"3449","DOI":"10.3390\/ijerph19063449","article-title":"Artificial intelligence in dentistry\u2013narrative review","volume":"19","author":"Ossowska","year":"2022","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1101\/2025.01.30.25321418","article-title":"Classification of pediatric dental diseases from panoramic radiographs using natural language transformer and deep learning models","author":"Pham","year":"2025","journal-title":"medRxiv"},{"key":"B27","doi-asserted-by":"publisher","first-page":"130417","DOI":"10.1016\/j.neucom.2025.130417","article-title":"Vision transformers on the edge: a comprehensive survey of model compression and acceleration strategies","volume":"643","author":"Saha","year":"2025","journal-title":"Neurocomputing"},{"key":"B28","first-page":"1","article-title":"\u201cGoing deeper with convolutions,\u201d","author":"Szegedy","year":"2015","journal-title":"Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e40367","DOI":"10.7759\/cureus.40367","article-title":"Implications of ChatGPT in public health dentistry: a systematic review","volume":"15","author":"Tiwari","year":"2023","journal-title":"Cureus"},{"key":"B30","doi-asserted-by":"publisher","first-page":"32","DOI":"10.3390\/technologies13010032","article-title":"Vision transformers for image classification: a comparative survey","volume":"13","author":"Wang","year":"2025","journal-title":"Technologies"},{"key":"B31","doi-asserted-by":"publisher","first-page":"e52746","DOI":"10.2196\/52746","article-title":"Performance of ChatGPT on nursing licensure examinations in the United States and China: cross-sectional study","volume":"10","author":"Wu","year":"2024","journal-title":"JMIR Med. Educ"},{"key":"B32","doi-asserted-by":"publisher","first-page":"e56413","DOI":"10.2196\/56413","article-title":"Performance of large language models in patient complaint resolution: web-based cross-sectional survey","volume":"26","author":"Yong","year":"2024","journal-title":"J. Med. Internet Res"},{"key":"B33","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1038\/s41597-023-02237-5","article-title":"Children's dental panoramic radiographs dataset for caries segmentation and dental disease detection","volume":"10","author":"Zhang","year":"2023","journal-title":"Sci Data"},{"key":"B34","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1038\/s41368-018-0012-3","article-title":"Common dental diseases in children and malocclusion","volume":"10","author":"Zou","year":"2018","journal-title":"Int. J. Oral Sci"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1754498\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:26:00Z","timestamp":1773829560000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1754498\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":34,"alternative-id":["10.3389\/frai.2026.1754498"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1754498","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,3]]},"article-number":"1754498"}}