[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-460640-105":59,"doc-detail-460640-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","challenges-and-limitations-of-multimodal-large-language-models-in-interpreting-pediatric-panoramic-radiographs","Challenges and Limitations of Multimodal Large Language Models in Interpreting Pediatric Panoramic Radiographs","","Multimodal large language models (LLMs) offer promise for medical image analysis, yet dependable interpretation of pediatric panoramic radiographs remains uncertain. This study assessed two multimodal LLMs—OpenAI o1 and Claude 3.5 Sonnet—for detecting and counting teeth, including tooth germs, on 87 pediatric radiographs. Images were annotated by two pediatric dentists and processed five times with identical prompts; results were benchmarked using performance metrics and Fleiss’ kappa. Both models missed nuanced developmental stages and minor tooth loss; Claude 3.5 Sonnet showed higher sensitivity but very low specificity with many false positives, while OpenAI o1 had better specificity but still failed in mixed dentition cases. Both exhibited substantial variability across repeated runs, indicating clinically inadequate reliability.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/challenges-and-limitations-of-multimodal-large-language-models-in-interpreting-pediatric-panoramic-radiographs/460640/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/challenges-and-limitations-of-multimodal-large-language-models-in-interpreting-pediatric-panoramic-radiographs/460640.png","ImageObject",300,407,{"name":92,"@type":93},"Liam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Which multimodal LLMs were evaluated for interpreting pediatric panoramic radiographs?","Question",{"text":112,"@type":113},"The study evaluated OpenAI o1 and Claude 3.5 Sonnet for detecting and counting teeth (including tooth germs).","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How was the model performance assessed in the study?",{"text":117,"@type":113},"Eighty-seven pediatric panoramic radiographs from an open-source dataset were analyzed, with two pediatric dentists annotating each potential tooth position. The models processed each image five times with identical prompts, and performance metrics plus Fleiss’ kappa were calculated.",{"name":119,"@type":110,"acceptedAnswer":120},"What were the key findings about limitations and reliability?",{"text":121,"@type":113},"Both models failed to achieve clinically acceptable performance, particularly for subtle developmental stages and minor tooth loss. Claude 3.5 Sonnet produced many false positives due to low specificity, OpenAI o1 showed better specificity but still missed subtle defects in mixed dentition cases, and both models varied substantially across repeated runs.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},460640,1791180481,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":34,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","International Journal of Paediatric Dentistry  \nORIGINAL ARTICLE  OPEN ACCESS   \nChallenges and Limitations of Multimodal Large Language Models in Interpreting Pediatric Panoramic Radiographs  \nYuichi Mine1,2  | Yuko Iwamoto3  | Shota Okazaki1,2 | Taku Nishimura2,3 | Eimi Tabata2,3 | Saori Takeda2 | Tzu-Yu Peng4 | Ryota Nomura3 | Naoya Kakimoto5 | Takeshi Murayama1,2  \n1Project Research Center for Integrating Digital Dentistry, Hiroshima University, Hiroshima, Japan | 2Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan | 3Department of Pediatric Dentistry, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan | 4School of Dentistry, College of Oral Medicine, Taipei Medical University, Taipei, Taiwan | 5Department of Oral and Maxillofacial Radiology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan  \nCorrespondence: Yuichi Mine ([mine@hiroshima-u.ac.jp](mine@hiroshima-u.ac.jp))  \nReceived: 15 April 2025 | Revised: 9 July 2025 | Accepted: 16 August 2025  \nFunding: This study was partially supported by SmaSo-X Challenge Project Young Researchers Research Grant from the Graduate School of Innovation and Practice for Smart Society, Hiroshima University to Y.M.  \nKeywords: artificial intelligence | multimodal large language models | panoramic radiograph | pediatric patients  \nABSTRACT  \nBackground: Multimodal large language models (LLMs) have potential for medical image analysis, yet their reliability for pediatric panoramic radiographs remains uncertain.  \nAim: This study evaluated two multimodal LLMs (OpenAI o1, Claude 3.5 Sonnet) for detecting and counting teeth (including tooth germs) on pediatric panoramic radiographs.  \nDesign: Eighty-seven pediatric panoramic radiographs from an open-source data set were analyzed. Two pediatric dentists annotated the presence or absence of each potential tooth position. Each image was processed five times by the LLMs using identical prompts, and the results were compared with the expert annotations. Standard performance metrics and Fleiss' kappa were calculated. Results: Detailed examination revealed that subtle developmental stages and minor tooth loss were consistently misidentified. Claude 3.5 Sonnet had higher sensitivity but significantly lower specificity (29.8% ± 21.5%), resulting in many false positives. OpenAI o1 demonstrated superior specificity compared to Claude 3.5 Sonnet, but still failed to correctly detect subtle defects in certain mixed dentition cases. Both models showed large variability in repeated runs.  \nConclusion: Both LLMs failed to achieve clinically acceptable performance and cannot reliably identify nuanced discrepancies critical for pediatric dentistry. Further refinements and consistency improvements are essential before routine clinical use.  \n1 | Introduction  \nDental radiography is one of the most important diagnostic tools in the dental practice [1]. Pediatric patients are no exception, and panoramic radiographs play a pivotal role in the comprehensive evaluation of tooth eruption, bone structure, and jaw development [2]. Early identification of caries risk, malocclusion, and other developmental anomalies is critical in the growing child, as delayed  \ndetection or misinterpretation can lead to missed opportunities for timely intervention [3]. However, panoramic radiographs of children are subject to many anatomical variations and individual differences due to the developmental process, and accurate reading of these images requires specialized knowledge and experience [4, 5].  \nIn recent years, the development of reading assistance technology using artificial intelligence (AI) has progressed, and its usefulness  \nThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is","cbCaigqtsHFJ6FXB","https://ap.wps.com/l/cbCaigqtsHFJ6FXB","pdf",1858735,"English","# Introduction\n## Background and motivation\n## Related work on AI and multimodal LLMs\n## Study evaluation approach (models, dataset, and annotation)","[{\"question\":\"Which multimodal LLMs were evaluated for interpreting pediatric panoramic radiographs?\",\"answer\":\"The study evaluated OpenAI o1 and Claude 3.5 Sonnet for detecting and counting teeth (including tooth germs).\"},{\"question\":\"How was the model performance assessed in the study?\",\"answer\":\"Eighty-seven pediatric panoramic radiographs from an open-source dataset were analyzed, with two pediatric dentists annotating each potential tooth position. The models processed each image five times with identical prompts, and performance metrics plus Fleiss’ kappa were calculated.\"},{\"question\":\"What were the key findings about limitations and reliability?\",\"answer\":\"Both models failed to achieve clinically acceptable performance, particularly for subtle developmental stages and minor tooth loss. Claude 3.5 Sonnet produced many false positives due to low specificity, OpenAI o1 showed better specificity but still missed subtle defects in mixed dentition cases, and both models varied substantially across repeated runs.\"}]","Challenges and Limitations of Multimodal Large Language Models in Interpreting Pediatric Panoramic Radiographs | PDF",1790758954,18,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/10e3f41340c58adab0e275845931cfc6.webp",983,1291,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/e68bac5a4d48ff87d99677aed2329ebc.webp",982,1290,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/42b093c2b00aa554dd97e81e250a17be.webp",981,1289,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/318a760eddfdd86a19b6143edb827cc6.webp",980,1287]