{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T09:38:45Z","timestamp":1793353125201,"version":"4.5.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Insights Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>MRI is used for staging head and neck cancer (HNC), but assigning T-\u00a0and N-category criteria requires specialised expertise, and so many institutions offer only descriptive MRI reports. This study assessed potentials of commercial large language models (LLMs) to stage oral cavity cancer (OCC) using descriptive MRI reports and compared their accuracy with human experts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>104 eligible MRI reports were processed by five commercial LLMs (ChatGPT5.4, ChatGPT5.0, ChatGPT4.1, Gemini3.1 and DeepSeekV3.2). T- and N-categories, and overall stage were extracted from outputs of the LLMs. MRI reports were also staged by two multidisciplinary team (MDT) members. Accuracies of the LLMs and MDT members for cancer staging were assessed against the reference staging standard and compared using the McNemar test.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The LLMs showed accuracy of 54.8\u201376.0% for T-categorisation, 63.5\u201388.5% for N-categorisation, and 53.8\u201380.8% for overall stage. Compared with DeepSeekV3.2, ChatGPT and Gemini3.1 showed significantly higher accuracy (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009\u2264\u20090.001), except for Gemini3.1 for T-categorisation (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.07). No differences in accuracy for staging between ChatGPT versions and between them and Gemini3.1 (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.08 to &gt; 0.99). MDT members showed accuracy of 74.0\u201376.9% for T-categorisation, 76.9\u201377.9% for N-categorisation and 68.3\u201371.2% for overall stage. The tested LLMs did not consistently outperform MDT members for staging.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Variable tested LLM performance in staging OCC from descriptive MRI reports suggested that they are not suitable as standalone staging tools. Additionally, Low MDT staging accuracy highlighted the need for structured reports that include clinical cancer staging to facilitate MDT assessment, thus potentially ensuring optimised disease management.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>\n                            <jats:bold>Question<\/jats:bold>\n                            Can commercial LLMs accurately assign cancer stage based on descriptive MRI reports to overcome the lack of specialised expertise in clinical practice?\n                          <\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>\n                            <jats:bold>Findings<\/jats:bold>\n                            Tested LLMs demonstrated variable performances, ranging 54.8\u201376.0% for T-categorisation, 63.5\u201388.5% for N-categorisation and 53.8\u201380.8% for overall stage, and failed to consistently outperform MDT members.\n                          <\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>\n                            <jats:bold>Critical relevance statement<\/jats:bold>\n                            Variable tested LLM performance in staging OCC from descriptive MRI reports suggested that they are not suitable as standalone staging tools. MDT members\u2019 low performances highlight that structured MRI reports with clinical cancer staging are needed to improve multidisciplinary assessment.\n                          <\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13244-026-02409-y","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:27:22Z","timestamp":1790011642000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Commercial large language models for oral cavity cancer staging using descriptive pre-treatment MRI reports: ready for standalone use in clinical practice?"],"prefix":"10.1186","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1155-4389","authenticated-orcid":false,"given":"Qi Yong Hemis","family":"Ai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hoi Ming","family":"Kwok","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Yi","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tracy T. S.","family":"Lau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuo Feng","family":"Hung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lun M.","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiffany Y.","family":"So","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ann D.","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ho Sang","family":"Leung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"2409_CR1","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.nic.2012.08.004","volume":"23","author":"AH Aiken","year":"2013","unstructured":"Aiken AH (2013) Pitfalls in the staging of cancer of oral cavity cancer. Neuroimaging Clin N Am 23:27\u201345","journal-title":"Neuroimaging Clin N Am"},{"key":"2409_CR2","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.3174\/ajnr.A4742","volume":"37","author":"B Ko","year":"2016","unstructured":"Ko B, Parvathaneni U, Hudgins PA, Anzai Y (2016) Do radiologists report the TNM staging in radiology reports for head and neck cancers? A national survey study. AJNR Am J Neuroradiol 37:1504\u20131509","journal-title":"AJNR Am J Neuroradiol"},{"key":"2409_CR3","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s12929-025-01131-z","volume":"32","author":"U Iqbal","year":"2025","unstructured":"Iqbal U, Tanweer A, Rahmanti AR, Greenfield D, Lee LT, Li YJ (2025) Impact of large language model (ChatGPT) in healthcare: an umbrella review and evidence synthesis. J Biomed Sci 32:45","journal-title":"J Biomed Sci"},{"key":"2409_CR4","doi-asserted-by":"publisher","DOI":"10.1259\/dmfr.20220335","volume":"52","author":"KF Hung","year":"2023","unstructured":"Hung KF, Yeung AWK, Bornstein MM, Schwendicke F (2023) Personalized dental medicine, artificial intelligence, and their relevance for dentomaxillofacial imaging. Dentomaxillofac Radiol 52:20220335","journal-title":"Dentomaxillofac Radiol"},{"key":"2409_CR5","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1038\/s41746-025-01818-5","volume":"8","author":"J Hao","year":"2025","unstructured":"Hao J, Nalley A, Yeung AWK et al (2025) Characteristics, licensing, and ethical considerations of openly accessible oral-maxillofacial imaging datasets: a systematic review. NPJ Digit Med 8:412","journal-title":"NPJ Digit Med"},{"key":"2409_CR6","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s13244-026-02236-1","volume":"17","author":"PS Suh","year":"2026","unstructured":"Suh PS, Jeong SY, Ueda D et al (2026) Insufficient reporting quality in large language model studies in the field of radiology. Insights Imaging 17:71","journal-title":"Insights Imaging"},{"key":"2409_CR7","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1093\/dmfr\/twaf060","volume":"54","author":"Z Liu","year":"2025","unstructured":"Liu Z, Nalley A, Hao J et al (2025) The performance of large language models in dentomaxillofacial radiology: a systematic review. Dentomaxillofac Radiol 54:613\u2013631","journal-title":"Dentomaxillofac Radiol"},{"key":"2409_CR8","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1007\/s11547-024-01915-7","volume":"129","author":"M Parillo","year":"2024","unstructured":"Parillo M, Vaccarino F, Beomonte Zobel B, Mallio CA (2024) ChatGPT and radiology report: potential applications and limitations. Radiol Med 129:1849\u20131863","journal-title":"Radiol Med"},{"key":"2409_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.radi.2025.102972","volume":"31","author":"L Federico","year":"2025","unstructured":"Federico L, Fusaro DD, Coppola GC, Gregori M, Durante S (2025) Application of ChatGPT 4.0 in radiological dose management: perceptions of radiographers with varying expertise. Radiography 31:102972","journal-title":"Radiography"},{"key":"2409_CR10","doi-asserted-by":"publisher","first-page":"1635","DOI":"10.3390\/diagnostics15131635","volume":"15","author":"LRM Lanzafame","year":"2025","unstructured":"Lanzafame LRM, Gulli C, Mazziotti S et al (2025) Chatbots in radiology: current applications, limitations and future directions of ChatGPT in medical imaging. Diagnostics (Basel) 15:1635","journal-title":"Diagnostics (Basel)"},{"key":"2409_CR11","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.jacr.2025.09.004","volume":"23","author":"V Patwardhan","year":"2026","unstructured":"Patwardhan V, Balchander D, Fussell D et al (2026) Leveraging large language models to enhance radiology report readability: a systematic review. J Am Coll Radiol 23:354\u2013361","journal-title":"J Am Coll Radiol"},{"key":"2409_CR12","doi-asserted-by":"publisher","DOI":"10.3389\/fradi.2024.1390774","volume":"4","author":"P Fervers","year":"2024","unstructured":"Fervers P, Hahnfeldt R, Kottlors J et al (2024) ChatGPT yields low accuracy in determining LI-RADS scores based on free-text and structured radiology reports in German language. Front Radiol 4:1390774","journal-title":"Front Radiol"},{"key":"2409_CR13","doi-asserted-by":"publisher","first-page":"2177","DOI":"10.1007\/s00234-024-03427-7","volume":"66","author":"J Kanzawa","year":"2024","unstructured":"Kanzawa J, Yasaka K, Fujita N, Fujiwara S, Abe O (2024) Automated classification of brain MRI reports using fine-tuned large language models. Neuroradiology 66:2177\u20132183","journal-title":"Neuroradiology"},{"key":"2409_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.106053","volume":"204","author":"D Spitzl","year":"2025","unstructured":"Spitzl D, Mergen M, Braren R, Endros L, Eiber M, Steinhelfer L (2025) LLM-powered breast cancer staging from PET\/CT reports: a comparative performance study. Int J Med Inform 204:106053","journal-title":"Int J Med Inform"},{"key":"2409_CR15","doi-asserted-by":"publisher","first-page":"1793","DOI":"10.1002\/jmri.70140","volume":"62","author":"Y Yang","year":"2025","unstructured":"Yang Y, Yang F, Xiao S et al (2025) Application of large language models in TN staging and treatment response evaluation for patients with nasopharyngeal carcinoma: a comparative performance analysis of ChatGPT-4o-Latest and DeepSeek-V3-0324. J Magn Reson Imaging 62:1793\u20131801","journal-title":"J Magn Reson Imaging"},{"key":"2409_CR16","volume":"17","author":"Y Asari","year":"2025","unstructured":"Asari Y, Kurokawa R, Hagiwara A et al (2025) Beyond reporting: Claude 3.7 Sonnet accurately classifies T stage and uncovers omitted anatomic invasion in nasopharyngeal carcinoma magnetic resonance imaging (MRI) reports. Cureus 17:e91209","journal-title":"Cureus"},{"key":"2409_CR17","doi-asserted-by":"publisher","first-page":"2474","DOI":"10.3390\/diagnostics15192474","volume":"15","author":"E Jo","year":"2025","unstructured":"Jo E, Noh TI, Joo HJ (2025) Large language model and knowledge graph-driven AJCC staging of prostate cancer using pathology reports. Diagnostics (Basel) 15:2474","journal-title":"Diagnostics (Basel)"},{"key":"2409_CR18","doi-asserted-by":"publisher","first-page":"e73605","DOI":"10.2196\/73605","volume":"13","author":"YJ Kang","year":"2025","unstructured":"Kang YJ, Lee H, Yi JP et al (2025) Large language model versus manual review for clinical data curation in breast cancer: retrospective comparative study. JMIR Med Inform 13:e73605","journal-title":"JMIR Med Inform"},{"key":"2409_CR19","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.251844","volume":"317","author":"P Prucker","year":"2025","unstructured":"Prucker P, Bressem KK, Peeken J et al (2025) A prospective controlled trial of large language model-based simplification of oncologic CT reports for patients with cancer. Radiology 317:e251844","journal-title":"Radiology"},{"key":"2409_CR20","doi-asserted-by":"publisher","first-page":"318","DOI":"10.4174\/astr.2025.109.5.318","volume":"109","author":"JS Kim","year":"2025","unstructured":"Kim JS, Baek SJ, Ryu HS et al (2025) Using large language models for clinical staging of colorectal cancer from imaging reports: a pilot study. Ann Surg Treat Res 109:318\u2013327","journal-title":"Ann Surg Treat Res"},{"key":"2409_CR21","volume":"17","author":"S Fujisawa","year":"2025","unstructured":"Fujisawa S, Kurokawa R, Hagiwara A et al (2025) Large language model-based automated tumor, node, metastasis staging and resectability assessment for pancreatic cancer in radiology reports with detection of incomplete documentation. Cureus 17:e96448","journal-title":"Cureus"},{"key":"2409_CR22","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-025-02092-3","volume":"26","author":"M Mergen","year":"2025","unstructured":"Mergen M, Spitzl D, Eiber M, Braren RF, Steinhelfer L (2025) LLM-powered TNM staging of neuroendocrine tumors from PET\/CT reports. BMC Med Imaging 26:50","journal-title":"BMC Med Imaging"},{"key":"2409_CR23","doi-asserted-by":"publisher","unstructured":"Gupta A, Adams LC, Rangarajan K (2026) CALM-RAD: calibrated GPT-4o confidence-based triage enables 96\u2013100% accuracy in automated TNM staging of head and neck cancer reports. J Imaging Inform Med. https:\/\/doi.org\/10.1007\/s10278-026-01904-4","DOI":"10.1007\/s10278-026-01904-4"},{"key":"2409_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-025-01157-4","volume":"9","author":"K Ishida","year":"2025","unstructured":"Ishida K, Murakami R, Yamanoi K et al (2025) Real-world application of large language models for automated TNM staging using unstructured gynecologic oncology reports. NPJ Precis Oncol 9:366","journal-title":"NPJ Precis Oncol"},{"key":"2409_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjoto.2025.104642","volume":"46","author":"TA Patel","year":"2025","unstructured":"Patel TA, Michaelson G, Morton Z et al (2025) Use of ChatGPT for patient education involving HPV-associated oropharyngeal cancer. Am J Otolaryngol 46:104642","journal-title":"Am J Otolaryngol"},{"key":"2409_CR26","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1111\/coa.14261","volume":"50","author":"P Boscolo-Rizzo","year":"2025","unstructured":"Boscolo-Rizzo P, Marcuzzo AV, Lazzarin C et al (2025) Quality of information provided by artificial intelligence chatbots surrounding the reconstructive surgery for head and neck cancer: a comparative analysis between ChatGPT4 and Claude2. Clin Otolaryngol 50:330\u2013335","journal-title":"Clin Otolaryngol"},{"key":"2409_CR27","doi-asserted-by":"publisher","first-page":"e224","DOI":"10.4317\/medoral.26824","volume":"30","author":"P Pradhan","year":"2025","unstructured":"Pradhan P (2025) Accuracy of ChatGPT 3.5, 4.0, 4o and Gemini in diagnosing oral potentially malignant lesions based on clinical case reports and image recognition. Med Oral Patol Oral Cir Bucal 30:e224\u2013e231","journal-title":"Med Oral Patol Oral Cir Bucal"},{"key":"2409_CR28","doi-asserted-by":"publisher","unstructured":"Chiesa-Estomba CM, Andueza-Guembe M, Maniaci A et al (2025) Accuracy of ChatGPT-4o in text and video analysis of laryngeal malignant and premalignant diseases. J Voice. https:\/\/doi.org\/10.1016\/j.jvoice.2025.03.006","DOI":"10.1016\/j.jvoice.2025.03.006"},{"key":"2409_CR29","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.1097\/JS9.0000000000002234","volume":"111","author":"B Liang","year":"2025","unstructured":"Liang B, Gao Y, Wang T, Zhang L, Wang Q (2025) Multimodal large language models address clinical queries in laryngeal cancer surgery: a comparative evaluation of image interpretation across different models. Int J Surg 111:2727\u20132730","journal-title":"Int J Surg"},{"key":"2409_CR30","doi-asserted-by":"publisher","first-page":"4815","DOI":"10.1007\/s00405-025-09524-4","volume":"282","author":"B Vural Camalan","year":"2025","unstructured":"Vural Camalan B, Doluoglu S, Taraf NH, Gunay MM, Ozlugedik S (2025) ChatGPT versus DeepSeek in head and neck cancer staging and treatment planning: guideline-based study. Eur Arch Otorhinolaryngol 282:4815\u20134824","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"2409_CR31","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1256459","volume":"13","author":"O Kuscu","year":"2023","unstructured":"Kuscu O, Pamuk AE, Sutay Suslu N, Hosal S (2023) Is ChatGPT accurate and reliable in answering questions regarding head and neck cancer? Front Oncol 13:1256459","journal-title":"Front Oncol"},{"key":"2409_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-024-02129-0","volume":"49","author":"Q Xu","year":"2025","unstructured":"Xu Q, Wang J, Chen X et al (2025) Assessing the efficacy of ChatGPT prompting strategies in enhancing thyroid cancer patient education: a prospective study. J Med Syst 49:11","journal-title":"J Med Syst"},{"key":"2409_CR33","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/s00784-025-06268-7","volume":"29","author":"N Grinberg","year":"2025","unstructured":"Grinberg N, Whitefield S, Kleinman S, Ianculovici C, Wasserman G, Peleg O (2025) Assessing the performance of an artificial intelligence based chatbot in the differential diagnosis of oral mucosal lesions: clinical validation study. Clin Oral Investig 29:188","journal-title":"Clin Oral Investig"},{"key":"2409_CR34","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1007\/s12020-024-04066-x","volume":"87","author":"Z Chen","year":"2025","unstructured":"Chen Z, Chambara N, Wu C et al (2025) Assessing the feasibility of ChatGPT-4o and Claude 3-Opus in thyroid nodule classification based on ultrasound images. Endocrine 87:1041\u20131049","journal-title":"Endocrine"},{"key":"2409_CR35","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-025-05619-w","volume":"25","author":"YT Xiong","year":"2025","unstructured":"Xiong YT, Liu HN, Zeng YM et al (2025) Exploring the capabilities of GenAI for oral cancer consultations in remote consultations. BMC Oral Health 25:269","journal-title":"BMC Oral Health"},{"key":"2409_CR36","first-page":"56","volume":"328","author":"E Watts","year":"2025","unstructured":"Watts E, Pournik O, Allington R et al (2025) Enhancing diagnostic precision: utilising a large language model to extract U scores from thyroid sonography reports. Stud Health Technol Inform 328:56\u201360","journal-title":"Stud Health Technol Inform"},{"key":"2409_CR37","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1080\/00016489.2025.2502563","volume":"145","author":"E Pamuk","year":"2025","unstructured":"Pamuk E, Bilen YE, Kulekci C, Kuscu O (2025) ChatGPT-4 vs. multi-disciplinary tumor board decisions for the therapeutic management of primary laryngeal cancer. Acta Otolaryngol 145:714\u2013719","journal-title":"Acta Otolaryngol"},{"key":"2409_CR38","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-85920-4","volume":"15","author":"B Schmidl","year":"2025","unstructured":"Schmidl B, Hutten T, Pigorsch S et al (2025) Artificial intelligence for image recognition in diagnosing oral and oropharyngeal cancer and leukoplakia. Sci Rep 15:3625","journal-title":"Sci Rep"},{"key":"2409_CR39","doi-asserted-by":"publisher","first-page":"918","DOI":"10.5534\/wjmh.240173","volume":"43","author":"LH Yuan","year":"2025","unstructured":"Yuan LH, Huang SW, Chou D, Tsai CY (2025) The in-depth comparative analysis of four large language AI models for risk assessment and information retrieval from multi-modality prostate cancer work-up reports. World J Mens Health 43:918\u2013933","journal-title":"World J Mens Health"},{"key":"2409_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110645","volume":"202","author":"S Ramadan","year":"2025","unstructured":"Ramadan S, Mutsaers A, Chen PC et al (2025) Evaluating ChatGPT\u2019s competency in radiation oncology: a comprehensive assessment across clinical scenarios. Radiother Oncol 202:110645","journal-title":"Radiother Oncol"},{"key":"2409_CR41","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41746-024-01079-8","volume":"7","author":"J Huang","year":"2024","unstructured":"Huang J, Yang DM, Rong R et al (2024) A critical assessment of using ChatGPT for extracting structured data from clinical notes. NPJ Digit Med 7:106","journal-title":"NPJ Digit Med"},{"key":"2409_CR42","doi-asserted-by":"crossref","unstructured":"Brierley JD, Gospodarowicz MK, Wittekind C (2016) TNM classification of malignant tumours, 8th edn. Wiley-Blackwell. Hoboken, New Jersey","DOI":"10.1002\/9780471420194.tnmc26.pub3"},{"key":"2409_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2020.104607","volume":"104","author":"DK Zanoni","year":"2020","unstructured":"Zanoni DK, Patel SG (2020) New AJCC: How does it impact oral cancers? Oral Oncol 104:104607","journal-title":"Oral Oncol"},{"key":"2409_CR44","unstructured":"Amin M, Edge S, Greene F et al (2017) American Joint Committee on Cancer staging manual, 8th edn. Springer. New York"},{"key":"2409_CR45","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.24.31696","volume":"223","author":"JE Lee","year":"2024","unstructured":"Lee JE, Park KS, Kim YH, Song HC, Park B, Jeong YJ (2024) Lung cancer staging using chest CT and FDG PET\/CT free-text reports: comparison among three ChatGPT large language models and six human readers of varying experience. AJR Am J Roentgenol 223:e2431696","journal-title":"AJR Am J Roentgenol"},{"key":"2409_CR46","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.241516","volume":"316","author":"PH Yi","year":"2025","unstructured":"Yi PH, Haver HL, Jeudy JJ et al (2025) Best practices for the safe use of large language models and other generative AI in radiology. Radiology 316:e241516","journal-title":"Radiology"},{"key":"2409_CR47","doi-asserted-by":"publisher","unstructured":"Hung KF, Wang F, Lu MY, Shi X, Bornstein MM, Ai QYH (2026) Current evidence of generative artificial intelligence specifically developed for dental and maxillofacial radiology (DMFR): a systematic review. Dentomaxillofac Radiol. https:\/\/doi.org\/10.1093\/dmfr\/twag024","DOI":"10.1093\/dmfr\/twag024"},{"key":"2409_CR48","doi-asserted-by":"publisher","first-page":"2315","DOI":"10.3390\/diagnostics15182315","volume":"15","author":"Z Liu","year":"2025","unstructured":"Liu Z, Ai QYH, Yeung AWK, Tanaka R, Nalley A, Hung KF (2025) Performance of a vision-language model in detecting common dental conditions on panoramic radiographs using different tooth numbering systems. Diagnostics (Basel) 15:2315","journal-title":"Diagnostics (Basel)"},{"key":"2409_CR49","doi-asserted-by":"publisher","first-page":"959","DOI":"10.3348\/kjr.2024.0392","volume":"25","author":"HK Jung","year":"2024","unstructured":"Jung HK, Kim K, Park JE, Kim N (2024) Image-based generative artificial intelligence in radiology: comprehensive updates. Korean J Radiol 25:959\u2013981","journal-title":"Korean J Radiol"},{"key":"2409_CR50","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.diii.2024.04.003","volume":"105","author":"P Keshavarz","year":"2024","unstructured":"Keshavarz P, Bagherieh S, Nabipoorashrafi SA et al (2024) ChatGPT in radiology: a systematic review of performance, pitfalls, and future perspectives. Diagn Interv Imaging 105:251\u2013265","journal-title":"Diagn Interv Imaging"}],"container-title":["Insights into Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-026-02409-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13244-026-02409-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-026-02409-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:27:26Z","timestamp":1790011646000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13244-026-02409-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2409"],"URL":"https:\/\/doi.org\/10.1186\/s13244-026-02409-y","relation":{},"ISSN":["1869-4101"],"issn-type":[{"value":"1869-4101","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]},"assertion":[{"value":"28 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 September 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Institutional Review Board (Joint Chinese University of Hong Kong and New Territories East Cluster Clinical Research Ethical Committee) approval was obtained (Ref. No. 2025.567). Written informed consent was waived by the Institutional Review Board.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Consent from the patients was obtained.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Qi Yong Hemis Ai is a member of the\n                      Insights into Imaging\n                      Editorial Board, and as such, they have not participated in the review or selection processes for this article. All remaining authors declare no potential conflict of interest.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"233"}}