{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T10:11:44Z","timestamp":1790071904390,"version":"4.0.1"},"reference-count":47,"publisher":"MDPI AG","issue":"9","license":[{"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":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Ovarian cancer (OC) is the second most common gynecological malignancy and remains one of the leading causes of gynecological cancer-related mortality worldwide. A major clinical challenge is the lack of an accurate and widely applicable strategy for identifying patients at high risk of malignancy at an early stage. In this context, artificial intelligence (AI) has emerged as a promising tool to improve diagnostic performance. Among AI technologies, large language models (LLMs) have recently shown considerable potential in healthcare applications. In this study, we evaluated the diagnostic performance of ChatGPT (GPT-5) in classifying 300 adnexal masses as benign or malignant and compared its performance with that of the IOTA Simple Rules, the ADNEX model, and expert subjective assessment. We also assessed ChatGPT\u2019s ability to predict the most likely histological diagnosis for each lesion. All adnexal masses were described using the International Ovarian Tumor Analysis (IOTA) terminology, and histopathological examination served as the reference standard. Our findings showed that expert subjective assessment achieved the highest overall diagnostic performance for both benign\/malignant classification (accuracy 87.3%; 95% CI, 83.0\u201390.9%) and prediction of the presumed histological diagnosis. ChatGPT A and ChatGPT B reached a sensitivity of 72.3% and 73.5%, a specificity of 74.5% and 75.9%, a positive predictive value of 75.2% and 76.5%, and a negative predictive value of 71.5% and 72.8%, respectively (inconclusive responses counted as misclassifications), with an overall accuracy of 73.3% and 74.7%. After adequate validation, large language models might complement existing decision-support tools for less experienced examiners, without replacing expert evaluation. Their ease of use and reliance on standardized ultrasound descriptors make them accessible to ultrasonographers with varying levels of expertise.<\/jats:p>","DOI":"10.3390\/jimaging12090462","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T09:04:17Z","timestamp":1790067857000},"page":"462","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models Meet Gynecologic Ultrasound: Advancing the Characterization of ADNEXal Masses"],"prefix":"10.3390","volume":"12","author":[{"given":"Giulia","family":"Soccio","sequence":"first","affiliation":[{"name":"Department of Interdisciplinary Medicine (DIM), University of Bari \u201cAldo Moro\u201d, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"conceptualization","vocabulary":"credit"}]},{"given":"Stefania","family":"Di Napoli","sequence":"additional","affiliation":[{"name":"Department of Interdisciplinary Medicine (DIM), University of Bari \u201cAldo Moro\u201d, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7102-9108","authenticated-orcid":false,"given":"Paolo","family":"Trerotoli","sequence":"additional","affiliation":[{"name":"Department of Interdisciplinary Medicine (DIM), University of Bari \u201cAldo Moro\u201d, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4006-6421","authenticated-orcid":false,"given":"Vera","family":"Loizzi","sequence":"additional","affiliation":[{"name":"Gynecologic Oncology Unit, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d, 70124 Bari, Italy"},{"name":"Translational Biomedicine and Neuroscience Department (DiBraIn), University of Bari \u201cAldo Moro\u201d, Polyclinic of Bari, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Laura Grazia","family":"Zomp\u00ec","sequence":"additional","affiliation":[{"name":"Department of Interdisciplinary Medicine (DIM), University of Bari \u201cAldo Moro\u201d, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4672-5003","authenticated-orcid":false,"given":"Giuseppe","family":"Colonna","sequence":"additional","affiliation":[{"name":"Gynecologic Oncology Unit, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3902-4523","authenticated-orcid":false,"given":"Daniele","family":"La Forgia","sequence":"additional","affiliation":[{"name":"SSD Radiologia Senologia, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5745-372X","authenticated-orcid":false,"given":"Gennaro","family":"Cormio","sequence":"additional","affiliation":[{"name":"Gynecologic Oncology Unit, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d, 70124 Bari, Italy"},{"name":"Unit of Obstetrics and Gynecology, Department of Interdisciplinary Medicine (DIM), University of Bari \u201cAldo Moro\u201d, Polyclinic of Bari, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]},{"given":"Francesca","family":"Arezzo","sequence":"additional","affiliation":[{"name":"Gynecologic Oncology Unit, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"conceptualization","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"191","DOI":"10.6004\/jnccn.2021.0007","article-title":"Ovarian Cancer, Version 2.2020, NCCN Clinical Practice Guidelines in Oncology","volume":"19","author":"Armstrong","year":"2021","journal-title":"J. Natl. Compr. Cancer Netw."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.bpobgyn.2016.08.006","article-title":"Epidemiology of epithelial ovarian cancer","volume":"41","author":"Webb","year":"2017","journal-title":"Best Pract. Res. Clin. Obstet. Gynaecol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1046\/j.1469-0705.1999.13010011.x","article-title":"Subjective assessment of adnexal masses with the use of ultrasonograpgy: An analysis of interobserver variability and experience","volume":"13","author":"Timmerman","year":"1999","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1046\/j.1469-0705.2000.00287.x","article-title":"Terms, definitions and measurement to describe the sonographic features of adnexal tumors: A con-sensus opinion from tha International Ovarian Tumor Analysis (IOTA) group","volume":"16","author":"Timmerman","year":"2000","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1002\/uog.5365","article-title":"Simple ultrasound-based rules for the diagnosis of ovarian cancer","volume":"31","author":"Timmerman","year":"2008","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_6","unstructured":"SIEOG (2017). Nuove Terminologie in Ecografia Ginecologica, Engineering and Physical Sciences Research Council."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.ejca.2016.01.007","article-title":"Subjective assessment versus ultrasound models to diagnose ovarian cancer: A systematic review and meta-analysis","volume":"58","author":"Meys","year":"2016","journal-title":"Eur. J. Cancer"},{"key":"ref_8","unstructured":"United Kingdom Engineering and Physical Sciences Research Council (2026, January 15). Artificial Intelligence Technologies. Available online: https:\/\/epsrc.ukri.org\/research\/ourportfolio\/researchareas\/."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1038\/s41746-018-0040-6","article-title":"Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices","volume":"1","author":"Abramoff","year":"2018","journal-title":"npj Digit. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1813","DOI":"10.1136\/gutjnl-2018-317500","article-title":"Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: A prospec-tive randomised controlled study","volume":"68","author":"Wang","year":"2019","journal-title":"Gut"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1148\/radiol.2018180921","article-title":"Automated Triaging of Adult Chest Radiographs with Deep Artificial Neural Networks","volume":"291","author":"Annarumma","year":"2019","journal-title":"Radiology"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1038\/s41591-018-0147-y","article-title":"Automated deep-neural-network surveillance of cranial images for acute neurologic events","volume":"24","author":"Titano","year":"2018","journal-title":"Nat. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","article-title":"A comparison of deep learning performance against health-care professionals in detecting diseases from med-ical imaging: A systematic review and meta-analysis","volume":"1","author":"Liu","year":"2019","journal-title":"Lancet Digit. Health"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1038\/s41569-019-0330-y","article-title":"The Apple Watch can detect atrial fibrillation: So what now?","volume":"17","author":"Marcus","year":"2020","journal-title":"Nat. Rev. Cardiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1038\/s42256-019-0122-4","article-title":"Prediction of drug combination effects with a minimal set of experiments","volume":"1","author":"Ianevski","year":"2019","journal-title":"Nat. Mach. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2113","DOI":"10.1093\/bioinformatics\/btz870","article-title":"Protein Docking Model Evaluation by 3D Deep Convolutional Neural Networks","volume":"36","author":"Wang","year":"2020","journal-title":"Bioinformatics"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e1918377","DOI":"10.1001\/jamanetworkopen.2019.18377","article-title":"Use of Machine Learning for Predicting Escitalopram Treatment Outcome from Electroencephalography Recordings in Adult Patients with Depression","volume":"3","author":"Zhdanov","year":"2020","journal-title":"JAMA Netw. Open"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1148\/radiol.2019190613","article-title":"A roadmap for foundational research on artificial intelligence in medical imaging: From the 2018 NIH\/RSNA\/ACR\/The Academy Workshop","volume":"291","author":"Langlotz","year":"2019","journal-title":"Radiology"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e1917221","DOI":"10.1001\/jamanetworkopen.2019.17221","article-title":"Development and Validation of a Machine Learning Model to Aid Discharge Processes for Inpatient Sur-gical Care","volume":"2","author":"Safavi","year":"2019","journal-title":"JAMA Netw. Open"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1148\/radiol.2019192527","article-title":"Moving Artificial Intelligence from Feasible to Real: Time to Drill for Gas and Build Roads","volume":"294","author":"Chang","year":"2020","journal-title":"Radiology"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1148\/radiol.2019191293","article-title":"Chest Radiograph Interpretation with Deep Learning Models: Assessment with Radiolo-gist-adjudicated Reference Standards and Population-adjusted Evaluation","volume":"294","author":"Majkowska","year":"2020","journal-title":"Radiology"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1046\/j.1469-0705.1999.13010017.x","article-title":"Artificial neural network models for the preoperative discrimination between malignant and benign adnexal masses","volume":"13","author":"Timmerman","year":"1999","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"543","DOI":"10.7785\/tcrt.2012.500272","article-title":"Ovarian tumor characterization using 3D ultrasound","volume":"11","author":"Acharya","year":"2012","journal-title":"Technol. Cancer Res. Treat."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1016\/j.ultrasmedbio.2015.11.014","article-title":"Ultrasound Image Discrimination between Benign and Malignant ADNEXal Masses Based on a Neural Network Approach","volume":"42","author":"Cabeza","year":"2016","journal-title":"Ultrasound Med. Biol."},{"key":"ref_25","unstructured":"Sheskin, D.J. (2011). Handbook of Parametric and Non-Parametric Statistical Procedures, Chapman & Hall\/CRC. [5th ed.]."},{"key":"ref_26","first-page":"7","article-title":"Cancer statistics, 2020","volume":"70","author":"Siegel","year":"2020","journal-title":"CA Cancer J. Clin."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1159\/000447743","article-title":"Neoadjuvant Chemotherapy in Advanced Ovarian Cancer: A Single-Institution Experience and a Review of the Literature","volume":"91","author":"Loizzi","year":"2016","journal-title":"Oncology"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Arezzo, F., Loizzi, V., La Forgia, D., Moschetta, M., Tagliafico, A.S., Cataldo, V., Kawosha, A.A., Venerito, V., Cazzato, G., and Ingravallo, G. (2021). Radiomics Analysis in ovarian cancer: A narrative review. Appl. Sci., 11.","DOI":"10.3390\/app11177833"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1080\/0284186X.2017.1350285","article-title":"Feature selection methodology for longitudinal cone-beam CT radiomics","volume":"56","author":"Leijenaar","year":"2017","journal-title":"Acta Oncol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1007\/s11739-020-02583-x","article-title":"A convolutional neural network with transfer learning for automatic discrimination between low and high-grade synovitis: A pilot study","volume":"16","author":"Venerito","year":"2021","journal-title":"Intern. Emerg. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e334","DOI":"10.1097\/RHU.0000000000001720","article-title":"A machine learning approach for predicting sustained remission in rheumatoid arthritis patients on bio-logic agents","volume":"28","author":"Venerito","year":"2021","journal-title":"JCR J. Clin. Rheumatol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2143","DOI":"10.1007\/s00404-022-06578-1","article-title":"A machine learning approach applied to gynaecological ultrasound to predict progression-free survival in ovarian cancer patients","volume":"306","author":"Arezzo","year":"2022","journal-title":"Arch. Gynecol. Obstet."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e004367","DOI":"10.1136\/rmdopen-2024-004367","article-title":"Large language model-driven sentiment analysis for facilitating fibromyalgia diagnosis","volume":"10","author":"Venerito","year":"2024","journal-title":"RMD Open"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"e574","DOI":"10.1016\/S2665-9913(23)00216-3","article-title":"Large language models and rheumatology: A comparative evaluation","volume":"5","author":"Venerito","year":"2023","journal-title":"Lancet Rheumatol."},{"key":"ref_35","unstructured":"World Health Organization (2024). Ethics and Governance of Artificial Intelligence for Health. Guidance on Large Multi-Modal Models, World Health Organization."},{"key":"ref_36","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_37","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1016\/j.ajic.2024.03.016","article-title":"Utilizing natural language processing and large language models in the diagnosis and prediction of infectious diseases: A systematic review","volume":"52","author":"Omar","year":"2024","journal-title":"Am. J. Infect. Control"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1111\/apt.18058","article-title":"Systematic review: The use of large language models as medical chatbots in digestive diseases","volume":"60","author":"Kresevic","year":"2024","journal-title":"Aliment. Pharmacol. Ther."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2796","DOI":"10.3390\/curroncol31050212","article-title":"The Consistency and Quality of ChatGPT responses Compared to Clinical Guidelines for Ovarian Cancer: A Delphi Approach","volume":"31","author":"Piazza","year":"2024","journal-title":"Curr. Oncol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10916-023-01925-4","article-title":"Evaluating the Feasibility of ChatGPT in healthCare: An analysis of multiple clinical and research sce-narios","volume":"47","author":"Cascella","year":"2023","journal-title":"J. Med. Syst."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.ejogrb.2025.01.007","article-title":"The role of artificial intelligence in gynecologic and obstetric emergencies","volume":"306","author":"Psilopatis","year":"2025","journal-title":"Eur. J. Obstet. Gynecol. Reprod. Biol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"21133","DOI":"10.1038\/s41598-025-08424-1","article-title":"Comparative analysis of ChatGPT 3.5 and ChatGPT 4 obstetric and gynecological knowledge","volume":"15","author":"Ludwin","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"e179","DOI":"10.1016\/S2589-7500(21)00278-8","article-title":"Deep learning-enabled pelvic ultrasound images for accurate diagnosis of ovarian cancer in China: A retrospective, multicentre, diagnostic study","volume":"4","author":"Gao","year":"2022","journal-title":"Lancet Digit. Health"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1832","DOI":"10.1002\/ijc.35092","article-title":"Role of artificial intelligence applied to ultrasound in gynecology oncology: A systematic review","volume":"155","author":"Moro","year":"2024","journal-title":"Int. J. Cancer"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1007\/s40477-020-00503-5","article-title":"The Adoption of Radiomics and machine learning improves the diagnostic processes of women with Ovarian MAsses (the AROMA pilot study)","volume":"24","author":"Chiappa","year":"2021","journal-title":"J. Ultrasound"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"e544","DOI":"10.3399\/BJGP.2025.0366","article-title":"Using large language models to identify prediagnostic clinical features of ovarian cancer from healthcare records: A population-based case-control study","volume":"76","author":"Funston","year":"2026","journal-title":"Br. J. Gen. Pract."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"5251","DOI":"10.1007\/s00261-026-05498-x","article-title":"Transforming adnexal mass assessment: How large language model improve ovarian-adnexal reporting and data system interpretation and sonographer performance","volume":"51","author":"Sun","year":"2026","journal-title":"Abdom. Radiol."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/462\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T09:53:38Z","timestamp":1790070818000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":47,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["jimaging12090462"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12090462","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]}}}