{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T14:58:07Z","timestamp":1792421887001,"version":"4.5.0"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"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. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Accurate evaluation of thyroid nodules is crucial for effective management; however, methods such as ultrasonography and Fine Needle Aspiration Cytology (FNAC) can be subjective and operator-dependent. Indeterminate thyroid nodules (ITNs) complicate diagnosis, coming at the expense of time, money, and potentially additional FNA samplings, causing more discomfort for the patients. Recent advancements in artificial intelligence (AI) assisted ultrasound diagnosis system have demonstrated excellent diagnostic performance and the potential to aid in the differentiation of ITNs. This study aims to develop an AI classifier that integrates the AI-assisted ultrasound diagnosis system, FNAC, and demographic data to enhance the differentiation of benign and malignant thyroid nodules, and to compare the diagnostic performance of the models, with a focus on diagnosing ITNs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>In the present research, 620 thyroid nodules were collected from a single medical center and divided into training and testing cohorts (Testing1). We developed five AI models using distinct classification algorithms (Logistic Regression, Support Vector Machine, K-Nearest Neighbor, Random Forest, and Gradient Boosting Machine) that integrate demographic data, cytological findings, and an AI-assisted ultrasound diagnostic system for thyroid nodule assessment. These models underwent prospective validation (Testing2, n = 243) to identify the optimal model. A subsequent prospective study (Testing3) involving 70 thyroid nodules further evaluated the model\u2019s performance, where the selected optimal model was compared against FNAC combined with BRAF V600E mutation analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>After validation with the Testing1 and Testing2 cohorts, the Random Forest (RF) model demonstrated the best overall performance among the five classifiers. The area under the curve (AUC) for the RF model to diagnose thyroid nodules was 0.994 in the training cohort, 0.993 in the testing cohort, and 0.977 in the prospective data. In addition, for 42 included ITNs in the prospective data, the accuracy, sensitivity, and specificity of the RF model were 90.48%, 89.47%, and 91.30%, respectively. In the Testing 3 cohort, the RF model demonstrated superior diagnostic performance compared to both the standalone AI ultrasound auxiliary diagnostic system and FNAC alone. Its accuracy was comparable to FNAC combined with BRAF V600E mutation analysis. Conclusion: Our developed thyroid nodule AI diagnostic model shows favorable predictive value. It can serve as a decision support tool for non-thyroid specialists and assist thyroid surgeons in the management of ITN.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our developed thyroid nodule AI diagnostic model shows favorable predictive value. It can serve as a decision support tool for non-thyroid specialists and assist thyroid surgeons in the management of ITN.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2025.1546983","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:14:33Z","timestamp":1747786473000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Intelligent diagnosis of thyroid nodules with AI ultrasound assistance and cytology classification"],"prefix":"10.3389","volume":"16","author":[{"given":"Xiaojuan","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinrong","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanbing","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weizhe","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA: Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.6004\/jnccn.2022.0040","article-title":"Thyroid carcinoma, version 2.2022, nccn clinical practice guidelines in oncology","volume":"20","author":"Haddad","year":"2022","journal-title":"J Natl Compr Cancer Netw"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2017.01.046","article-title":"Acr thyroid imaging, reporting and data system (ti-rads): white paper of the acr ti-rads committee","volume":"14","author":"Tessler","year":"2017","journal-title":"J Am Coll Radiol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jasc.2023.05.005","article-title":"The 2023 bethesda system for reporting thyroid cytopathology","volume":"12","author":"Ali","year":"2023","journal-title":"J Am Soc Cytopathol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2022.4989","article-title":"Diagnostic accuracy of fine-needle biopsy in the detection of thyroid Malignancy: a systematic review and meta-analysis","volume":"157","author":"Hsiao","year":"2022","journal-title":"JAMA Surg"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1530\/EJE-21-1293","article-title":"Diagnosis of endocrine disease: usefulness of genetic testing of fine-needle aspirations for diagnosis of thyroid cancer","volume":"187","author":"Stewardson","year":"2022","journal-title":"Eur J Endocrinol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-021-02693-2","article-title":"Real-life use of braf-v600e mutation analysis in thyroid nodule fine needle aspiration: consequences on clinical decision-making","volume":"73","author":"Brigante","year":"2021","journal-title":"Endocrine"},{"key":"B8","doi-asserted-by":"publisher","first-page":"17129","DOI":"10.1038\/s41598-023-44464-1","article-title":"Braf v600e genetic testing should be recommended for bethesda iii or v thyroid nodules based on fine-needle aspiration","volume":"13","author":"Lu","year":"2023","journal-title":"Sci Rep"},{"key":"B9","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.surg.2017.10.004","article-title":"Cost-effectiveness of lobectomy versus genetic testing (afirma\u00ae) for indeterminate thyroid nodules: Considering the costs of surveillance","volume":"163","author":"Balentine","year":"2018","journal-title":"Surgery"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2023.0132","article-title":"Artificial intelligence in thyroidology: a narrative review of the current applications, associated challenges, and future directions","volume":"33","author":"Toro-Tobon","year":"2023","journal-title":"Thyroid"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trecan.2019.02.002","article-title":"Rise of the machines: advances in deep learning for cancer diagnosis","volume":"5","author":"Levine","year":"2019","journal-title":"Trends Cancer"},{"key":"B12","doi-asserted-by":"publisher","first-page":"40","DOI":"10.4274\/dir.2022.211260","article-title":"Artificial intelligence in diagnostic ultrasonography","volume":"29","author":"Dicle","year":"2023","journal-title":"Diagn Intervent Radiol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"109717","DOI":"10.1016\/j.ejrad.2021.109717","article-title":"Artificial intelligence in ultrasound","volume":"139","author":"Shen","year":"2021","journal-title":"Eur J Radiol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1210\/clinem\/dgad503","article-title":"Artificial intelligence model assisting thyroid nodule diagnosis and management: a multicenter diagnostic study","volume":"109","author":"Ha","year":"2024","journal-title":"J Clin Endocrinol Metab"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.1018321","article-title":"Identification of benign and Malignant thyroid nodules based on dynamic ai ultrasound intelligent auxiliary diagnosis system","volume":"13","author":"Wang","year":"2022","journal-title":"Front Endocrinol"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-09378-y","article-title":"Clinical value of artificial intelligence in thyroid ultrasound: a prospective study from the real world","volume":"33","author":"Li","year":"2023","journal-title":"Eur Radiol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/s00405-022-07436-1","article-title":"A comparison of artificial intelligence versus radiologists in the diagnosis of thyroid nodules using ultrasonography: A systematic review and meta-analysis","volume":"279","author":"Potipimpanon","year":"2022","journal-title":"Eur Arch Oto-Rhino-Laryngol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e6564","DOI":"10.1097\/MD.0000000000006564","article-title":"Ultrasound is helpful to differentiate bethesda class iii thyroid nodules: A prisma-compliant systematic review and meta-analysis","volume":"96","author":"Gao","year":"2017","journal-title":"Medicine"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-10132-1","article-title":"Us of thyroid nodules: can ai-assisted diagnostic system compete with fine needle aspiration","volume":"34","author":"Zhou","year":"2024","journal-title":"Eur Radiol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.19538\/j.cjps.issn1005-2208.2018.03.01","article-title":"Expert consensus and operational guidelines for ultrasoundguided fine needle aspiration biopsy of thyroid nodules (2018 edition)","volume":"38","author":"Tian","year":"2018","journal-title":"Chin J Pract Surg"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2017.0500","article-title":"The 2017 bethesda system for reporting thyroid cytopathology","volume":"27","author":"Cibas","year":"2017","journal-title":"Thyroid"},{"key":"B22","volume-title":"WHO Classification of Tumours of Endocrine Organs","author":"Lloyd","year":"2017"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2019.0478","article-title":"Investigating the effect of thyroid nodule location on the risk of thyroid cancer","volume":"30","author":"Jasim","year":"2020","journal-title":"Thyroid"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-7687-1","volume-title":"Encyclopedia of machine learning and data mining","author":"Sammut","year":"2017"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-007-0114-2","article-title":"Top 10 algorithms in data mining","volume":"14","author":"Wu","year":"2008","journal-title":"Knowledge Inf Syst"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1992.10475879","article-title":"An introduction to kernel and nearest-neighbor nonparametric regression","volume":"46","author":"Altman","year":"1992","journal-title":"Am Stat"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann Stat"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.12126","article-title":"Discrimination and calibration of clinical prediction models: users\u2019 guides to the medical literature","volume":"318","author":"Alba","year":"2017","journal-title":"Jama"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1002\/cncy.v124.3","article-title":"Impact of reclassifying noninvasive follicular variant of papillary thyroid carcinoma on the risk of Malignancy in the bethesda system for reporting thyroid cytopathology","volume":"124","author":"Faquin","year":"2016","journal-title":"Cancer Cytopathol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1186\/s12916-024-03510-z","article-title":"The clinical value of artificial intelligence in assisting junior radiologists in thyroid ultrasound: a multicenter prospective study from real clinical practice","volume":"22","author":"Xu","year":"2024","journal-title":"BMC Med"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1546983\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:14:35Z","timestamp":1747786475000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1546983\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,21]]},"references-count":30,"alternative-id":["10.3389\/fendo.2025.1546983"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1546983","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,21]]},"article-number":"1546983"}}