{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T12:54:27Z","timestamp":1770987267241,"version":"3.50.1"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T00:00:00Z","timestamp":1754870400000},"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><jats:title>Background<\/jats:title><jats:p>Parathyroid carcinoma (PC) and atypical parathyroid tumors (APT), constituting rare endocrine malignancies, demonstrate overlapping clinical-radiological presentations with benign adenomas. This study aimed to investigate the predictive performance of three radiomics-based machine learning models for the identification of PC\/APT from solitary parathyroid lesions using ultrasound.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This retrospective diagnostic study analyzed 913 surgically-confirmed parathyroid neoplasms (mean age 54.2 \u00b1 13.7 years; 694 females, 219 male) from Nanjing Drum Tower Hospital (n = 730) and Jinling Hospital (n = 183). The cohort comprised 90 malignant lesions and 823 benign adenomas, divided into training (Hospital I) and external test cohort (Hospital II). A radiomic signature derived from 544 quantitative ultrasound features was developed using three machine learning classifiers: Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR). The performance of the predictive models was evaluated based on the pathological diagnosis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The RF-based radiomics model showed excellent diagnostic performance. The AUC of this model (0.933) was higher than that of SVM (0.900, <jats:italic>P<\/jats:italic> &amp;lt; 0.05) and LR (0.901, <jats:italic>P<\/jats:italic> &amp;lt; 0.05). The accuracy, precision, recall, and F1-score of RF model in distinguishing PA from APT\/PC were 0.940, 0.683, 0.638 and 0.660. The explainable bar chart, heatmap and Shapley Additive exPlanations (SHAP) values were used to explain and visualize the main predictors of the optimal model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>This radiomics framework provides a promising tool to support doctors in the clinical management of parathyroid lesions.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fendo.2025.1617032","type":"journal-article","created":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T04:10:59Z","timestamp":1754885459000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["An explainable radiomics-based machine learning model for preoperative differentiation of parathyroid carcinoma and atypical tumors on ultrasound: a retrospective diagnostic study"],"prefix":"10.3389","volume":"16","author":[{"given":"Chunrui","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baojie","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyan","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yidan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuping","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinxia","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1624","DOI":"10.1001\/jama.2022.18331","article-title":"Hypercalcemia: A review","volume":"328","author":"Walker","year":"2022","journal-title":"JAMA"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-015-4901-9","article-title":"The incidence and survival of rare cancers of the thyroid, parathyroid, adrenal, and pancreas","volume":"23","author":"James","year":"2016","journal-title":"Ann Surg Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctrv.2020.102012","article-title":"Parathyroid cancer: an update","volume":"86","author":"Rodrigo","year":"2020","journal-title":"Cancer Treat Rev"},{"key":"B4","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/s12022-022-09709-1","article-title":"Overview of the 2022 WHO classification of parathyroid tumors","volume":"33","author":"Erickson","year":"2022","journal-title":"Endocr Pathol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1097\/PAP.0000000000000379","article-title":"Advances and updates in parathyroid pathology","volume":"30","author":"Gokozan","year":"2023","journal-title":"Adv Anat Pathol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2023.1027598","article-title":"Clinical and genetic analysis of atypical parathyroid adenoma compared with parathyroid carcinoma and benign lesions in a Chinese cohort","volume":"14","author":"Chen","year":"2023","journal-title":"Front Endocrinol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2020.557050","article-title":"Prevalence of parathyroid carcinoma and atypical parathyroid neoplasms in 153 patients with multiple endocrine neoplasia type 1: Case series and literature review","volume":"11","author":"Song","year":"2020","journal-title":"Front Endocrinol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15051405","article-title":"Novel PRUNE2 germline mutations in aggressive and benign parathyroid neoplasms","volume":"15","author":"Storvall","year":"2023","journal-title":"Cancers"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1530\/ERC-19-0135","article-title":"Atypical parathyroid adenomas: challenging lesions in the differential diagnosis of endocrine tumors","volume":"26","author":"Cetani","year":"2019","journal-title":"Endocr Relat Cancer"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-022-00503-0","article-title":"Shear wave elastography for differentiating parathyroid neoplasms with Malignant diagnosis or uncertain Malignant potential from parathyroid adenomas: initial experience","volume":"22","author":"Liu","year":"2022","journal-title":"Cancer Imaging"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1535089","article-title":"The impact of management traps on surgical strategies in parathyroid benign and Malignant tumors-related PHPT: A retrospective cohort study","volume":"15","author":"Zhu","year":"2025","journal-title":"Front Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1111\/cen.14807","article-title":"Early diagnosis of parathyroid carcinoma: A challenging for physicians","volume":"98","author":"Campenn\u00ec","year":"2023","journal-title":"Clin Endocrinol (Oxf)"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1038\/nrendo.2012.102","article-title":"Diagnosis and management of parathyroid cancer","volume":"8","author":"Schulte","year":"2012","journal-title":"Nat Rev Endocrinol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-019-02069-7","article-title":"Ultrasound combined with biochemical parameters can predict parathyroid carcinoma in patients with primary hyperparathyroidism","volume":"66","author":"Liu","year":"2019","journal-title":"Endocrine"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2025.1538361","article-title":"A retrospective study on a nomogram combining clinical and ultrasound parameters for differentiating solitary parathyroid adenoma from carcinoma or atypical tumors","volume":"16","author":"Liu","year":"2025","journal-title":"Front Endocrinol"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-016-1116-1","article-title":"Multiparametric ultrasonography and ultrasound elastographyin the differentiation of parathyroid lesions from ectopicthyroid lesions or lymphadenopathies","volume":"57","author":"Isidori","year":"2017","journal-title":"Endocrine"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3330578","article-title":"Hybrid QUS radiomics: A multimodal-integrated quantitative ultrasound radiomics for assessing ambulatory function in duchenne muscular dystrophy","volume":"28","author":"Yan","year":"2024","journal-title":"IEEE J BioMed Health Inform"},{"key":"B18","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1038\/s41523-024-00628-4","article-title":"Deep learning radiomics based prediction of axillary lymph node metastasis in breast cancer","volume":"10","author":"Liu","year":"2024","journal-title":"NPJ Breast Cancer"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2023.3269776","article-title":"Radiomics and deep learning in nasopharyngeal carcinoma: A review","volume":"17","author":"Wang","year":"2024","journal-title":"IEEE Rev BioMed Eng"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.241795","article-title":"Combining AI and radiomics to improve the accuracy of breast US","volume":"312","author":"Bahl","year":"2024","journal-title":"Radiology"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2024.05.026","article-title":"Development and validation of an explainable machine learning model for identification of hyper-functioning parathyroid glands from high-frequency ultrasonographic images","volume":"50","author":"Zhou","year":"2024","journal-title":"Ultrasound Med Biol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpi.2022.100134","article-title":"Mathematical model for preoperative differential diagnosis for the parathyroid neoplasms","volume":"13","author":"Krupinova","year":"2022","journal-title":"J Pathol Inform"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-59226-8_26","article-title":"BUSAT: A MATLAB toolbox for breast ultrasound image analysis","volume-title":"Pattern recognition","author":"Rodr\u00edguez-Cristerna","year":"2017"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3136503","article-title":"DeepSMOTE: fusing deep learning and SMOTE for imbalanced data","volume":"34","author":"Dablain","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"B25","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"B26","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.compmedimag.2015.08.002","article-title":"Machine learning approaches to analyze histological images of tissues from radical prostatectomies","volume":"46","author":"Gertych","year":"2015","journal-title":"Comput Med Imaging Graph"},{"key":"B27","first-page":"3235","article-title":"Parathyroid adenoma subtype decoding by using SPECT radiomic features and machine learning algorithms","volume":"63","author":"Valavi","year":"2022","journal-title":"J Nucl Med"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-024-11159-8","article-title":"Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism","volume":"35","author":"Yeh","year":"2025","journal-title":"Eur Radiol"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1617032\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T04:11:00Z","timestamp":1754885460000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1617032\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,11]]},"references-count":28,"alternative-id":["10.3389\/fendo.2025.1617032"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1617032","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,11]]},"article-number":"1617032"}}