{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T06:26:57Z","timestamp":1786688817832,"version":"build-2736575974"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate an interpretable multimodal machine learning model that integrates transvaginal ultrasound (TVUS) deep learning features with clinical risk factors for differentiating benign from malignant endometrial thickening in postmenopausal women, with the aim of reducing unnecessary invasive procedures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective single-centre diagnostic study, 601 postmenopausal women with histopathologically confirmed endometrial thickening (509 benign, 92 malignant) were identified consecutively and allocated to a training set (n = 420) and a stratified held-out test set (n = 181) at a 7:3 ratio. Deep learning features were extracted from manually segmented mid-sagittal TVUS images via four pretrained ResNet architectures and compressed into a single imaging score (DL_score) through sequential mRMR filtering and LASSO regression. Independent clinical predictors were identified by multivariate logistic regression. Ten fusion classifiers were trained on the combined feature set and evaluated by AUC, calibration, decision curve analysis, and SHAP-based interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the test set, all image-based models outperformed the clinical-only model (AUC, 0.797; 95% CI, 0.707\u20130.888), with ResNet152 achieving the highest single-modality AUC (0.850; 95% CI, 0.782\u20130.917). Among the combined models, logistic regression (LR) performed best, with an AUC of 0.906 (95% CI, 0.842\u20130.970), an accuracy of 84.6%, a sensitivity of 75.9%, and a specificity of 92.1%. The LR model was well calibrated (Brier score, 0.08; Hosmer\u2013Lemeshow P\u00a0=\u00a00.60) and, on DCA, provided the greatest net benefit across the clinically relevant range of threshold probabilities. SHAP analysis identified the DL_score, postmenopausal bleeding, and BMI as the three most influential predictors; Grad-CAM activation maps indicated that the DL_score captured spatially localised information related to endometrial bulk and junction integrity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The combined image\u2013clinical logistic regression model demonstrated promising discriminatory and calibration performance for risk stratification of postmenopausal endometrial thickening, achieving improved specificity over conventional thickness-based criteria. This interpretable multimodal approach may serve as a useful adjunct to support clinical decision-making in identifying postmenopausal women at lower risk of malignancy, potentially reducing the burden of unnecessary invasive procedures.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1914063","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T05:32:05Z","timestamp":1786685525000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An interpretable multimodal machine learning model integrating transvaginal ultrasound and clinical features for differentiating benign from malignant endometrial thickening in postmenopausal women"],"prefix":"10.3389","volume":"16","author":[{"given":"Ling","family":"Li","sequence":"first","affiliation":[{"name":"Department of Ultrasound, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynaecology, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhai","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynaecology, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zexing","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yating","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynaecology, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyu","family":"Ge","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Beijing Chao-yang Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(22)01438-6","article-title":"The global burden of cancer attributable to risk factors, 2010\u20132019: a systematic analysis for the Global Burden of Disease Study 2019","volume":"400","year":"2022","journal-title":"Lancet"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1001\/jamainternmed.2018.2820","article-title":"Association of endometrial cancer risk with postmenopausal bleeding in women: a systematic review and meta-analysis","volume":"178","author":"Clarke","year":"2018","journal-title":"JAMA Intern Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1136\/ijgc-2020-002230","article-title":"ESGO\/ESTRO\/ESP guidelines for the management of patients with endometrial carcinoma","volume":"31","author":"Concin","year":"2021","journal-title":"Int J Gynecol Cancer"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1111\/1471-0528.13342","article-title":"Reappraisal of endometrial thickness for the detection of endometrial cancer in postmenopausal bleeding: a retrospective cohort study","volume":"123","author":"Wong","year":"2016","journal-title":"BJOG"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1002\/uog.7487","article-title":"Terms, definitions and measurements to describe the sonographic features of the endometrium and uterine cavity: a consensus opinion from the International Endometrial Tumor Analysis (IETA) group","volume":"35","author":"Leone","year":"2010","journal-title":"Ultrasound Obstet Gynecol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1002\/uog.18957","article-title":"Interobserver reliability of ultrasound characteristics of the endometrium in women with postmenopausal bleeding","volume":"52","author":"Green","year":"2018","journal-title":"Ultrasound Obstet Gynecol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: extracting more information from medical images using advanced feature analysis","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur J Cancer"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B10","doi-asserted-by":"publisher","first-page":"17843","DOI":"10.1038\/s41598-019-54434-1","article-title":"Diagnosis of thyroid nodules: performance of a deep learning convolutional neural network model vs. radiologists","volume":"9","author":"Park","year":"2019","journal-title":"Sci Rep"},{"key":"B11","doi-asserted-by":"publisher","first-page":"5645","DOI":"10.1038\/s41467-021-26023-2","article-title":"Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams","volume":"12","author":"Shen","year":"2021","journal-title":"Nat Commun"},{"key":"B12","doi-asserted-by":"publisher","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":"B13","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial intelligence in radiology","volume":"18","author":"Hosny","year":"2018","journal-title":"Nat Rev Cancer"},{"key":"B14","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1186\/s12880-022-00808-3","article-title":"The efficacy of deep learning models in the diagnosis of endometrial cancer using MRI: a comparison with radiologists","volume":"22","author":"Urushibara","year":"2022","journal-title":"BMC Med Imaging"},{"key":"B15","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.mri.2021.10.024","article-title":"Radiomic machine learning for pretreatment assessment of prognostic risk factors for endometrial cancer and its effects on radiologists' decisions of deep myometrial invasion","volume":"85","author":"Otani","year":"2022","journal-title":"Magn Reson Imaging"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1016\/j.acra.2023.12.035","article-title":"A transvaginal ultrasound-based deep learning model for the noninvasive diagnosis of myometrial invasion in patients with endometrial cancer: comparison with radiologists","volume":"31","author":"Liu","year":"2024","journal-title":"Acad Radiol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2023.08.012","article-title":"Deep learning and radiomics in endometrial lesions: clinical application gaps and the need for interpretability","volume":"31","author":"Bi","year":"2024","journal-title":"Acad Radiol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"55","DOI":"10.7326\/M14-0697","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"162","author":"Collins","year":"2015","journal-title":"Ann Intern Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","article-title":"mice: multivariate imputation by chained equations in R","volume":"45","author":"van Buuren","year":"2011","journal-title":"J Stat Softw"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy","volume":"27","author":"Peng","year":"2005","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B22","doi-asserted-by":"crossref","first-page":"2623","DOI":"10.1145\/3292500.3330701","article-title":"Optuna: a next-generation hyperparameter optimization framework","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '19)","author":"Akiba","year":"2019"},{"key":"B23","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in Neural Information Processing Systems 30 (NeurIPS 2017)","author":"Lundberg","year":"2017"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3054390","article-title":"A review of deep learning in medical imaging: imaging traits, technology trends, case studies with progress highlights, and future promises","volume":"109","author":"Zhou","year":"2021","journal-title":"Proc IEEE"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102444","article-title":"Recent advances and clinical applications of deep learning in medical image analysis","volume":"79","author":"Chen","year":"2022","journal-title":"Med Image Anal"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1093\/humupd\/dmad004","article-title":"Angiogenesis in abnormal uterine bleeding: a narrative review","volume":"29","author":"Middelkoop","year":"2023","journal-title":"Hum Reprod Update"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD012513.pub2","article-title":"Interventions for weight loss in obesity to reduce endometrial cancer risk: a Cochrane systematic review","volume":"2","author":"Kitson","year":"2021","journal-title":"Cochrane Database Syst Rev"},{"key":"B28","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.maturitas.2019.01.011","article-title":"Identification of endometrial cancers and atypical hyperplasia: Development and validation of a simplified system for ultrasound scoring of endometrial pattern","volume":"123","author":"Dueholm","year":"2019","journal-title":"Maturitas"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1002\/uog.24805","article-title":"Developing and validating ultrasound-based radiomics models for predicting high-risk endometrial cancer","volume":"60","author":"Moro","year":"2022","journal-title":"Ultrasound Obstet Gynecol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1136\/ijgc-2024-005652","article-title":"Artificial intelligence model for enhancing the accuracy of transvaginal ultrasound in detecting endometrial cancer and endometrial atypical hyperplasia","volume":"34","author":"Capasso","year":"2024","journal-title":"Int J Gynecol Cancer"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1600242","article-title":"Integrating deep learning and clinical characteristics for early prediction of endometrial cancer using multimodal ultrasound imaging: a multicenter study","volume":"15","author":"Lin","year":"2025","journal-title":"Front Oncol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.31557\/APJCP.2023.24.2.693","article-title":"Endometrial thickness measurement as predictor of endometrial hyperplasia and cancer in perimenopausal uterine bleeding: cross-sectional study","volume":"24","author":"Thoprasert","year":"2023","journal-title":"Asian Pac J Cancer Prev"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1002\/uog.18739","article-title":"Ultrasound characteristics of endometrial cancer as defined by International Endometrial Tumor Analysis (IETA) consensus nomenclature","volume":"51","author":"Epstein","year":"2018","journal-title":"Ultrasound Obstet Gynecol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1002\/uog.21885","article-title":"Dynamic contrast-enhanced ultrasound improves diagnostic performance in endometrial cancer staging","volume":"56","author":"Green","year":"2020","journal-title":"Ultrasound Obstet Gynecol"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.26355\/eurrev_202401_35055","article-title":"The role of shear wave elastography in predicting endometrial cancer in patients presenting with abnormal uterine bleeding","volume":"28","author":"Guler","year":"2024","journal-title":"Eur Rev Med Pharmacol Sci"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1914063\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T05:32:07Z","timestamp":1786685527000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1914063\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":35,"alternative-id":["10.3389\/fonc.2026.1914063"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1914063","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]},"article-number":"1914063"}}