{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T05:05:07Z","timestamp":1789362307363,"version":"build-2803163510"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Differentiating stage I endometrial carcinoma (EC) from atypical endometrial hyperplasia (AEH) before surgery is critical for guiding treatment decisions, yet current magnetic resonance imaging (MRI) assessment is limited by overlapping appearances and inter-observer variability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective, two-center study, 297 patients (153 stage I EC and 144 AEH) who underwent multiparametric MRI were included. Radiomics features were extracted from T2-weighted imaging with fat saturation (T2WI-FS), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) map, and contrast-enhanced T1-weighted imaging (CE-T1WI) sequences. Feature selections were performed using univariate filtering, correlation analysis, least absolute shrinkage and selection operator (LASSO) and multivariate stepwise regression. A Radiomics model, a Clin+Rad model, and a DenseNet121-derived deep-feature model were constructed and compared for differentiating stage I EC from AEH. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, decision curve analysis (DCA).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Seven radiomics features and eight deep-learning features were ultimately selected to construct the models. In the external validation cohort, the DenseNet121-derived deep-feature model achieved the numerically highest AUC of 0.854 (95% CI, 0.743-0.965), compared with 0.803 (95% CI, 0.673-0.933) for the Radiomics model and 0.773 (95% CI, 0.626-0.919) for the Clin+Rad model, although the pairwise differences in AUC were not statistically significant. In addition, the DenseNet121-derived model showed a relatively greater net clinical benefit at threshold probabilities of approximately 0.15-0.80. SHAP analysis indicated that several influential deep features were derived from ADC images, suggesting that ADC-derived features contributed substantially to the model predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The DenseNet121-derived model achieved the numerically highest AUC in the external validation cohort, although the pairwise differences were not statistically significant, indicating its potential as a non-invasive tool to support individualized decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1943943","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T04:37:54Z","timestamp":1789360674000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MRI-derived deep-feature model for differentiating stage I endometrial carcinoma from atypical endometrial hyperplasia: a two-center retrospective study"],"prefix":"10.3389","volume":"16","author":[{"given":"Danhong","family":"Chai","sequence":"first","affiliation":[{"name":"Radiology Department, Jinshan Hospital of Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fenghua","family":"Ma","sequence":"additional","affiliation":[{"name":"Obstetrics and Gynecology Hospital of Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Chen","sequence":"additional","affiliation":[{"name":"Radiology Department, Jinshan Hospital of Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yapei","family":"Zhong","sequence":"additional","affiliation":[{"name":"Radiology Department, Jinshan Hospital of Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guofu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Obstetrics and Gynecology Hospital of Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxia","family":"Qian","sequence":"additional","affiliation":[{"name":"Radiology Department, Shanghai Jiao Tong University School of Medicine Affiliated International Peace Maternal and Child Health Hospital","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinwei","family":"Qiang","sequence":"additional","affiliation":[{"name":"Radiology Department, Jinshan Hospital of Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.70090","article-title":"Global cancer statistics 2024: GLOBOCAN estimates of incidence and mortality worldwide for 34 cancers in 186 countries","volume":"76","author":"Sung","year":"2026","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ygyno.2021.01.036","article-title":"Variations in incidence and mortality rates of endometrial cancer at the global, regional, and national levels, 1990\u20132019","volume":"161","author":"Gu","year":"2021","journal-title":"Gynecol Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(22)00323-3","article-title":"Endometrial cancer","volume":"399","author":"Crosbie","year":"2022","journal-title":"Lancet"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.852746","article-title":"Machine learning for endometrial cancer prediction and prognostication","volume":"12","author":"Bhardwaj","year":"2022","journal-title":"Front Oncol"},{"key":"B5","volume-title":"WHO Classification of Tumours: Female Genital Tumours","author":"Herrington","year":"2020"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2008.02.015","article-title":"Can we rely on blind endometrial biopsy for detection of focal intrauterine pathology","volume":"199","author":"Svirsky","year":"2008","journal-title":"Am J Obstet Gynecol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.21650","article-title":"Concurrent endometrial carcinoma in women with a biopsy diagnosis of atypical endometrial hyperplasia: a Gynecologic Oncology Group study","volume":"106","author":"Trimble","year":"2006","journal-title":"Cancer"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1097\/PAS.0b013e31825dd4ff","article-title":"Clinical outcome of atypical endometrial hyperplasia diagnosed on an endometrial biopsy: institutional experience and review of literature","volume":"36","author":"Rakha","year":"2012","journal-title":"Am J Surg Pathol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.bpobgyn.2019.12.006","article-title":"Current and future approaches to screening for endometrial cancer","volume":"65","author":"Gentry-Maharaj","year":"2020","journal-title":"Best Pract Res Clin Obstet Gynaecol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s11912-016-0506-0","article-title":"What is the best preoperative imaging for endometrial cancer","volume":"18","author":"Haldorsen","year":"2016","journal-title":"Curr Oncol Rep"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1148\/radiographics.21.6.g01nv211409","article-title":"Imaging the endometrium: disease and normal variants","volume":"21","author":"Nalaboff","year":"2001","journal-title":"Radiographics"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2013.11.030","article-title":"Utility of conventional and diffusion-weighted MRI features in distinguishing benign from Malignant endometrial lesions","volume":"83","author":"Kierans","year":"2014","journal-title":"Eur J Radiol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.clinimag.2016.10.016","article-title":"Role of diffusion-weighted MRI in the differential diagnosis of endometrial cancer, polyp, hyperplasia, and physiological thickening","volume":"41","author":"Bakir","year":"2017","journal-title":"Clin Imaging"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-020-02660-x","article-title":"Deep learning model for classifying endometrial lesions","volume":"19","author":"Zhang","year":"2021","journal-title":"J Transl Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-005-2814-x","article-title":"Pathologies of the uterine endometrial cavity: usual and unusual manifestations and pitfalls on magnetic resonance imaging","volume":"15","author":"Takeuchi","year":"2005","journal-title":"Eur Radiol"},{"key":"B16","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":"B17","doi-asserted-by":"publisher","DOI":"10.1093\/noajnl\/vdaa092","article-title":"Deep learning for medical image analysis: a brief introduction","volume":"2","author":"Wiestler","year":"2021","journal-title":"Neuro-Oncol Adv"},{"key":"B18","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26534","article-title":"Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI","volume":"49","author":"Mazurowski","year":"2019","journal-title":"J Magn Reson Imaging"},{"key":"B20","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.cmpb.2018.01.011","article-title":"Deep convolutional neural networks for breast cancer screening","volume":"157","author":"Chougrad","year":"2018","journal-title":"Comput Methods Programs BioMed"},{"key":"B21","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1186\/s13014-023-02283-8","article-title":"Deep learning for segmentation of the cervical cancer gross tumor volume on magnetic resonance imaging for brachytherapy","volume":"18","author":"Rodr\u00edguez Outeiral","year":"2023","journal-title":"Radiat Oncol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1055\/a-0981-6133","article-title":"Automated classification of gastric neoplasms in endoscopic images using a convolutional neural network","volume":"51","author":"Cho","year":"2019","journal-title":"Endoscopy"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.887546","article-title":"Multimodal MRI-based radiomics-clinical model for preoperatively differentiating concurrent endometrial carcinoma from atypical endometrial hyperplasia","volume":"12","author":"Zhang","year":"2022","journal-title":"Front Oncol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0248526","article-title":"Automated system for diagnosing endometrial cancer by adopting deep-learning technology in hysteroscopy","volume":"16","author":"Takahashi","year":"2021","journal-title":"PLoS One"},{"key":"B25","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1186\/s13244-020-00887-2","article-title":"Radiomics in medical imaging-\"how-to\" guide and critical reflection","volume":"11","author":"van Timmeren","year":"2020","journal-title":"Insights Imaging"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1590","DOI":"10.1038\/s41598-023-28819-2","article-title":"Development of MRI-based radiomics predictive model for classifying endometrial lesions","volume":"13","author":"Liu","year":"2023","journal-title":"Sci Rep"},{"key":"B27","doi-asserted-by":"publisher","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":"B28","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3932943","article-title":"An MRI radiomics nomogram improves the accuracy in identifying eligible candidates for fertility-preserving treatment in endometrioid adenocarcinoma","volume":"12","author":"Yan","year":"2022","journal-title":"Am J Cancer Res"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1148\/rg.293085130","article-title":"Diffusion-weighted MR imaging of female pelvic tumors: a pictorial review","volume":"29","author":"Whittaker","year":"2009","journal-title":"Radiographics"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1177\/0284185115612249","article-title":"Endometrial cancer: correlation of apparent diffusion coefficient (ADC) with tumor cellularity and tumor grade","volume":"57","author":"Kishimoto","year":"2016","journal-title":"Acta Radiologica"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-007-0769-9","article-title":"Diagnostic accuracy of the apparent diffusion coefficient in differentiating benign from Malignant uterine endometrial cavity lesions: initial results","volume":"18","author":"Fujii","year":"2008","journal-title":"Eur Radiol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.20997","article-title":"Diffusion-weighted MR imaging of uterine endometrial cancer","volume":"26","author":"Tamai","year":"2007","journal-title":"J Magn Reson Imaging"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.10.5584","article-title":"Endometrial cancer: correlation of apparent diffusion coefficient with tumor grade, depth of myometrial invasion, and presence of lymph node metastases","volume":"197","author":"Rechichi","year":"2011","journal-title":"AJR Am J Roentgenol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14030325","article-title":"Can the ADC value be used as an imaging \"biopsy\" in endometrial cancer","volume":"14","author":"Petrila","year":"2024","journal-title":"Diagnostics (Basel)"},{"key":"B35","doi-asserted-by":"publisher","first-page":"4800","DOI":"10.1038\/s41598-019-41344-5","article-title":"Stability of radiomics features in apparent diffusion coefficient maps from a multi-centre test-retest trial","volume":"9","author":"Peerlings","year":"2019","journal-title":"Sci Rep"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.17752","article-title":"Correlation between apparent diffusion coefficient (ADC) and cellularity is different in several tumors: a meta-analysis","volume":"8","author":"Surov","year":"2017","journal-title":"Oncotarget"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2019.2944977","article-title":"Computer-aided diagnosis in histopathological images of the endometrium using a convolutional neural network and attention mechanisms","volume":"24","author":"Sun","year":"2020","journal-title":"IEEE J BioMed Health Inform"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1943943\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T04:38:04Z","timestamp":1789360684000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1943943\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"references-count":37,"alternative-id":["10.3389\/fonc.2026.1943943"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1943943","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]},"article-number":"1943943"}}