{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:35:23Z","timestamp":1790703323733,"version":"4.1.0"},"reference-count":32,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>A subset of biopsy\u2010confirmed ductal carcinoma in\u00a0situ (DCIS) cases can be upstaged to invasive breast cancer at surgery. Preoperative identification of upstaging risk is essential for treatment planning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop clinical and breast MRI radiomics models to preoperatively predict upstaging in DCIS.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Study Type<\/jats:title>\n                    <jats:p>Retrospective and prospective.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Population<\/jats:title>\n                    <jats:p>\n                      Three hundred forty\u2010five women (median age, 59\u2009years [IQR, 49\u201367]) with 362 DCIS lesions diagnosed via core\u2010needle biopsy (training:\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009216, internal testing:\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200953, external testing:\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200993).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Field Strength\/Sequences<\/jats:title>\n                    <jats:p>1.5\u2009T 3D T1\u2010weighted spoiled gradient\u2010echo MRI: pre\u2010contrast non\u2010fat\u2010suppressed and dynamic contrast\u2010enhanced (DCE) fat\u2010suppressed sequences.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Assessments<\/jats:title>\n                    <jats:p>Clinical and radiomics features were extracted from radiologist\u2010segmented lesions on DCE breast MRI. Seven machine learning algorithms were evaluated across clinical\u2010only (demographic and clinicopathologic variables), radiomics\u2010only (whole\u2010lesion\/peritumoral), and combined models, using nested cross\u2010validation and internal and external testing. Feature importance was assessed using Shapley additive explanation (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Statistical Tests<\/jats:title>\n                    <jats:p>Mann\u2013Whitney, Chi\u2010square, DeLong tests; area under the receiver operating characteristic curve (AUC), sensitivity, negative predictive value (NPV).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The clinical model achieved AUC 0.70 (95% CI: 0.51\u20130.89), with 36% sensitivity and 84% NPV. A multilayer perceptron integrating clinical and peritumoral radiomics non\u2010significantly increased AUC to 0.75 (95% CI: 0.58\u20130.92; \u0394AUC\u2009=\u2009+0.05; False Discovery Rate\n                      <jats:italic>p\u2010<\/jats:italic>\n                      adj\u2009=\u20090.65), improving sensitivity to 82% (\u0394\u2009=\u2009+46%) and NPV to 92% (\u0394\u2009=\u2009+8%). On external testing, AUC was 0.63 (95% CI: 0.50\u20130.76) with no significant change over the clinical baseline (\u0394AUC\u2009=\u2009\u22120.03; FDR\n                      <jats:italic>p<\/jats:italic>\n                      \u2010adj\u2009=\u20090.857) but demonstrated superior sensitivity (68%; \u0394\u2009=\u2009+30%) and NPV (84%; \u0394\u2009=\u2009+3%). SHAP identified peritumoral center\u2010of\u2010mass shift as the dominant predictor.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Data Conclusion<\/jats:title>\n                    <jats:p>Clinical\u2010peritumoral modeling did not significantly improve discrimination over the clinical baseline but showed higher NPV and sensitivity, suggesting the tumor microenvironment may provide complementary information for upstaging risk stratification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence<\/jats:title>\n                    <jats:p>3.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Technical Efficacy<\/jats:title>\n                    <jats:p>Stage 2.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jmri.70552","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T07:23:51Z","timestamp":1790321031000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Preoperative Prediction of Ductal Carcinoma In\u00a0Situ Upstaging Using Machine Learning\u2010Based Peritumoral Breast\n                    <scp>MRI<\/scp>\n                    Radiomics"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0236-8469","authenticated-orcid":false,"given":"K. Ruwani M.","family":"Fernando","sequence":"first","affiliation":[{"name":"Department of Machine Learning H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6023-1132","authenticated-orcid":false,"given":"Issam","family":"El Naqa","sequence":"additional","affiliation":[{"name":"Department of Machine Learning H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmoud","family":"Abdalah","sequence":"additional","affiliation":[{"name":"Quantitative Imaging Core H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dana","family":"Ataya","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging and Interventional Radiology H. Lee Moffitt Cancer Center  Tampa Florida USA"},{"name":"Department of Oncologic Sciences University of South Florida  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marilyn M.","family":"Bui","sequence":"additional","affiliation":[{"name":"Department of Pathology H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4817-5002","authenticated-orcid":false,"given":"Jasmine R.","family":"Brainerd","sequence":"additional","affiliation":[{"name":"Non\u2010Therapeutic Research Operations H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7087-6546","authenticated-orcid":false,"given":"Yarelis","family":"De La Cruz","sequence":"additional","affiliation":[{"name":"Non\u2010Therapeutic Research Operations H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2296-3524","authenticated-orcid":false,"given":"Olya","family":"Stringfield","sequence":"additional","affiliation":[{"name":"Quantitative Imaging Core H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Czerniecki","sequence":"additional","affiliation":[{"name":"Department of Breast Oncology H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8893-7687","authenticated-orcid":false,"given":"Natarajan","family":"Raghunand","sequence":"additional","affiliation":[{"name":"Department of Oncologic Sciences University of South Florida  Tampa Florida USA"},{"name":"Department of Cancer Physiology H. Lee Moffitt Cancer Center  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lev","family":"Barinov","sequence":"additional","affiliation":[{"name":"Department of Radiology Hospital of the University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amber C.","family":"Simmons","sequence":"additional","affiliation":[{"name":"Department of Radiology Hospital of the University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7209-4216","authenticated-orcid":false,"given":"Elizabeth S.","family":"McDonald","sequence":"additional","affiliation":[{"name":"Department of Radiology Hospital of the University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bethany L.","family":"Niell","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging and Interventional Radiology H. Lee Moffitt Cancer Center  Tampa Florida USA"},{"name":"Department of Oncologic Sciences University of South Florida  Tampa Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"crossref","first-page":"1430","DOI":"10.1056\/NEJMra031301","article-title":"Ductal Carcinoma In\u00a0Situ of the Breast","volume":"350","author":"Burstein H. J.","year":"2004","journal-title":"New England Journal of Medicine"},{"key":"e_1_2_10_3_1","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1148\/radiol.213174","article-title":"Diffusion\u2010Weighted Breast MRI in Prediction of Upstaging in Women With Biopsy\u2010Proven Ductal Carcinoma In\u00a0Situ","volume":"305","author":"Lee S. A.","year":"2022","journal-title":"Radiology"},{"key":"e_1_2_10_4_1","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1148\/radiol.211839","article-title":"Ductal Carcinoma In\u00a0Situ: State\u2010Of\u2010The\u2010Art Review","volume":"302","author":"Grimm L. J.","year":"2022","journal-title":"Radiology"},{"key":"e_1_2_10_5_1","article-title":"Cancer Statistics, 2026","volume":"76","author":"Siegel R. L.","year":"2026","journal-title":"CA: A Cancer Journal for Clinicians"},{"key":"e_1_2_10_6_1","doi-asserted-by":"crossref","first-page":"e2330503","DOI":"10.2214\/AJR.23.30503","article-title":"Evolving Treatment Paradigms for Low\u2010Risk Ductal Carcinoma In\u00a0Situ: Imaging Needs","volume":"222","author":"Nguyen D. L.","year":"2024","journal-title":"American Journal of Roentgenology"},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1001\/archsurg.2010.243","article-title":"Risk Factors for Invasive Breast Cancer When Core Needle Biopsy Shows Ductal Carcinoma In\u00a0Situ","volume":"145","author":"Kurniawan E. D.","year":"2010","journal-title":"Archives of Surgery"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1016\/j.breast.2012.06.012","article-title":"Factors Associated With Upstaging From Ductal Carcinoma In\u00a0Situ Following Core Needle Biopsy to Invasive Cancer in Subsequent Surgical Excision","volume":"21","author":"Kim J.","year":"2012","journal-title":"Breast"},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","first-page":"67","DOI":"10.3892\/mco.2020.2036","article-title":"Predictors for Upstaging of Ductal Carcinoma In\u00a0Situ (DCIS) to Invasive Carcinoma in Non\u2010Mass\u2010Type DCIS","volume":"13","author":"Oda G.","year":"2020","journal-title":"Molecular and Clinical Oncology"},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1148\/radiol.2021204743","article-title":"Preoperative Breast MRI for Newly Diagnosed Ductal Carcinoma In\u00a0Situ: Imaging Features and Performance in a Multicenter Setting (ECOG\u2010ACRIN E4112 Trial)","volume":"301","author":"Chou S.\u2010H. S.","year":"2021","journal-title":"Radiology"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1148\/radiol.210407","article-title":"Prediction of Upstaging in Ductal Carcinoma In\u00a0Situ Based on Mammographic Radiomic Features","volume":"303","author":"Hou R.","year":"2022","journal-title":"Radiology"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1002\/jmri.25655","article-title":"Can Algorithmically Assessed MRI Features Predict Which Patients With a Preoperative Diagnosis of Ductal Carcinoma In\u00a0Situ are Upstaged to Invasive Breast Cancer?","volume":"46","author":"Harowicz M. R.","year":"2017","journal-title":"Journal of Magnetic Resonance Imaging"},{"key":"e_1_2_10_13_1","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1002\/jmri.28539","article-title":"Evaluating Upstaging in Ductal Carcinoma In\u00a0Situ Using Preoperative MRI\u2010Based Radiomics","volume":"58","author":"Hong M.","year":"2022","journal-title":"Journal of Magnetic Resonance Imaging"},{"key":"e_1_2_10_14_1","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1186\/s12880-020-00494-z","article-title":"The Role of MRI and Clinicopathologic Features in Predicting the Invasive Component of Biopsy\u2010Confirmed Ductal Carcinoma In\u00a0Situ","volume":"20","author":"Yoon G. Y.","year":"2020","journal-title":"BMC Medical Imaging"},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","DOI":"10.2463\/mrms.mp.2023-0168","article-title":"Predictive Performance of Radiomic Features Extracted From Breast MR Imaging in Postoperative Upgrading of Ductal Carcinoma In\u00a0Situ to Invasive Carcinoma","volume":"24","author":"Satake H.","year":"2025","journal-title":"Magnetic Resonance in Medical Sciences"},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1007\/s12282-021-01225-0","article-title":"Clinicopathological Predictors of Postoperative Upstaging to Invasive Ductal Carcinoma (IDC) in Patients Preoperatively Diagnosed With Ductal Carcinoma in Situ (DCIS): A Multi\u2010Institutional Retrospective Cohort Study","volume":"28","author":"Tanaka K.","year":"2021","journal-title":"Breast Cancer"},{"key":"e_1_2_10_17_1","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2022.1032809","article-title":"Prediction of the Histologic Upgrade of Ductal Carcinoma In\u00a0Situ Using a Combined Radiomics and Machine Learning Approach Based on Breast Dynamic Contrast\u2010Enhanced Magnetic Resonance Imaging","volume":"12","author":"Lee H.","year":"2022","journal-title":"Frontiers in Oncology"},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1038\/s41523-021-00364-z","article-title":"Ductal Carcinoma In\u00a0Situ: A Risk Prediction Model for the Underestimation of Invasive Breast Cancer","volume":"8","author":"Park K. W.","year":"2022","journal-title":"npj Breast Cancer"},{"key":"e_1_2_10_19_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2019.103498","article-title":"Deep Learning Analysis of Breast MRIs for Prediction of Occult Invasive Disease in Ductal Carcinoma In\u00a0Situ","volume":"115","author":"Zhu Z.","year":"2019","journal-title":"Computers in Biology and Medicine"},{"key":"e_1_2_10_20_1","unstructured":"\u201cMRI Exam\u2010Specific Parameters: Breast \u201d revised March 19 2025 https:\/\/accreditationsupport.acr.org\/support\/solutions\/articles\/11000114407\u2010mri\u2010exam\u2010specific\u2010parameters\u2010breast\u2010revised\u20103\u201019\u20102025#RevisionHistory."},{"key":"e_1_2_10_21_1","unstructured":"The MathWorks Inc. \u201cMATLAB Version: 9.12.0 (R2022a) \u201d 2022."},{"key":"e_1_2_10_22_1","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High\u2010Throughput Image\u2010Based Phenotyping","volume":"295","author":"Zwanenburg A.","year":"2020","journal-title":"Radiology"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1093\/biomet\/87.4.954","article-title":"A New Family of Power Transformations to Improve Normality or Symmetry","volume":"87","author":"Yeo I.","year":"2000","journal-title":"Biometrika"},{"key":"e_1_2_10_24_1","first-page":"30","volume-title":"Lightgbm: A Highly Efficient Gradient Boosting Decision Tree","author":"Ke G.","year":"2017"},{"key":"e_1_2_10_25_1","first-page":"30","volume-title":"A Unified Approach to Interpreting Model Predictions","author":"Lundberg S. M.","year":"2017"},{"key":"e_1_2_10_26_1","volume-title":"Proceedings of the 9th Python in Science Conference","author":"Seabold S.","year":"2010"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1002\/jso.21077","article-title":"Sonographic Lesion Size of Ductal Carcinoma In\u00a0Situ as a Preoperative Predictor for the Presence of an Invasive Focus","volume":"98","author":"Lee J. W.","year":"2008","journal-title":"Journal of Surgical Oncology"},{"key":"e_1_2_10_28_1","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1148\/radiol.11102368","article-title":"Ductal Carcinoma In\u00a0Situ at Core\u2010Needle Biopsy: Meta\u2010Analysis of Underestimation and Predictors of Invasive Breast Cancer","volume":"260","author":"Brennan M. E.","year":"2011","journal-title":"Radiology"},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1186\/s12880-023-01092-5","article-title":"A Clinical Radiomics Nomogram Preoperatively to Predict Ductal Carcinoma in Situ With Microinvasion in Women With Biopsy\u2010Confirmed Ductal Carcinoma In\u00a0Situ: A Preliminary Study","volume":"23","author":"Huang Z.","year":"2023","journal-title":"BMC Medical Imaging"},{"key":"e_1_2_10_30_1","unstructured":"\u201cInterpretable Machine Learning: A Guide for Making Black Box Models Explainable \u201d https:\/\/christophm.github.io\/interpretable\u2010ml\u2010book."},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1038\/s41416-021-01328-7","article-title":"Breast Cancer as an Example of Tumour Heterogeneity and Tumour Cell Plasticity During Malignant Progression","volume":"125","author":"L\u00fc\u00f6nd F.","year":"2021","journal-title":"British Journal of Cancer"},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/s10911-018-9410-6","article-title":"Intratumoral Heterogeneity in Ductal Carcinoma In\u00a0Situ: Chaos and Consequence","volume":"23","author":"Sinha V. C.","year":"2018","journal-title":"Journal of Mammary Gland Biology and Neoplasia"},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","first-page":"34","DOI":"10.2214\/AJR.22.28698","article-title":"Predicting Upgrade of Ductal Carcinoma In\u00a0Situ to Invasive Breast Cancer at Surgery With Ultrafast Imaging","volume":"221","author":"Miceli R.","year":"2023","journal-title":"American Journal of Roentgenology"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70552","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.70552","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T07:23:56Z","timestamp":1790321036000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.70552"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":32,"alternative-id":["10.1002\/jmri.70552"],"URL":"https:\/\/doi.org\/10.1002\/jmri.70552","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"assertion":[{"value":"2026-06-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"jmri.70552"}}