{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T18:03:08Z","timestamp":1784829788788,"version":"3.55.0"},"reference-count":24,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":179,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>The interpretation of contrast-enhanced mammography (CEM) images heavily depends on radiologists\u2019 expertise, highlighting the need for automated tools to assist clinical decision-making. This pilot study aimed to develop a deep learning model using CEM images to predict the histological diagnosis of breast cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed patients who underwent CEM followed by histopathological assessment (October 2022-May 2023) across 2 centers. CEM images from center 1 were used for model development, including training and 10-fold cross-validation, while images from center 2 served as an independent external test set. The breast region was manually segmented, and 2 deep learning architectures were implemented as ensemble classifiers, using biopsy results as reference standard. Performance metrics included accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the Receiver Operating Characteristic Curve (ROC) curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 106 CEM images were retrospectively analyzed (50 from center 1 and 56 from center 2), obtained using different mammography systems. Histopathology identified 51 lesions (48%) as malignant and 55 (52%) as benign. Cross-validation yielded an ROC-AUC of 75% [58.4-91.6], accuracy of 68.7% [58.3-79], sensitivity of 68.9% [52.2-85.6], specificity of 67.8% [65.4-70.2], PPV of 69.3% [55.5-83.1], and NPV of 73.5% [55.2-91.8] (P\u2009&amp;lt;\u2009.05). External testing on images from center 2 (27 malignant, 29 benign) achieved an accuracy of 64.3%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The study showed promising performance but requires further development and dataset expansion. The model has the potential to be integrated into clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Advances in knowledge<\/jats:title>\n                    <jats:p>A deep learning model based on CEM provides a tool to support physicians in the decision-making process and reduce invasiveness in breast cancer management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bjrai\/ubag013","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T16:43:03Z","timestamp":1782751383000},"source":"Crossref","is-referenced-by-count":0,"title":["Predictive deep learning model based on contrast-enhanced mammography for breast cancer diagnosis: a pilot study"],"prefix":"10.1093","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6626-2478","authenticated-orcid":false,"given":"Roberto","family":"Maroncelli","sequence":"first","affiliation":[{"name":"Department of Radiological, Oncological and Pathological Sciences, Sapienza\u2014University of Rome , 00185 Rome,","place":["Italy"]},{"name":"Department of Experimental Medicine, Sapienza\u2014University of Rome , 00161 Rome,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5288-1098","authenticated-orcid":false,"given":"Chiara","family":"De Nardo","sequence":"additional","affiliation":[{"name":"Department of Radiological, Oncological and Pathological Sciences, Sapienza\u2014University of Rome , 00185 Rome,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1781-3174","authenticated-orcid":false,"given":"Veronica","family":"Rizzo","sequence":"additional","affiliation":[{"name":"Department of Radiological, Oncological and Pathological Sciences, Sapienza\u2014University of Rome , 00185 Rome,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7566-1798","authenticated-orcid":false,"given":"Federica","family":"Cicciarelli","sequence":"additional","affiliation":[{"name":"Department of Radiological, Oncological and Pathological Sciences, Sapienza\u2014University of Rome , 00185 Rome,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3633-649X","authenticated-orcid":false,"given":"Marcella","family":"Pasculli","sequence":"additional","affiliation":[{"name":"Department of Radiological, Oncological and Pathological Sciences, Sapienza\u2014University of Rome , 00185 Rome,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2103-2856","authenticated-orcid":false,"given":"Francesca","family":"Galati","sequence":"additional","affiliation":[{"name":"Department of Radiological, Oncological and Pathological Sciences, Sapienza\u2014University of Rome , 00185 Rome,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1432-2137","authenticated-orcid":false,"given":"Federica","family":"Pediconi","sequence":"additional","affiliation":[{"name":"Department of Radiological, Oncological and Pathological Sciences, Sapienza\u2014University of Rome , 00185 Rome,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"2026072313112837300_ubag013-B1","doi-asserted-by":"publisher","author":"Zhang","DOI":"10.3389\/fonc.2024.1364397"},{"key":"2026072313112837300_ubag013-B2","doi-asserted-by":"publisher","first-page":"439","DOI":"10.3322\/caac.21412","article-title":"Breast cancer statistics, 2017, racial disparity in mortality by state","volume":"67","author":"DeSantis","year":"2017","journal-title":"CA Cancer J Clin"},{"key":"2026072313112837300_ubag013-B3","doi-asserted-by":"publisher","first-page":"1326831","DOI":"10.3389\/fradi.2023.1326831","article-title":"Empowering breast cancer diagnosis and radiology practice: advances in artificial intelligence for contrast-enhanced mammography","volume":"3","author":"Ketki","year":"2024","journal-title":"Front Radiol"},{"key":"2026072313112837300_ubag013-B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.breast.2022.04.003","article-title":"Global guidelines for breast cancer screening: a systematic review","volume-title":"Breast","author":"Ren","year":"2022"},{"key":"2026072313112837300_ubag013-B5","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06549-2","article-title":"Digital breast tomosynthesis for breast cancer detection: a diagnostic test accuracy systematic review and meta-analysis","volume-title":"Eur Radiol","author":"Alabousi"},{"key":"2026072313112837300_ubag013-B6","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2217856","article-title":"Supplemental breast cancer screening in women with dense breasts and negative mammography: a systematic review and meta-analysis","volume-title":"Radiology","author":"Hussein"},{"key":"2026072313112837300_ubag013-B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.breast.2022.09.007","article-title":"Mammographic breast density and the risk of breast cancer: a systematic review and meta-analysis","volume-title":"Breast","author":"Bodewes"},{"key":"2026072313112837300_ubag013-B8","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2303768","article-title":"Contrast-enhanced mammography: revisiting the roots of screening","volume-title":"Radiology","author":"Mahecha Carvajal"},{"key":"2026072313112837300_ubag013-B9","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.859838","volume-title":"Front Oncol","author":"Vasselli","year":"2022"},{"key":"2026072313112837300_ubag013-B10","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.clinimag.2016.12.011","article-title":"Contrast-enhanced spectral mammography (CESM) versus MRI in the high-risk screening setting: patient preferences and attitudes","volume":"42","author":"Phillips","year":"2017","journal-title":"Clin Imaging"},{"key":"2026072313112837300_ubag013-B11","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1002\/jmri.20541","article-title":"Breast lesion analysis of shape technique: semiautomated vs. manual morphological description","volume":"23","author":"Liney","year":"2006","journal-title":"J Magn Reson Imaging"},{"key":"2026072313112837300_ubag013-B12","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.acra.2016.08.019","article-title":"Contrast-enhanced spectral mammography: technique, indications and clinical applications","volume":"24","author":"Bhimani","year":"2017","journal-title":"Acad Radiol"},{"key":"2026072313112837300_ubag013-B13","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.600546","article-title":"Radiomic analysis of contrast-enhanced mammography with different image types: classification of breast lesions","volume-title":"Front Oncol","author":"Wang"},{"key":"2026072313112837300_ubag013-B14","first-page":"568","article-title":"Contrast-enhanced mammography: a systematic review and meta-analysis of diagnostic performance","volume-title":"Radiology","author":"Cozzi"},{"key":"2026072313112837300_ubag013-B15","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1118\/1.3151811","article-title":"STEP: Spatiotemporal enhancement pattern for MR-based breast tumor diagnosis","volume":"36","author":"Zheng","year":"2009","journal-title":"Med Phys"},{"key":"2026072313112837300_ubag013-B16","doi-asserted-by":"publisher","article-title":"Fuseini mumuni data augmentation: a comprehensive survey of modern approaches","author":"Mumuni","DOI":"10.1016\/j.array.2022.100258"},{"key":"2026072313112837300_ubag013-B17","doi-asserted-by":"publisher","first-page":"2497","DOI":"10.1016\/j.acra.2024.11.035","article-title":"Deep learning for contrast enhanced mammography\u2014a systematic review","volume":"32","author":"Sorin","year":"2025","journal-title":"Acad Radiol"},{"key":"2026072313112837300_ubag013-B18","doi-asserted-by":"publisher","first-page":"1326831","DOI":"10.3389\/fradi.2023.1326831","article-title":"Empowering breast cancer diagnosis and radiology practice: advances in artificial intelligence for contrast-enhanced mammography","volume":"3","author":"Kinkar","year":"2023","journal-title":"Front Radiol"},{"key":"2026072313112837300_ubag013-B19","doi-asserted-by":"publisher","first-page":"20190580","DOI":"10.1259\/bjr.20190580","article-title":"CAD and AI for breast cancer-recent development and challenges","volume":"93","author":"Chan","year":"2020","journal-title":"Br J Radiol"},{"key":"2026072313112837300_ubag013-B20","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.breast.2020.06.005","article-title":"Diagnostic accuracy of contrast-enhanced spectral mammography for breast lesions: a systematic review and meta-analysis","volume":"53","author":"Suter","year":"2020","journal-title":"Breast"},{"key":"2026072313112837300_ubag013-B21","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13040754","article-title":"Is the level of contrast enhancement on contrast-enhanced mammography (CEM) associated with the presence and biological aggressiveness of breast cancer?","volume":"13","author":"Marzogi","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"2026072313112837300_ubag013-B22","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1007\/s10439-018-2044-4","article-title":"Classification of breast masses using a computer-aided diagnosis scheme of contrast enhanced digital mammograms","volume":"46","author":"Danala","year":"2018","journal-title":"Ann Biomed Eng"},{"key":"2026072313112837300_ubag013-B23","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/s13058-019-1187-z","article-title":"Radiomic signatures with contrast-enhanced magnetic resonance imaging for the assessment of breast cancer receptor status and molecular subtypes: initial results","volume":"21","author":"Leithner","year":"2019","journal-title":"Breast Cancer Res"},{"key":"2026072313112837300_ubag013-B24","doi-asserted-by":"publisher","first-page":"101913","DOI":"10.1016\/j.eclinm.2023.101913","article-title":"Deep learning-enabled fully automated pipeline system for segmentation and classification of single-mass breast lesions using contrast-enhanced mammography: a prospective, multicentre study","volume":"58","author":"Zheng","year":"2023","journal-title":"EClinicalMedicine"}],"container-title":["BJR|Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bjrai\/advance-article-pdf\/doi\/10.1093\/bjrai\/ubag013\/68645669\/ubag013.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bjrai\/article-pdf\/3\/1\/ubag013\/68645669\/ubag013.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bjrai\/article-pdf\/3\/1\/ubag013\/68645669\/ubag013.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T17:11:36Z","timestamp":1784826696000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bjrai\/article\/doi\/10.1093\/bjrai\/ubag013\/8721565"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bjrai\/ubag013","relation":{},"ISSN":["2976-8705"],"issn-type":[{"value":"2976-8705","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2026,1]]},"article-number":"ubag013"}}