{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T22:14:19Z","timestamp":1787004859554,"version":"build-2736575974"},"reference-count":20,"publisher":"Georg Thieme Verlag KG","issue":"01","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Rofo"],"published-print":{"date-parts":[[2023,1]]},"abstract":"Purpose\u2002Lesion-related evaluation of the diagnostic performance of an individual artificial intelligence (AI) system to assess mamographically detected and histologically proven calcifications.<\/jats:p>\n Materials and Methods\u2002This retrospective study included 634 women of one screening unit (July 2012 \u2013 June 2018) who completed the invasive assessment of calcifications. For each leasion, the AI-system calculated a score between 0 and 98. Lesions scored >\u200a0 were classified as AI-positive. The performance of the system was evaluated based on its positive predictive value of invasive assessment (PPV3), the false-negative rate and the true-negative rate.<\/jats:p>\n Results\u2002The PPV3 increased across the categories (readers: 4a: 21.2\u200a%, 4b: 57.7\u200a%, 5: 100\u200a%, overall 30.3\u200a%; AI: 4a: 20.8\u200a%, 4b: 57.8\u200a%, 5: 100\u200a%, overall: 30.7\u200a%). The AI system yielded a false-negative rate of 7.2\u200a% (95\u200a%-CI: 4.3\u200a%: 11.4\u200a%) and a true-negative rate of 9.1\u200a% (95\u200a%-CI: 6.6\u200a%; 11.9\u200a%). These rates were highest in category 4a, 12.5\u200a% and 10.4\u200a% retrospectively. The lowest median AI score was observed for benign lesions (61, interquartile range (IQR): 45\u201374). Invasive cancers yielded the highest median AI score (81, IQR: 64\u201386). Median AI scores for ductal carcinoma in situ were: 74\u00a0(IQR: 63\u201384) for low grade, 70 (IQR: 52\u201379) for intermediate grade and 74 (IQR: 66\u201383) for high grade.<\/jats:p>\n Conclusion\u2002At the lowest threshold, the AI system yielded calcification-related PPV3 values that increased across categories, similar as seen in human evaluation. The strongest loss in AI-based breast cancer detection was observed for invasively assessed calcifications with the lowest suspicion of malignancy, yet with a comparable decrease in the false-positive rate. An AI-score based stratification of malignant lesions could not be determined.<\/jats:p>\n Key Points:\u2002<\/jats:p>\n Citation Format<\/jats:p>","DOI":"10.1055\/a-1967-1443","type":"journal-article","created":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T18:30:20Z","timestamp":1672597820000},"page":"38-46","source":"Crossref","is-referenced-by-count":4,"title":["Artificial Intelligence for Indication of Invasive Assessment of Calcifications in Mammography Screening"],"prefix":"10.1055","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8009-8831","authenticated-orcid":false,"given":"Stefanie","family":"Weigel","sequence":"additional","affiliation":[{"name":"Clinic for Radiology and Reference Center for Mammography, University Hospital and University of M\u00fcnster, M\u00fcnster, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne-Kathrin","family":"Brehl","sequence":"additional","affiliation":[{"name":"ScreenPoint Medical, Nijmegen, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6562-280X","authenticated-orcid":false,"given":"Walter","family":"Heindel","sequence":"additional","affiliation":[{"name":"Clinic for Radiology and Reference Center for Mammography, University Hospital and University of M\u00fcnster, M\u00fcnster, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1195-7399","authenticated-orcid":false,"given":"Laura","family":"Kerschke","sequence":"additional","affiliation":[{"name":"Institute of Biostatistics and Clinical Research, University of M\u00fcnster, M\u00fcnster, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"194","published-online":{"date-parts":[[2023,1,1]]},"reference":[{"key":"ref1","volume-title":"European guidelines for quality assurance in breast cancer screening and diagnosis","author":"N Perry","year":"2006"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12885-020-6646-5","article-title":"Incidence of advanced-stage breast cancer in regular participants of a mammography screening program: a prospective register-based study","volume":"20","author":"L Khil","year":"2020","journal-title":"BMC Cancer"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1002\/ijc.32767","article-title":"Breast cancer incidence and mortality before and after implementation of the German mammography screening program","volume":"147","author":"A Katalinic","year":"2020","journal-title":"Int J Cancer"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1007\/s00117-019-00615-y","article-title":"K\u00fcnstliche Intelligenz in der Mammadiagnostik","volume":"60","author":"B Bennani-Baiti","year":"2020","journal-title":"Radiologe"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1148\/radiol.2021210391","article-title":"Machine Learning for Workflow Applications in Screening Mammography: Systematic Review and Meta-Analysis","volume":"302","author":"S E Hickman","year":"2022","journal-title":"Radiology"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1148\/radiol.10091173","article-title":"Calcifications in digital mammographic screening: improvement of early detection of invasive breast cancers?","volume":"255","author":"S Weigel","year":"2010","journal-title":"Radiology"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1136\/jcp.2006.046201","article-title":"Calcification in breast lesions: pathologists\u2019 perspective","volume":"61","author":"G M Tse","year":"2008","journal-title":"J Clin Pathol"},{"key":"ref8","volume-title":"Breast Imaging Reporting and Data System: ACR BI-RADS \u2013 breast imaging atlas","author":"C J D\u2019Orsi","year":"2003"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1093\/jnci\/djy222","article-title":"Stand-Alone Artificial Intelligence for Breast Cancer Detection in Mammography: Comparison With 101 Radiologists","volume":"111","author":"A Rodriguez-Ruiz","year":"2019","journal-title":"J Natl Cancer Inst"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1007\/s00330-021-08217-w","article-title":"Using deep learning to assist readers during the arbitration process: a lesion-based retrospective evaluation of breast cancer screening performance","volume":"32","author":"L Kerschke","year":"2022","journal-title":"Eur Radiol"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1148\/radiol.2018181371","article-title":"Detection of Breast Cancer with Mammography: Effect of an Artificial Intelligence Support System","volume":"290","author":"A Rodr\u00edguez-Ruiz","year":"2019","journal-title":"Radiology"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1055\/s-0031-1273330","article-title":"Minimalinvasive biopsy results of \u201cuncertain malignant potential\u201d in digital mammography screening: high prevalence but also high predictive value for malignancy","volume":"183","author":"S Weigel","year":"2011","journal-title":"Fortschr R\u00f6ntgenstr"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1148\/radiol.2422052130","article-title":"Use of calcification descriptors in BI-RADS 4th edition to stratify risk of malignancy","volume":"242","author":"E S Burnside","year":"2007","journal-title":"Radiology"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.3390\/diagnostics11081409","article-title":"Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Diagnosis for Breast Microcalcification on Mammography","volume":"11","author":"Y A Do","year":"2021","journal-title":"Diagnostics"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1097\/RLI.0000000000000729","article-title":"Classification of Mammographic Breast Microcalcifications Using a Deep Convolutional Neural Network: A BI-RADS-Based Approach","volume":"56","author":"C Sch\u00f6nenberger","year":"2021","journal-title":"Invest Radiol"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.semcancer.2019.10.024","article-title":"The clinical value of detecting calcifications on a mammogram","volume":"72","author":"T Tot","year":"2021","journal-title":"Semin Cancer Biol"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.breast.2022.01.001","article-title":"Unresected screen-detected ductal carcinoma in situ: Outcomes of 311 women in the Forget-Me-Not 2 study","volume":"61","author":"A J Maxwell","year":"2022","journal-title":"Breast"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"109661","DOI":"10.1016\/j.ejrad.2021.109661","article-title":"Artificial intelligence for the real world of breast screening","volume":"144","author":"M G Wallis","year":"2021","journal-title":"Eur J Radiol"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"5940","DOI":"10.1007\/s00330-021-07686-3","article-title":"Can artificial intelligence reduce the interval cancer rate?","volume":"31","author":"K Lang","year":"2021","journal-title":"Eur Radiol"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1148\/radiol.210832","article-title":"Interval cancer detection using a neural network and breast density in women with negative screening mammograms","volume":"303","author":"A JT Wanders","year":"2022","journal-title":"Radiology"}],"container-title":["R\u00f6Fo - Fortschritte auf dem Gebiet der R\u00f6ntgenstrahlen und der bildgebenden Verfahren"],"original-title":[],"language":"de","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/a-1967-1443.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T07:36:54Z","timestamp":1717745814000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/a-1967-1443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":20,"journal-issue":{"issue":"01","published-online":{"date-parts":[[2023,1,1]]},"published-print":{"date-parts":[[2023,1]]}},"URL":"https:\/\/doi.org\/10.1055\/a-1967-1443","archive":["Portico","CLOCKSS"],"relation":{},"ISSN":["1438-9029","1438-9010"],"issn-type":[{"value":"1438-9029","type":"print"},{"value":"1438-9010","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}