{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:10:24Z","timestamp":1792595424324,"version":"4.5.0"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["C49757\/A2868"],"award-info":[{"award-number":["C49757\/A2868"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["C49757\/A2868"],"award-info":[{"award-number":["C49757\/A2868"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["C49757\/A2868"],"award-info":[{"award-number":["C49757\/A2868"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["C49757\/A2868"],"award-info":[{"award-number":["C49757\/A2868"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["C49757\/A2868"],"award-info":[{"award-number":["C49757\/A2868"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Breast Cancer Res"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>There is increasing evidence that artificial intelligence (AI) breast cancer risk evaluation tools using digital mammograms are highly informative for 1\u20136 years following a negative screening examination. We hypothesized that algorithms that have previously been shown to work well for cancer detection will also work well for risk assessment and that performance of algorithms for detection and risk assessment is correlated.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>To evaluate our hypothesis, we designed a case-control study using paired mammograms at diagnosis and at the previous screening visit. The study included <jats:italic>n<\/jats:italic> = 3386 women from the OPTIMAM registry, that includes mammograms from women diagnosed with breast cancer in the English breast screening program 2010\u20132019. Cases were diagnosed with invasive breast cancer or ductal carcinoma in situ at screening and were selected if they had a mammogram available at the screening examination that led to detection, and a paired mammogram at their previous screening visit 3y prior to detection when no cancer was detected. Controls without cancer were matched 1:1 to cases based on age (year), screening site, and mammography machine type. Risk assessment was conducted using a deep-learning model designed for breast cancer risk assessment (Mirai), and three open-source deep-learning algorithms designed for breast cancer detection. Discrimination was assessed using a matched area under the curve (AUC) statistic.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Overall performance using the paired mammograms followed the same order by algorithm for risk assessment (AUC range 0.59\u20130.67) and detection (AUC 0.81\u20130.89), with Mirai performing best for both. There was also a correlation in performance for risk and detection within algorithms by cancer size, with much greater accuracy for large cancers (30 mm+, detection AUC: 0.88\u20130.92; risk AUC: 0.64\u20130.74) than smaller cancers (0 to &lt; 10 mm, detection AUC: 0.73\u20130.86, risk AUC: 0.54\u20130.64). Mirai was relatively strong for risk assessment of smaller cancers (0 to &lt; 10 mm, risk, Mirai AUC: 0.64 (95% CI 0.57 to 0.70); other algorithms AUC 0.54\u20130.56).<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Improvements in risk assessment could stem from enhancing cancer detection capabilities of smaller cancers. Other state-of-the-art AI detection algorithms with high performance for smaller cancers might achieve relatively high performance for risk assessment.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s13058-024-01775-z","type":"journal-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T11:02:22Z","timestamp":1707303742000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Are better AI algorithms for breast cancer detection also better at predicting risk? A paired case\u2013control study"],"prefix":"10.1186","volume":"26","author":[{"given":"Ruggiero","family":"Santeramo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Celeste","family":"Damiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiefei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"Montana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam R.","family":"Brentnall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,7]]},"reference":[{"key":"1775_CR1","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","volume":"71","author":"H Sung","year":"2021","unstructured":"Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71:209\u201349.","journal-title":"CA Cancer J Clin"},{"key":"1775_CR2","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.canlet.2019.12.007","volume":"471","author":"S Huang","year":"2020","unstructured":"Huang S, Yang J, Fong S, Zhao Q. Artificial intelligence in cancer diagnosis and prognosis: opportunities and challenges. Cancer Lett. 2020;471:61\u201371.","journal-title":"Cancer Lett"},{"key":"1775_CR3","doi-asserted-by":"crossref","unstructured":"Santeramo R, Withey S, Montana G. Longitudinal detection of radiological abnormalities with time-modulated LSTM. In: Deep learning in medical image analysis and multimodal learning for clinical decision support: 4th international workshop, DLMIA 2018, and 8th international workshop, ML-CDS 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, proceedings, vol 4. Springer; 2018. p. 326\u201333.","DOI":"10.1007\/978-3-030-00889-5_37"},{"key":"1775_CR4","doi-asserted-by":"publisher","first-page":"100060","DOI":"10.1016\/j.neuri.2022.100060","volume":"2","author":"A Chattopadhyay","year":"2022","unstructured":"Chattopadhyay A, Maitra M. MRI-based brain tumour image detection using CNN based deep learning method. Neurosci inform. 2022;2:100060.","journal-title":"Neurosci inform"},{"key":"1775_CR5","doi-asserted-by":"publisher","first-page":"12495","DOI":"10.1038\/s41598-019-48995-4","volume":"9","author":"L Shen","year":"2019","unstructured":"Shen L, Margolies LR, Rothstein JH, Fluder E, McBride R, Sieh W. Deep learning to improve breast cancer detection on screening mammography. Sci Rep. 2019;9:12495.","journal-title":"Sci Rep"},{"key":"1775_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102276","volume":"127","author":"AB Nassif","year":"2022","unstructured":"Nassif AB, Talib MA, Nasir Q, Afadar Y, Elgendy O. Breast cancer detection using artificial intelligence techniques: a systematic literature review. Artif Intell Med. 2022;127: 102276.","journal-title":"Artif Intell Med"},{"key":"1775_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2023.111087","volume":"167","author":"TJ Nijnatten","year":"2023","unstructured":"Nijnatten TJ, Payne NR, Hickman SE, Ashrafian H, Gilbert FJ. Overview of trials on artificial intelligence algorithms in breast cancer screening\u2014a roadmap for international evaluation and implementation. Eur J Radiol. 2023;167: 111087.","journal-title":"Eur J Radiol"},{"key":"1775_CR8","first-page":"3","volume":"65","author":"EF Harkness","year":"2020","unstructured":"Harkness EF, Astley SM, Evans DG. Risk-based breast cancer screening strategies in women. Best practice and research. Clin obstet Gynaecol. 2020;65:3\u201317.","journal-title":"Clin obstet Gynaecol"},{"key":"1775_CR9","doi-asserted-by":"crossref","unstructured":"Arasu VA, Habel LA, Achacoso NS, et al. Comparison of mammography AI algorithms with a clinical risk model for 5-year breast cancer risk prediction: an observational study. Radiology. 2023; 307: e222733.","DOI":"10.1148\/radiol.222733"},{"key":"1775_CR10","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.222679","volume":"307","author":"C Damiani","year":"2023","unstructured":"Damiani C, Kalliatakis G, Sreenivas M, et al. Evaluation of an AI model to assess future breast cancer risk. Radiology. 2023;307: e222679.","journal-title":"Radiology"},{"key":"1775_CR11","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230227","volume":"308","author":"AD Lauritzen","year":"2023","unstructured":"Lauritzen AD, Euler-Chelpin MC, Lynge E, et al. Assessing breast cancer risk by combining AI for lesion detection and mammographic texture. Radiology. 2023;308: e230227.","journal-title":"Radiology"},{"key":"1775_CR12","doi-asserted-by":"publisher","first-page":"eaba4373","DOI":"10.1126\/scitranslmed.aba4373","volume":"13","author":"A Yala","year":"2021","unstructured":"Yala A, Mikhael PG, Strand F, et al. Toward robust mammography-based models for breast cancer risk. Sci Transl Med. 2021;13:eaba4373.","journal-title":"Sci Transl Med"},{"key":"1775_CR13","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1214\/19-STS729","volume":"35","author":"AR Brentnall","year":"2020","unstructured":"Brentnall AR, Cuzick J. Risk models for breast cancer and their validation. Stat Sci. 2020;35:14\u201330.","journal-title":"Stat Sci"},{"key":"1775_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101908","volume":"68","author":"Y Shen","year":"2021","unstructured":"Shen Y, Wu N, Phang J, et al. An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization. Med Image Anal. 2021;68: 101908.","journal-title":"Med Image Anal"},{"key":"1775_CR15","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200103","volume":"3","author":"MD Halling-Brown","year":"2021","unstructured":"Halling-Brown MD, Warren LM, Ward D, et al. Optimam mammography image database: a large-scale resource of mammography images and clinical data. Radiol Artif Intell. 2021;3: e200103.","journal-title":"Radiol Artif Intell"},{"key":"1775_CR16","unstructured":"OPTIMAM. Publications. https:\/\/medphys.royalsurrey.nhs.uk\/omidb\/publications\/"},{"key":"1775_CR17","unstructured":"Yala A. Mirai. 2021. https:\/\/github.com\/yala\/Mirai"},{"key":"1775_CR18","doi-asserted-by":"crossref","unstructured":"Yala A, Mikhael PG, Strand F, et al. Toward robust mammography-based models for breast cancer risk. Sci Transl Med. 2021;13.","DOI":"10.1126\/scitranslmed.aba4373"},{"key":"1775_CR19","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1109\/TMI.2019.2945514","volume":"39","author":"N Wu","year":"2019","unstructured":"Wu N, Phang J, Park J, et al. Deep neural networks improve radiologists\u2019 performance in breast cancer screening. IEEE Trans Med Imaging. 2019;39:1184\u201394.","journal-title":"IEEE Trans Med Imaging"},{"key":"1775_CR20","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1002\/sim.6335","volume":"34","author":"AR Brentnall","year":"2015","unstructured":"Brentnall AR, Cuzick J, Field J, Duffy SW. A concordance index for matched case-control studies with applications in cancer risk. Stat Med. 2015;34:396\u2013405.","journal-title":"Stat Med"},{"key":"1775_CR21","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1038\/s41746-023-00967-9","volume":"6","author":"AR Brentnall","year":"2023","unstructured":"Brentnall AR, Atakpa E, Hill H, et al. An optimization framework to guide choice of thresholds for risk-based cancer screening. NPJ Digit Med. 2023;6:223.","journal-title":"NPJ Digit Med"}],"container-title":["Breast Cancer Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13058-024-01775-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13058-024-01775-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13058-024-01775-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,10]],"date-time":"2024-02-10T16:17:05Z","timestamp":1707581825000},"score":1,"resource":{"primary":{"URL":"https:\/\/breast-cancer-research.biomedcentral.com\/articles\/10.1186\/s13058-024-01775-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,7]]},"references-count":21,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["1775"],"URL":"https:\/\/doi.org\/10.1186\/s13058-024-01775-z","relation":{},"ISSN":["1465-542X"],"issn-type":[{"value":"1465-542X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,7]]},"assertion":[{"value":"2 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The data used in this manuscript were fully anonymized and made available for research following ethical approval from the NHS Health Research Agency (REC reference: 19\/SC\/0284, IRAS reference: 265403).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"AB declares income from Cancer Research UK arising from commercial use of the Tyrer-Cuzick (IBIS) breast cancer risk evaluator.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25"}}