{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T13:59:36Z","timestamp":1791899976077,"version":"4.3.4"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Forschung, Technologie und Raumfahrt","doi-asserted-by":"publisher","award":["01DL20003"],"award-info":[{"award-number":["01DL20003"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001655","name":"German Academic Exchange Service","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001655","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019465","name":"Arab-German Young Academy of Sciences and Humanities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019465","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.media.2026.104258","type":"journal-article","created":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T14:48:06Z","timestamp":1787410086000},"page":"104258","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["When multi-institutional dataset aggregation masks shortcut-like behavior in Foundation Models for medical imaging"],"prefix":"10.1016","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5786-9538","authenticated-orcid":false,"given":"Elodie","family":"Germani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4548-7647","authenticated-orcid":false,"given":"Fatima","family":"Zeineddine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charbel","family":"Mourad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2157-2211","authenticated-orcid":false,"given":"Shadi","family":"Albarqouni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.media.2026.104258_b1","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/s10916-019-1494-z","article-title":"Classification of mammogram images using multiscale all convolutional neural network (MA-CNN)","volume":"44","author":"Agnes","year":"2019","journal-title":"J. Med. Syst."},{"issue":"11","key":"10.1016\/j.media.2026.104258_b2","doi-asserted-by":"crossref","first-page":"111","DOI":"10.3390\/data6110111","article-title":"King Abdulaziz University breast cancer Mammogram dataset (KAU-BCMD)","volume":"6","author":"Alsolami","year":"2021","journal-title":"Data"},{"key":"10.1016\/j.media.2026.104258_b3","article-title":"Mammogram mastery: A robust dataset for breast cancer detection and medical education","volume":"1","author":"Aqdar","year":"2024","journal-title":"Data Brief"},{"issue":"10","key":"10.1016\/j.media.2026.104258_b4","doi-asserted-by":"crossref","first-page":"2704","DOI":"10.3390\/cancers15102704","article-title":"Attention-based deep learning system for classification of breast lesions\u2014Multimodal, weakly supervised approach","volume":"15","author":"Bobowicz","year":"2023","journal-title":"Cancers"},{"issue":"1","key":"10.1016\/j.media.2026.104258_b5","doi-asserted-by":"crossref","first-page":"4314","DOI":"10.1038\/s41467-023-39902-7","article-title":"Detecting shortcut learning for fair medical AI using shortcut testing","volume":"14","author":"Brown","year":"2023","journal-title":"Nat. Commun."},{"issue":"1","key":"10.1016\/j.media.2026.104258_b6","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1038\/s41597-023-02025-1","article-title":"An online Mammography database with biopsy confirmed types","volume":"10","author":"Cai","year":"2023","journal-title":"Sci. Data"},{"issue":"6","key":"10.1016\/j.media.2026.104258_b7","article-title":"Reconsidering conclusions of bias assessment in medical imaging foundation models","volume":"5","author":"Chaudhari","year":"2023","journal-title":"Radiol.: Artif. Intell."},{"issue":"3","key":"10.1016\/j.media.2026.104258_b8","doi-asserted-by":"crossref","first-page":"W292","DOI":"10.2214\/AJR.10.6049","article-title":"The relationship of mammographic density and age: Implications for breast cancer screening","volume":"198","author":"Checka","year":"2012","journal-title":"Am. J. Roentgenol."},{"issue":"6679","key":"10.1016\/j.media.2026.104258_b9","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1126\/science.adg8538","article-title":"Illusory generalizability of clinical prediction models","volume":"383","author":"Chekroud","year":"2024","journal-title":"Science"},{"key":"10.1016\/j.media.2026.104258_b10","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025","first-page":"173","article-title":"Domain generalization for mammogram classification by suppressing domain-specific features","author":"Chen","year":"2026"},{"key":"10.1016\/j.media.2026.104258_b11","series-title":"Proceedings of the 8th Machine Learning for Healthcare Conference","first-page":"110","article-title":"When more is less: Incorporating additional datasets can hurt performance by introducing spurious correlations","volume":"Vol. 219","author":"Compton","year":"2023"},{"key":"10.1016\/j.media.2026.104258_b12","doi-asserted-by":"crossref","DOI":"10.3389\/fgene.2022.1097207","article-title":"Breast cancer detection: Shallow convolutional neural network against deep convolutional neural networks based approach","volume":"13","author":"Das","year":"2023","journal-title":"Front. Genet."},{"issue":"4","key":"10.1016\/j.media.2026.104258_b13","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.2214\/AJR.06.0619","article-title":"Mammographic breast density and race","volume":"188","author":"del Carmen","year":"2007","journal-title":"Am. J. Roentgenol."},{"key":"10.1016\/j.media.2026.104258_b14","series-title":"Breast Imaging Reporting and Data System: ACR BI-RADS-Mammography","first-page":"230","author":"D\u2019orsi","year":"2003"},{"key":"10.1016\/j.media.2026.104258_b15","series-title":"Findings of the Association for Computational Linguistics: EACL 2023","first-page":"1181","article-title":"PubmedCLIP: How much does CLIP benefit visual question answering in the medical domain?","author":"Eslami","year":"2023"},{"issue":"417","key":"10.1016\/j.media.2026.104258_b16","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1080\/01621459.1992.10475190","article-title":"Generalized collinearity diagnostics","volume":"87","author":"Fox","year":"1992","journal-title":"J. Amer. Statist. Assoc."},{"key":"10.1016\/j.media.2026.104258_b17","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025","first-page":"24","article-title":"Bias and generalizability of foundation models across datasets in breast mammography","author":"Germani","year":"2025"},{"key":"10.1016\/j.media.2026.104258_b18","doi-asserted-by":"crossref","unstructured":"Ghosh, S., Poynton, C.B., Visweswaran, S., et al., 2024. Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography. In: Linguraru, M.G., Dou, Q., Feragen, A., Giannarou, S., Glocker, B., Lekadir, K., Schnabel, J.A. (Eds.), Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. Cham, pp. 632\u2013642. http:\/\/dx.doi.org\/10.1007\/978-3-031-72390-2_59.","DOI":"10.1007\/978-3-031-72390-2_59"},{"issue":"6","key":"10.1016\/j.media.2026.104258_b19","doi-asserted-by":"crossref","first-page":"e406","DOI":"10.1016\/S2589-7500(22)00063-2","article-title":"AI recognition of patient race in medical imaging: a modelling study","volume":"4","author":"Gichoya","year":"2022","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.media.2026.104258_b20","doi-asserted-by":"crossref","unstructured":"Girdhar, R., El-Nouby, A., Liu, Z., et al., 2023. ImageBind One Embedding Space to Bind Them All. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, Vancouver, BC, Canada, pp. 15180\u201315190. http:\/\/dx.doi.org\/10.1109\/CVPR52729.2023.01457.","DOI":"10.1109\/CVPR52729.2023.01457"},{"issue":"6","key":"10.1016\/j.media.2026.104258_b21","article-title":"Risk of bias in chest radiography deep learning foundation models","volume":"5","author":"Glocker","year":"2023","journal-title":"Radiol.: Artif. Intell."},{"key":"10.1016\/j.media.2026.104258_b22","series-title":"Machine learning with multi-site imaging data: An empirical study on the impact of scanner effects","author":"Glocker","year":"2019"},{"issue":"12","key":"10.1016\/j.media.2026.104258_b23","doi-asserted-by":"crossref","first-page":"6467","DOI":"10.1007\/s00521-023-09364-5","article-title":"YOLO-based CAD framework with vit transformer for breast mass detection and classification in CESM and FFDM images","volume":"36","author":"Hassan","year":"2024","journal-title":"Neural Comput. Appl."},{"issue":"1055","key":"10.1016\/j.media.2026.104258_b24","doi-asserted-by":"crossref","DOI":"10.1259\/bjr.20150242","article-title":"Breast density across a regional screening population: effects of age, ethnicity and deprivation","volume":"88","author":"Heller","year":"2015","journal-title":"Br. J. Radiol."},{"key":"10.1016\/j.media.2026.104258_b25","doi-asserted-by":"crossref","unstructured":"Huang, S.-C., Shen, L., Lungren, M.P., et al., 2021. GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 3942\u20133951.","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"10.1016\/j.media.2026.104258_b26","series-title":"A versatile foundation model for AI-enabled mammogram interpretation","author":"Huang","year":"2025"},{"key":"10.1016\/j.media.2026.104258_b27","series-title":"Advances in Neural Information Processing Systems","first-page":"111318","article-title":"FairmedFM: Fairness benchmarking for medical imaging foundation models","volume":"Vol. 37","author":"Jin","year":"2024"},{"issue":"3","key":"10.1016\/j.media.2026.104258_b28","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s42256-025-01000-2","article-title":"Explainable AI reveals Clever Hans effects in unsupervised learning models","volume":"7","author":"Kauffmann","year":"2025","journal-title":"Nat. Mach. Intell."},{"issue":"1","key":"10.1016\/j.media.2026.104258_b29","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1038\/s41597-022-01238-0","article-title":"Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research","volume":"9","author":"Khaled","year":"2022","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104258_b30","unstructured":"Khan, M.O., Afzal, M.M., Mirza, S., et al., 2023. How Fair are Medical Imaging Foundation Models?. In: Proceedings of the 3rd Machine Learning for Health Symposium. pp. 217\u2013231."},{"issue":"23","key":"10.1016\/j.media.2026.104258_b31","doi-asserted-by":"crossref","first-page":"12592","DOI":"10.1073\/pnas.1919012117","article-title":"Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis","volume":"117","author":"Larrazabal","year":"2020","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"1","key":"10.1016\/j.media.2026.104258_b32","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1186\/s40537-018-0151-6","article-title":"A survey on addressing high-class imbalance in big data","volume":"5","author":"Leevy","year":"2018","journal-title":"J. Big Data"},{"key":"10.1016\/j.media.2026.104258_b33","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2024-081554","article-title":"FUTURE-AI: international consensus guideline for trustworthy and deployable artificial intelligence in healthcare","volume":"388","author":"Lekadir","year":"2025","journal-title":"Bmj"},{"issue":"3","key":"10.1016\/j.media.2026.104258_b34","doi-asserted-by":"crossref","first-page":"671","DOI":"10.2214\/ajr.179.3.1790671","article-title":"Clinical comparison of Full-Field digital mammography and screen-film mammography for detection of breast cancer","volume":"179","author":"Lewin","year":"2002","journal-title":"Am. J. Roentgenol."},{"issue":"16","key":"10.1016\/j.media.2026.104258_b35","doi-asserted-by":"crossref","first-page":"4905","DOI":"10.1088\/0031-9155\/52\/16\/013","article-title":"Computing mammographic density from a multiple regression model constructed with image-acquisition parameters from a full-field digital mammographic unit","volume":"52","author":"Lu","year":"2007","journal-title":"Phys. Med. Biol."},{"issue":"7956","key":"10.1016\/j.media.2026.104258_b36","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"issue":"2","key":"10.1016\/j.media.2026.104258_b37","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.acra.2011.09.014","article-title":"INbreast: Toward a full-field digital mammographic database","volume":"19","author":"Moreira","year":"2012","journal-title":"Academic Radiol."},{"issue":"1","key":"10.1016\/j.media.2026.104258_b38","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1038\/s41597-023-02100-7","article-title":"VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography","volume":"10","author":"Nguyen","year":"2023","journal-title":"Sci. Data"},{"issue":"1","key":"10.1016\/j.media.2026.104258_b39","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1038\/s41746-024-01118-4","article-title":"Shortcut learning in medical AI hinders generalization: method for estimating AI model generalization without external data","volume":"7","author":"Ong Ly","year":"2024","journal-title":"Npj Digit. Med."},{"key":"10.1016\/j.media.2026.104258_b40","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.media.2026.104258_b41","series-title":"2023 7th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","first-page":"1","article-title":"An approach to classifying breast density level using deep learning-based segmentation model on full-field digital mammograms","author":"Oz\u0131c","year":"2023"},{"issue":"2","key":"10.1016\/j.media.2026.104258_b42","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.240597","article-title":"Foundation models in radiology: What, how, why, and why not","volume":"314","author":"Paschali","year":"2025","journal-title":"Radiology"},{"issue":"1","key":"10.1016\/j.media.2026.104258_b43","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1038\/s41591-020-01192-7","article-title":"An algorithmic approach to reducing unexplained pain disparities in underserved populations","volume":"27","author":"Pierson","year":"2021","journal-title":"Nature Med."},{"key":"10.1016\/j.media.2026.104258_b44","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.media.2026.104258_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2020.103842","article-title":"Breast density classification in mammograms: An investigation of encoding techniques in binary-based local patterns","volume":"122","author":"Rampun","year":"2020","journal-title":"Comput. Biol. Med."},{"issue":"1","key":"10.1016\/j.media.2026.104258_b46","doi-asserted-by":"crossref","first-page":"4581","DOI":"10.1038\/s41467-022-32186-3","article-title":"Addressing fairness in artificial intelligence for medical imaging","volume":"13","author":"Ricci Lara","year":"2022","journal-title":"Nat. Commun."},{"issue":"1","key":"10.1016\/j.media.2026.104258_b47","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digit. Med."},{"issue":"5","key":"10.1016\/j.media.2026.104258_b48","doi-asserted-by":"crossref","first-page":"4701","DOI":"10.1016\/j.aej.2021.03.048","article-title":"Deep learning in mammography images segmentation and classification: Automated CNN approach","volume":"60","author":"Salama","year":"2021","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.media.2026.104258_b49","series-title":"Curated breast imaging subset of digital database for screening mammography (CBIS-ddsm) [data set]","author":"Sawyer-Lee","year":"2016"},{"key":"10.1016\/j.media.2026.104258_b50","series-title":"Mammographic image analysis society (MIAS) database v1.21","author":"Suckling","year":"2015"},{"key":"10.1016\/j.media.2026.104258_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103090","article-title":"Fighting the scanner effect in brain MRI segmentation with a progressive level-of-detail network trained on multi-site data","volume":"93","author":"Svanera","year":"2024","journal-title":"Med. Image Anal."},{"issue":"2","key":"10.1016\/j.media.2026.104258_b52","article-title":"Open-source dataset for the RSNA screening mammography cancer detection challenge","volume":"8","author":"Trivedi","year":"2026","journal-title":"Radiol.: Artif. Intell."},{"key":"10.1016\/j.media.2026.104258_b53","series-title":"Machine Learning in Medical Imaging","first-page":"367","article-title":"Delving into Ipsilateral mammogram assessment under Multi-view network","author":"Truong","year":"2024"},{"issue":"4","key":"10.1016\/j.media.2026.104258_b54","doi-asserted-by":"crossref","first-page":"2563","DOI":"10.1007\/s10278-024-01335-z","article-title":"Detecting and mitigating the clever hans effect in medical imaging: A scoping review","volume":"38","author":"V\u00e1squez-Venegas","year":"2025","journal-title":"J. Imaging Inform. Med."},{"key":"10.1016\/j.media.2026.104258_b55","series-title":"Breast cancer","author":"World Health Organization","year":"2026"},{"key":"10.1016\/j.media.2026.104258_b56","series-title":"Demographic bias of expert-level vision-language foundation models in medical imaging","author":"Yang","year":"2024"},{"issue":"5","key":"10.1016\/j.media.2026.104258_b57","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1007\/s10140-021-01953-y","article-title":"Radiology \u201cforensics\u201d: determination of age and sex from chest radiographs using deep learning","volume":"28","author":"Yi","year":"2021","journal-title":"Emerg. Radiol."},{"key":"10.1016\/j.media.2026.104258_b58","series-title":"Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2025"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003270?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003270?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T07:07:19Z","timestamp":1789110439000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526003270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":58,"alternative-id":["S1361841526003270"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104258","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"When multi-institutional dataset aggregation masks shortcut-like behavior in Foundation Models for medical imaging","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104258","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104258"}}