{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T23:54:18Z","timestamp":1782345258163,"version":"3.54.5"},"reference-count":23,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T00:00:00Z","timestamp":1711584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006545","name":"National Institute on Minority Health and Health Disparities of the National Institutes of Health\n    10.13039\/100006545","doi-asserted-by":"publisher","award":["U54MD007601"],"award-info":[{"award-number":["U54MD007601"]}],"id":[{"id":"10.13039\/100006545","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Breast cancer is the most common cancer affecting women globally. Despite the significant impact of deep learning models on breast cancer diagnosis and treatment, achieving fairness or equitable outcomes across diverse populations remains a challenge when some demographic groups are underrepresented in the training data. We quantified the bias of models trained to predict breast cancer stage from a dataset consisting of 1000 biopsies from 842 patients provided by AIM-Ahead (Artificial Intelligence\/Machine Learning Consortium to Advance Health Equity and Researcher Diversity). Notably, the majority of data (over 70%) were from White patients. We found that prior to post-processing adjustments, all deep learning models we trained consistently performed better for White patients than for non-White patients. After model calibration, we observed mixed results, with only some models demonstrating improved performance. This work provides a case study of bias in breast cancer medical imaging models and highlights the challenges in using post-processing to attempt to achieve fairness.<\/jats:p>","DOI":"10.3390\/a17040141","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T12:09:40Z","timestamp":1711627780000},"page":"141","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Challenges in Reducing Bias Using Post-Processing Fairness for Breast Cancer Stage Classification with Deep Learning"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9131-9356","authenticated-orcid":false,"given":"Armin","family":"Soltan","sequence":"first","affiliation":[{"name":"Hawaii Health Digital Lab, Information and Computer Science, University of Hawaii at Manoa, Honolulu, HI 96822, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3276-4411","authenticated-orcid":false,"given":"Peter","family":"Washington","sequence":"additional","affiliation":[{"name":"Hawaii Health Digital Lab, Information and Computer Science, University of Hawaii at Manoa, Honolulu, HI 96822, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"12","DOI":"10.3322\/caac.21820","article-title":"Cancer statistics, 2024","volume":"74","author":"Siegel","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","unstructured":"Golatkar, A., Anand, D., and Sethi, A. (2018, January 27\u201329). Classification of breast cancer histology using deep learning. Proceedings of the Image Analysis and Recognition: 15th International Conference, ICIAR 2018, P\u00f3voa de Varzim, Portugal. Proceedings 15."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Spanhol, F.A., Oliveira, L.S., Petitjean, C., and Heutte, L. (2016, January 24\u201329). Breast cancer histopathological image classification using Convolutional Neural Networks. Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727519"},{"key":"ref_4","first-page":"587","article-title":"Racial Disparities and Mistrust in End-of-Life Care","volume":"85","author":"Boag","year":"2018","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1001\/jamadermatol.2018.2348","article-title":"Machine Learning and Health Care Disparities in Dermatology","volume":"154","author":"Adamson","year":"2018","journal-title":"JAMA Dermatol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"Ensuring Fairness in Machine Learning to Advance Health Equity","volume":"169","author":"Rajkomar","year":"2018","journal-title":"Ann. Intern. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"105832","DOI":"10.1016\/j.jstrokecerebrovasdis.2021.105832","article-title":"Discrepancies in Stroke Distribution and Dataset Origin in Machine Learning for Stroke","volume":"30","author":"Velagapudi","year":"2021","journal-title":"J. Stroke Cerebrovasc. Dis. Off. J. Natl. Stroke Assoc."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1001\/jamaoncol.2022.2844","article-title":"World Health Organization 2021 classification of central nervous system tumors and implications for therapy for adult-type gliomas: A review","volume":"8","author":"Berger","year":"2022","journal-title":"JAMA Oncol."},{"key":"ref_9","first-page":"185","article-title":"Connecting systems, data, and people: A multidisciplinary research roadmap for chronic disease management","volume":"44","author":"Bardhan","year":"2020","journal-title":"Manag. Inf. Syst. Q."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Frankish, K., and Ramsey, W.M. (2014). The Cambridge Handbook of Artificial Intelligence, Cambridge University Press.","DOI":"10.1017\/CBO9781139046855"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e489","DOI":"10.1016\/S2589-7500(20)30186-2","article-title":"The myth of generalisability in clinical research and machine learning in health care","volume":"2","author":"Futoma","year":"2020","journal-title":"Lancet Digit. Health"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1089\/big.2016.0048","article-title":"Conscientious Classification: A Data Scientist\u2019s Guide to Discrimination-Aware Classification","volume":"5","author":"LaGatta","year":"2017","journal-title":"Big Data"},{"key":"ref_13","unstructured":"Bellamy, R.K.E., Dey, K., Hind, M., Hoffman, S.C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., and Mojsilovic, A. (2018). AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias. arXiv."},{"key":"ref_14","unstructured":"Berk, R., Heidari, H., Jabbari, S., Joseph, M., Kearns, M., Morgenstern, J., Neel, S., and Roth, A. (2017). A Convex Framework for Fair Regression. arXiv."},{"key":"ref_15","unstructured":"Bifulco, C., Piening, B., Bower, T., Robicsek, A., Weerasinghe, R., Lee, S., Foster, N., Juergens, N., Risley, J., and Nachimuthu, S. (2024, March 26). Identifying High-risk Breast Cancer Using Digital Pathology Images: A Nightingale Open Science Dataset. Nightingale Open Science. Available online: https:\/\/docs.ngsci.org\/datasets\/brca-psj-path\/."},{"key":"ref_16","unstructured":"Zhu, H., Chen, B., and Yang, C. (2023). Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lu, M.Y., Williamson, D.F.K., Chen, T.Y., Chen, R.J., Barbieri, M., and Mahmood, F. (2020). Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images. arXiv.","DOI":"10.1038\/s41551-020-00682-w"},{"key":"ref_18","unstructured":"Hardt, M., Price, E., and Srebro, N. (2016). Equality of Opportunity in Supervised Learning. arXiv."},{"key":"ref_19","unstructured":"Putzel, P., and Lee, S. (2022). Blackbox Post-Processing for Multiclass Fairness. arXiv."},{"key":"ref_20","unstructured":"Lee, S. (2024, March 26). Scotthlee\/Fairness: Now with Support for Multiclass Outcomes. Available online: https:\/\/zenodo.org\/records\/6127503."},{"key":"ref_21","first-page":"204","article-title":"Improving the Fairness of Chest X-ray Classifiers","volume":"174","author":"Zhang","year":"2022","journal-title":"PMLR"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1038\/s41746-022-00595-9","article-title":"Machine learning and health need better values","volume":"5","author":"Ghassemi","year":"2022","journal-title":"Npj Digit. Med."},{"key":"ref_23","unstructured":"Chen, I., Johansson, F.D., and Sontag, D. (2018). Why Is My Classifier Discriminatory?. arXiv."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/4\/141\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:20:23Z","timestamp":1760106023000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/4\/141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,28]]},"references-count":23,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["a17040141"],"URL":"https:\/\/doi.org\/10.3390\/a17040141","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,28]]}}}