Deep learning analysis of hematoxylin and eosin-stained benign breast biopsies to predict future invasive breast cancer
This study opens promising avenues for breast cancer risk assessment in women with benign breast disease. Integrating whole-slide images and clinicopathological characteristics through a multimodal approach substantially improved predictive model performance. Future research will explore deep learning techniques to understand benign breast disease progression to invasive breast cancer.
Authors
- Monjoy Saha (ORCID: https://orcid.org/0000-0002-6470-3544)
- Jonas S. Almeida (ORCID: https://orcid.org/0000-0002-7883-7922)
- Mustapha Abubakar (ORCID: https://orcid.org/0000-0003-3728-6535)
- Ruth M. Pfeiffer (ORCID: https://orcid.org/0000-0001-7791-2698)
- Gretchen L. Gierach (ORCID: https://orcid.org/0000-0002-0165-5522)
- Máire A. Duggan (ORCID: https://orcid.org/0000-0001-6625-7683)
- Thomas E. Rohan (ORCID: https://orcid.org/0000-0001-6897-4045)
- Kathryn Richert-Boe
Institutions
- National Institutes of Health (US)
- Albert Einstein College of Medicine (US)
- University of Calgary (CA)
- Kaiser Permanente Center for Health Research (US)
- National Cancer Institute (US)
- Department of Health and Human Services (US)
- Division of Cancer Epidemiology and Genetics
Publication Details
- Journal
- JNCI Cancer Spectrum
- Published
- 2025-04-07
- DOI
- https://doi.org/10.1093/jncics/pkaf037
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Breast Cancer Research Foundation
- National Institutes of Health
- National Cancer Institute
- Division of Cancer Epidemiology and Genetics, National Cancer Institute