Deep Learning Predicts Subtype Heterogeneity and Outcomes in Luminal A Breast Cancer Using Routinely Stained Whole-Slide Images
A deep learning model, trained using transcriptomic data, inexpensively quantifies and fine-maps ITH due to subtype admixture in routine images of LumA breast cancer, the most favorable subtype. This new approach could facilitate exploration of the mechanisms behind such heterogeneity and its impact on selection of therapy for individual patients.
Authors
- Nikhil Cherian Kurian (ORCID: https://orcid.org/0000-0003-1713-0736)
- Peter H. Gann (ORCID: https://orcid.org/0000-0002-9439-2900)
- Ruchika Verma (ORCID: https://orcid.org/0000-0003-4870-128X)
- Amit Sethi (ORCID: https://orcid.org/0000-0002-8634-1804)
- Stephanie M. McGregor (ORCID: https://orcid.org/0000-0002-7940-1143)
- Neeraj Kumar (ORCID: https://orcid.org/0000-0002-3221-3831)
Institutions
- Mount Sinai Health System (US)
- Memorial Sloan Kettering Cancer Center (US)
- University of Wisconsin–Madison (US)
- Indian Institute of Technology Bombay (IN)
- University of Illinois Chicago (US)
- University of Wisconsin Carbone Cancer Center (US)
- The University of Adelaide (AU)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- Cancer Research Communications
- Published
- 2024-12-31
- DOI
- https://doi.org/10.1158/2767-9764.crc-24-0397
- Citations
- 2
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.69
Funders
- Breast Cancer Alliance
- National Institutes of Health
- University of Illinois at Urbana-Champaign
- National Cancer Institute
- Cancer Center, University of Illinois at Chicago