Weakly-supervised deep learning models enable HER2-low prediction from H &E stained slides
Our findings offer a demonstration of how deep learning technologies can be applied to identify HER2 subgroup statuses, potentially enriching the toolkit available for clinical decision-making in oncology.
Authors
- Dirce Maria Carraro (ORCID: https://orcid.org/0000-0001-5667-1418)
- Israel Tojal da Silva (ORCID: https://orcid.org/0000-0002-4687-1499)
- Emmanuel Dias‐Neto (ORCID: https://orcid.org/0000-0001-5670-8559)
- Renan Valieris (ORCID: https://orcid.org/0000-0002-8402-3175)
- Cynthia Aparecida Bueno de Toledo Osório (ORCID: https://orcid.org/0000-0002-7675-9780)
- Luan V. C. Martins (ORCID: https://orcid.org/0000-0002-3324-9844)
- Alexandre Defelicibus (ORCID: https://orcid.org/0000-0002-3484-6317)
- Adriana Passos Bueno (ORCID: https://orcid.org/0000-0002-8671-2847)
- Rafael Rosales (ORCID: https://orcid.org/0000-0002-7518-2975)
- Jose Marcio Barros de Figueiredo
Institutions
- Rutgers, The State University of New Jersey (US)
- Universidade de São Paulo (BR)
- AC Camargo Hospital (BR)
- Institute of Physics (PL)
- Institute of Mathematics and Computer Science (MD)
- Genomic (Brazil) (BR)
- Rutgers New Jersey Medical School (US)
Publication Details
- Journal
- Breast Cancer Research
- Published
- 2024-08-19
- DOI
- https://doi.org/10.1186/s13058-024-01863-0
- Citations
- 10
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 3.47
Funders
- Fundação de Amparo à Pesquisa do Estado de São Paulo