Machine learning prediction of HER2-low expression in breast cancers based on hematoxylin–eosin-stained slides
Our AI model is able to directly predict HER2 expression through HE images with strong interpretability, and has a better ACC particularly in HER2-low breast cancers, which provides a method for AI evaluation of HER2 status and helps to perform HER2 evaluation economically and efficiently. It has the potential to assist pathologists to improve diagnosis and assess biomarkers for companion diagnostics.
Authors
- Dongdong Sun (ORCID: https://orcid.org/0000-0001-6689-2177)
- Haibo Wu (ORCID: https://orcid.org/0000-0003-0817-9191)
- Jun Du (ORCID: https://orcid.org/0000-0002-4720-2561)
- Wenchao Zhou (ORCID: https://orcid.org/0000-0002-6650-1831)
- Jun Shi (ORCID: https://orcid.org/0000-0002-8531-0483)
- Jingru Chen (ORCID: https://orcid.org/0000-0001-9317-906X)
- Guanfeng Liu (ORCID: https://orcid.org/0000-0001-8980-4950)
- Yifei Wang (ORCID: https://orcid.org/0000-0002-9918-2865)
- Wei Wang (ORCID: https://orcid.org/0000-0002-1714-994X)
- Yushan Zheng
Institutions
- University of Science and Technology of China (CN)
- Hefei University of Technology (CN)
Publication Details
- Journal
- Breast Cancer Research
- Published
- 2025-04-18
- DOI
- https://doi.org/10.1186/s13058-025-01998-8
- Citations
- 3
- Primary Topic
- HER2/EGFR in Cancer Research
- Type
- article
- Field-Weighted Citation Impact
- 3.14
Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Anhui Province
- Fundamental Research Funds for the Central Universities