Enhancing deep learning interpretability for hand-crafted feature-guided histologic image classification via weak-to-strong generalization
Our study elucidates the key HCFs that drive DL model predictions in histologic image classification. The findings demonstrate that integrating HCFs into DL model training via the WSG framework can enhance both the interpretability and the model's predictive performance, supporting their broader clinical adoption.
Authors
- Mark A. Anastasio (ORCID: https://orcid.org/0000-0002-3192-4172)
- Zong Fan
- Lulu Sun
- Hua Li (ORCID: https://orcid.org/0009-0004-5898-8186)
- Jialin Yue
- Xiaowei Wang
- Changjie Lu
Institutions
- University of Illinois Urbana-Champaign (US)
- Washington University in St. Louis (US)
- University of Illinois Chicago (US)
- University of Chicago (US)
- Regenerative Medical Solutions (United States) (US)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2026-01-20
- DOI
- https://doi.org/10.1117/1.jmi.13.1.017502
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institutes of Health