Leveraging Interpretable <scp>AI</scp> for Deciphering Signature Histopathologic Patterns
This study demonstrates the potential of attention-based AI models to improve diagnostic accuracy and provide interpretable insights in differentiating LCV and MVO. The use of explainable AI and heatmaps offers a valuable tool for pathologists, enhancing their ability to identify and understand subtle histopathologic patterns.
Authors
- Goran Micevic (ORCID: https://orcid.org/0000-0003-0329-1053)
- William Damsky (ORCID: https://orcid.org/0000-0003-0975-4071)
- Jun Deng (ORCID: https://orcid.org/0000-0002-7644-5853)
- Christine J. Ko (ORCID: https://orcid.org/0000-0003-2270-2524)
- Shawn E. Cowper (ORCID: https://orcid.org/0000-0002-5850-4389)
- Jennifer Madison McNiff (ORCID: https://orcid.org/0000-0001-8142-6481)
- Jason Cohen (ORCID: https://orcid.org/0000-0002-1945-2715)
- Sophia T. Luyten
- Jeff R. Gehlhausen
Institutions
- Yale University (US)
- Columbia University (US)
Publication Details
- Journal
- Journal of Cutaneous Pathology
- Published
- 2026-01-02
- DOI
- https://doi.org/10.1111/cup.70048
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Yale University