Evaluating the Transferability of Pathology Foundation Models Across Cancer-related H&E Neurodegeneration-related Immunohistochemical Classification Tasks
Juan C Vizcarra, Bhavesh C Kataria, Chen-Nee Chuah, Thomas M Pearce, Brittany N Dugger, Carlos A Candano, Aaron M Rosado, Lee A Cooper, David A Gutman · 2026
Read Evaluating the Transferability of Pathology Foundation Models Across Cancer-related H&E Neurodegeneration-related Immunohistochemical Classification Tasks by Juan C Vizcarra, Bhavesh C Kataria, Chen-Nee Chuah, Thomas M Pearce, Brittany N Dugger, Carlos A Candano, Aaron M Rosado, Lee A Cooper, David A Gutman (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13648454.txt.
Description
Juan C. Vizcarra and eight colleagues test whether pathology foundation models, large artificial intelligence systems pretrained on tissue images, transfer to brain disease tasks outside their usual cancer training ground. They compared fourteen frozen feature extractors against a conventional network trained directly on each task.
Four datasets covered tau tangles and amyloid plaques in stained brain tissue, plus two cancer collections. On the brain tasks, the directly trained network beat every frozen model, even when trained on only a tiny fraction of the data. On cancer tasks the foundation models matched or exceeded it. The authors conclude that transfer depends heavily on how well pretraining covered the target domain.
Catalog record
| CREATOR | Juan C Vizcarra, Bhavesh C Kataria, Chen-Nee Chuah, Thomas M Pearce, Brittany N Dugger, Carlos A Candano, Aaron M Rosado, Lee A Cooper, David A Gutman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |