![[feed]](/style/images/feed-icon-14x14.png){kind=icon}
Tools
Tools
| Item Type: | Article |
|---|---|
| Title: | PathoCellBench: A comprehensive benchmark for cell phenotyping |
| Creators: |
Lüscher, Jérôme, Koreuber, Nora  ORCID: https://orcid.org/0009-0003-9328-4590, Franzen, Jannik ORCID: https://orcid.org/0000-0002-0761-641X, Reith, Fabian H. ORCID: https://orcid.org/0000-0002-0745-2726, Winklmayr, Claudia ORCID: https://orcid.org/0000-0002-8784-2301, Baumann, Elias, Schürch, Christian M., Kainmüller, Dagmar ORCID: https://orcid.org/0000-0002-9830-2415 and Rumberger, Josef Lorenz ORCID: https://orcid.org/0000-0002-7225-7011
|
| Abstract: | Digital pathology has seen the advent of a wealth of foundational models (FMs), yet to date their performance on cell phenotyping has not been benchmarked in a unified manner. We therefore propose PathoCellBench: A comprehensive benchmark for cell phenotyping on Hematoxylin and Eosin (H&E) stained histopathology images. We provide both PathoCell, a new H&E dataset featuring 14 cell types identified via multiplexed imaging, and ready-to-use fine-tuning and benchmarking code that allows the systematic evaluation of multiple prominent pathology FMs in terms of dense cell phenotype predictions in a range of generalization scenarios. We perform extensive benchmarking of existing FMs, providing insights into their generalization behavior under technical vs. medical domain shifts. Furthermore, while FMs achieve macro F1 scores > 0.70 on previously established benchmarks such as Lizard and PanNuke, on PathoCell, we observe scores as low as 0.20. This indicates a much more challenging task not captured by previous benchmarks, establishing PathoCell as a prime asset for future benchmarking of FMs and supervised models alike. Code and data are available on GitHub. |
| Keywords: | Digital Pathology, Cell Phenotyping, Foundation Models |
| Source: | Lecture Notes in Computer Science |
| Series Name: | Lecture Notes in Computer Science (LNCS) |
| Title of Book: | Medical Image Computing and Computer Assisted Intervention - MICCAI 2025 |
| ISSN: | 0302-9743 |
| ISBN: | 978-3-032-04980-3 |
| Publisher: | Springer |
| Volume: | 15966 |
| Page Range: | 411-420 |
| Number of Pages: | 10 |
| Date: | 20 September 2025 |
| Additional Information: | Erratum in: Lecture Notes in Computer Science, vol 15966. 04 Jan 2026. |
| Official Publication: | https://doi.org/10.1007/978-3-032-04981-0_39 |
| Related to: |
Repository Staff Only: item control page
