Item Type: | Conference or Workshop Item |
---|---|
Title: | PathoCellBench: A comprehensive benchmark for cell phenotyping |
Creators Name: | Lüscher, Jérôme, Koreuber, Nora, Franzen, Jannik, Reith, Fabian H., Winklmayr, Claudia, Baumann, Elias, Schürch, Christian M., Kainmüller, Dagmar and Rumberger, Josef Lorenz |
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 |
Official Publication: | https://doi.org/10.1007/978-3-032-04981-0_39 |
Related to: |
Repository Staff Only: item control page