# PhenoBench: A Comprehensive Benchmark for Cell Phenotyping

arXiv: https://arxiv.org/abs/2507.03532 · HTML: https://mlsanity.com/paper/2507.03532/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 18 of 18)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [Quilt-1M: One Million Image-Text Pairs for Histopathology](https://mlsanity.com/paper/2306.11207/) (2023)
- [Multimodal Whole Slide Foundation Model for Pathology](https://mlsanity.com/paper/2411.19666/) (2024)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [PanNuke Dataset Extension, Insights and Baselines](https://mlsanity.com/paper/2003.10778/) (2020)
- [Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation and Classification](https://mlsanity.com/paper/2108.11195/) (2021)
- [Phikon-v2, A large and public feature extractor for biomarker prediction](https://mlsanity.com/paper/2409.09173/) (2024)
- [PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology](https://mlsanity.com/paper/2305.15072/) (2023)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [RudolfV: A Foundation Model by Pathologists for Pathologists](https://mlsanity.com/paper/2401.04079/) (2024)
- [CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting](https://mlsanity.com/paper/2303.06274/) (2023)
- [Specialized Foundation Models Struggle to Beat Supervised Baselines](https://mlsanity.com/paper/2411.02796/) (2024)
- [Panoptic segmentation with highly imbalanced semantic labels](https://mlsanity.com/paper/2203.11692/) (2022)
- [Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification](https://mlsanity.com/paper/2411.07097/) (2024)

## Built on by (most cited first, 1 of 1)

- [Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy](https://mlsanity.com/paper/2606.12346/) (2026)

## Abstract (arXiv)

Digital pathology has seen the advent of a wealth of foundational models (FM), yet to date their performance on cell phenotyping has not been benchmarked in a unified manner. We therefore propose PhenoBench: A comprehensive benchmark for cell phenotyping on Hematoxylin and Eosin (H&E) stained histopathology images. We provide both PhenoCell, a new H&E dataset featuring 14 granular cell types identified by using 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 different 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 PhenoCell, we observe scores as low as 0.20. This indicates a much more challenging task not captured by previous benchmarks, establishing PhenoCell as a prime asset for future benchmarking of FMs and supervised models alike. Code and data are available on GitHub.