# Evaluating Computational Pathology Foundation Models for Prostate Cancer Grading under Distribution Shifts

arXiv: https://arxiv.org/abs/2410.06723 · HTML: https://mlsanity.com/paper/2410.06723/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 66 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision](https://mlsanity.com/paper/2310.18689/) (2023)
- [Phikon-v2, A large and public feature extractor for biomarker prediction](https://mlsanity.com/paper/2409.09173/) (2024)
- [A Clinical Benchmark of Public Self-Supervised Pathology Foundation Models](https://mlsanity.com/paper/2407.06508/) (2024)
- [Hibou: A Family of Foundational Vision Transformers for Pathology](https://mlsanity.com/paper/2406.05074/) (2024)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [Domain Generalization in Computational Pathology: Survey and Guidelines](https://mlsanity.com/paper/2310.19656/) (2023)
- [Towards Large-Scale Training of Pathology Foundation Models](https://mlsanity.com/paper/2404.15217/) (2024)
- [Predicting molecular phenotypes from histopathology images: a transcriptome-wide expression-morphology analysis in breast cancer](https://mlsanity.com/paper/2009.08917/) (2020)
- [How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?](https://mlsanity.com/paper/2302.03679/) (2023)
- [A Comprehensive Evaluation of Histopathology Foundation Models for Ovarian Cancer Subtype Classification](https://mlsanity.com/paper/2405.09990/) (2024)
- [Transcriptome-wide prediction of prostate cancer gene expression from histopathology images using co-expression based convolutional neural networks](https://mlsanity.com/paper/2104.09310/) (2021)
- [Benchmarking Pathology Feature Extractors for Whole Slide Image Classification](https://mlsanity.com/paper/2311.11772/) (2023)

## Built on by (most cited first, 9 of 9)

- [PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology](https://mlsanity.com/paper/2505.20202/) (2025)
- [Atlas 2 -- Foundation models for clinical deployment](https://mlsanity.com/paper/2601.05148/) (2026)
- [TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning](https://mlsanity.com/paper/2512.21331/) (2025)
- [Beyond Diagnostic Performance: Revealing and Quantifying Ethical Risks in Pathology Foundation Models](https://mlsanity.com/paper/2502.16889/) (2025)
- [Graph Laplacian Transformer with Progressive Sampling for Prostate Cancer Grading](https://mlsanity.com/paper/2512.10808/) (2025)
- [From Patches to Patients: A study of the tile-to-slide performance transferability in Digital Pathology](https://mlsanity.com/paper/2606.10778/) (2026)
- [Robustifying pathology foundation models via fine-tuning](https://mlsanity.com/paper/2607.22861/) (2026)
- [HERO: Histology Encoder for Robust Representation in Oncology](https://mlsanity.com/paper/2609.35943/) (2026)
- [Scaling Multi-Teacher Distillation for Digital Pathology](https://mlsanity.com/paper/2610.12574/) (2026)

## Abstract (arXiv)

Pathology foundation models (PFMs) have emerged as powerful pretrained encoders for computational pathology, but their robustness under clinically relevant distribution shifts remains insufficiently understood. We benchmark the robustness of recent PFMs in the setting of prostate cancer grading from whole-slide images (WSIs). Using the PANDA dataset, we evaluate PFMs as frozen patch-level feature extractors within weakly supervised slide-level grading models, and assess robustness to two important forms of distribution shift: shifts in WSI image appearance across collection sites, and shifts in the label distribution over cancer grade groups. Across in-distribution settings, PFMs consistently achieve strong performance and clearly outperform a natural-image baseline. Under cross-site transfer from Radboud to Karolinska, however, performance drops substantially for all models, showing that large-scale pretraining alone does not guarantee robust downstream generalization. In contrast, PFMs are less sensitive to label-distribution shift, indicating that visually grounded domain shift is the dominant challenge. Representation analysis further supports these findings by revealing persistent domain separation between sites across all PFMs. While grade-related structure is present, it is comparatively weak, indicating that domain-related variation dominates in the learned feature space. Together, these results provide a comprehensive benchmark of PFMs under distribution shift and highlight an important practical message: although PFMs provide strong representations, generalizability remains constrained by the quality and diversity of the data used to train downstream prediction models.