# Benchmarking histopathology foundation models in a multi-center dataset for skin cancer subtyping

arXiv: https://arxiv.org/abs/2506.18668 · HTML: https://mlsanity.com/paper/2506.18668/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 8 of 8)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Current Pathology Foundation Models are unrobust to Medical Center Differences](https://mlsanity.com/paper/2501.18055/) (2025)
- [Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation](https://mlsanity.com/paper/2407.18449/) (2024)
- [Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis](https://mlsanity.com/paper/2412.13126/) (2024)

## Built on by (most cited first, 3 of 3)

- [NucFuseRank: Dataset Fusion and Performance Ranking for Nuclei Instance Segmentation](https://mlsanity.com/paper/2601.20104/) (2026)
- [A Comprehensive Benchmark of Histopathology Foundation Models for Kidney Digital Pathology Images](https://mlsanity.com/paper/2603.15967/) (2026)
- [Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification](https://mlsanity.com/paper/2609.28231/) (2026)

## Abstract (arXiv)

Pretraining on large-scale, in-domain datasets grants histopathology foundation models (FM) the ability to learn task-agnostic data representations, enhancing transfer learning on downstream tasks. In computational pathology, automated whole slide image analysis requires multiple instance learning (MIL) frameworks due to the gigapixel scale of the slides. The diversity among histopathology FMs has highlighted the need to design real-world challenges for evaluating their effectiveness. To bridge this gap, our work presents a novel benchmark for evaluating histopathology FMs as patch-level feature extractors within a MIL classification framework. For that purpose, we leverage the AI4SkIN dataset, a multi-center cohort encompassing slides with challenging cutaneous spindle cell neoplasm subtypes. We also define the Foundation Model - Silhouette Index (FM-SI), a novel metric to measure model consistency against distribution shifts. Our experimentation shows that extracting less biased features enhances classification performance, especially in similarity-based MIL classifiers.