# Training state-of-the-art pathology foundation models with orders of magnitude less data

arXiv: https://arxiv.org/abs/2504.05186 · HTML: https://mlsanity.com/paper/2504.05186/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 16 of 16)

- [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)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Rotation Equivariant CNNs for Digital Pathology](https://mlsanity.com/paper/1806.03962/) (2018)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology](https://mlsanity.com/paper/1902.06543/) (2019)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [FlexiViT: One Model for All Patch Sizes](https://mlsanity.com/paper/2212.08013/) (2022)
- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis](https://mlsanity.com/paper/2406.16192/) (2024)
- [A Petri Dish for Histopathology Image Analysis](https://mlsanity.com/paper/2101.12355/) (2021)
- [Hibou: A Family of Foundational Vision Transformers for Pathology](https://mlsanity.com/paper/2406.05074/) (2024)
- [Atlas: A Novel Pathology Foundation Model by Mayo Clinic, Charit'e, and Aignostics](https://mlsanity.com/paper/2501.05409/) (2025)
- [Pathology Foundation Models](https://mlsanity.com/paper/2407.21317/) (2024)

## Built on by (most cited first, 22 of 22)

- [Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings](https://mlsanity.com/paper/2511.23204/) (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)
- [MOOZY: A Patient-First Foundation Model for Computational Pathology](https://mlsanity.com/paper/2603.27048/) (2026)
- [To What Extent Do Token-Level Representations from Pathology Foundation Models Improve Dense Prediction?](https://mlsanity.com/paper/2602.03887/) (2026)
- [Mixed Magnification Aggregation for Generalizable Region-Level Representations in Computational Pathology](https://mlsanity.com/paper/2602.22176/) (2026)
- [MINT: Molecularly Informed Training with Spatial Transcriptomics Supervision for Pathology Foundation Models](https://mlsanity.com/paper/2603.07895/) (2026)
- [CytoSyn: a Foundation Diffusion Model for Histopathology -- Tech Report](https://mlsanity.com/paper/2603.18089/) (2026)
- [HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction](https://mlsanity.com/paper/2603.19957/) (2026)
- [Clinically-Informed Modeling for Pediatric Brain Tumor Classification from Whole-Slide Histopathology Images](https://mlsanity.com/paper/2604.21060/) (2026)
- [Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction](https://mlsanity.com/paper/2605.08276/) (2026)
- [DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance](https://mlsanity.com/paper/2608.17872/) (2026)
- [SIMPLER: H&E-Informed Representation Learning for Structured Illumination Microscopy](https://mlsanity.com/paper/2604.10334/) (2026)
- [PC-MIL: Decoupling Feature Resolution from Supervision Scale in Whole-Slide Learning](https://mlsanity.com/paper/2604.12100/) (2026)
- [When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework](https://mlsanity.com/paper/2605.31504/) (2026)
- [From Patches to Patients: A study of the tile-to-slide performance transferability in Digital Pathology](https://mlsanity.com/paper/2606.10778/) (2026)
- [Probing, Fusion, and Trustworthiness: A Systematic Evaluation of Foundation Model Representations for Multimodal Cancer Analysis](https://mlsanity.com/paper/2606.17115/) (2026)
- [Robustifying pathology foundation models via fine-tuning](https://mlsanity.com/paper/2607.22861/) (2026)
- [A Distributional Robustness Margin For Pathology Foundation Models](https://mlsanity.com/paper/2607.25497/) (2026)
- [Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity](https://mlsanity.com/paper/2609.32876/) (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)

The field of computational pathology has recently seen rapid advances driven by the development of modern vision foundation models (FMs), typically trained on vast collections of pathology images. Recent studies demonstrate that increasing the training data set and model size and integrating domain-specific image processing techniques can significantly enhance the model's performance on downstream tasks. Building on these insights, our work incorporates several recent modifications to the standard DINOv2 framework from the literature to optimize the training of pathology FMs. We also apply a post-training procedure for fine-tuning models on higher-resolution images to further enrich the information encoded in the embeddings. We present three novel pathology FMs trained on up to two orders of magnitude fewer WSIs than those used to train other state-of-the-art FMs while demonstrating a comparable or superior performance on downstream tasks. Even the model trained on TCGA alone (12k WSIs) outperforms most existing FMs and, on average, matches Virchow2, the second-best FM published to date. This suggests that there still remains a significant potential for further improving the models and algorithms used to train pathology FMs to take full advantage of the vast data collections.