# Computational Pathology at Health System Scale -- Self-Supervised Foundation Models from Three Billion Images

arXiv: https://arxiv.org/abs/2310.07033 · HTML: https://mlsanity.com/paper/2310.07033/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 10 Oct 2023.

## Builds on (most cited first, 21 of 21)

- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Towards Generalist Biomedical AI](https://mlsanity.com/paper/2307.14334/) (2023)
- [GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records](https://mlsanity.com/paper/2203.03540/) (2022)
- [Benchmarking Self-Supervised Learning on Diverse Pathology Datasets](https://mlsanity.com/paper/2212.04690/) (2022)
- [Virchow: A Million-Slide Digital Pathology Foundation Model](https://mlsanity.com/paper/2309.07778/) (2023)
- [Divide and Contrast: Self-supervised Learning from Uncurated Data](https://mlsanity.com/paper/2105.08054/) (2021)
- [Towards a Visual-Language Foundation Model for Computational Pathology](https://mlsanity.com/paper/2307.12914/) (2023)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [Self-supervised Learning from 100 Million Medical Images](https://mlsanity.com/paper/2201.01283/) (2022)
- [H&E-based Computational Biomarker Enables Universal EGFR Screening for Lung Adenocarcinoma](https://mlsanity.com/paper/2206.10573/) (2022)

## Built on by (most cited first, 30 of 31)

- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology](https://mlsanity.com/paper/2405.10254/) (2024)
- [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)
- [RudolfV: A Foundation Model by Pathologists for Pathologists](https://mlsanity.com/paper/2401.04079/) (2024)
- [Multistain Pretraining for Slide Representation Learning in Pathology](https://mlsanity.com/paper/2408.02859/) (2024)
- [A Foundational Multimodal Vision Language AI Assistant for Human Pathology](https://mlsanity.com/paper/2312.07814/) (2023)
- [Low-resource finetuning of foundation models beats state-of-the-art in histopathology](https://mlsanity.com/paper/2401.04720/) (2024)
- [Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective](https://mlsanity.com/paper/2407.07841/) (2024)
- [Tissue Concepts: supervised foundation models in computational pathology](https://mlsanity.com/paper/2409.03519/) (2024)
- [SurGen: 1020 H&E-stained Whole Slide Images With Survival and Genetic Markers](https://mlsanity.com/paper/2502.04946/) (2025)
- [Foundation Models in Medical Imaging: A Review and Outlook](https://mlsanity.com/paper/2506.09095/) (2025)
- [EXAONEPath 1.0 Patch-level Foundation Model for Pathology](https://mlsanity.com/paper/2408.00380/) (2024)
- [VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification](https://mlsanity.com/paper/2402.01034/) (2024)
- [Beyond Multiple Instance Learning: Full Resolution All-In-Memory End-To-End Pathology Slide Modeling](https://mlsanity.com/paper/2403.04865/) (2024)
- [EXAONE Path 2.5: Pathology Foundation Model with Multi-Omics Alignment](https://mlsanity.com/paper/2512.14019/) (2025)
- [Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness](https://mlsanity.com/paper/2603.05884/) (2026)
- [Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image Classification](https://mlsanity.com/paper/2404.07605/) (2024)
- [Foundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation](https://mlsanity.com/paper/2406.18249/) (2024)
- [A Multicenter Benchmark of Multiple Instance Learning Models for Lymphoma Subtyping from HE-stained Whole Slide Images](https://mlsanity.com/paper/2512.14640/) (2025)
- [Mixed Magnification Aggregation for Generalizable Region-Level Representations in Computational Pathology](https://mlsanity.com/paper/2602.22176/) (2026)
- [Reducing self-supervised learning complexity improves weakly-supervised classification performance in computational pathology](https://mlsanity.com/paper/2403.04558/) (2024)
- [A Survey on Cell Nuclei Instance Segmentation and Classification: Leveraging Context and Attention](https://mlsanity.com/paper/2407.18673/) (2024)
- [CanvOI, an Oncology Intelligence Foundation Model: Scaling FLOPS Differently](https://mlsanity.com/paper/2409.02885/) (2024)
- [UNICORN: A Deep Learning Model for Integrating Multi-Stain Data in Histopathology](https://mlsanity.com/paper/2409.17775/) (2024)
- [SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images](https://mlsanity.com/paper/2505.06710/) (2025)
- [Predict Patient Self-reported Race from Skin Histological Images](https://mlsanity.com/paper/2507.21912/) (2025)
- [Decoupling Parcellation from Classification: Systematic Benchmark of Fast Brain Segmentation Methods for Alzheimer's Disease Detection](https://mlsanity.com/paper/2608.16039/) (2026)
- [Learning Where to Focus: Self-Supervised Multi-Scale ViTs for Histopathology](https://mlsanity.com/paper/2609.18578/) (2026)
- [HERO: Histology Encoder for Robust Representation in Oncology](https://mlsanity.com/paper/2609.35943/) (2026)

## Abstract (arXiv)

Recent breakthroughs in self-supervised learning have enabled the use of large unlabeled datasets to train visual foundation models that can generalize to a variety of downstream tasks. While this training paradigm is well suited for the medical domain where annotations are scarce, large-scale pre-training in the medical domain, and in particular pathology, has not been extensively studied. Previous work in self-supervised learning in pathology has leveraged smaller datasets for both pre-training and evaluating downstream performance. The aim of this project is to train the largest academic foundation model and benchmark the most prominent self-supervised learning algorithms by pre-training and evaluating downstream performance on large clinical pathology datasets. We collected the largest pathology dataset to date, consisting of over 3 billion images from over 423 thousand microscopy slides. We compared pre-training of visual transformer models using the masked autoencoder (MAE) and DINO algorithms. We evaluated performance on six clinically relevant tasks from three anatomic sites and two institutions: breast cancer detection, inflammatory bowel disease detection, breast cancer estrogen receptor prediction, lung adenocarcinoma EGFR mutation prediction, and lung cancer immunotherapy response prediction. Our results demonstrate that pre-training on pathology data is beneficial for downstream performance compared to pre-training on natural images. Additionally, the DINO algorithm achieved better generalization performance across all tasks tested. The presented results signify a phase change in computational pathology research, paving the way into a new era of more performant models based on large-scale, parallel pre-training at the billion-image scale.