Atlas: A Novel Pathology Foundation Model by Mayo Clinic, Charit\'e, and Aignostics

TL;DR

Atlas is a new pathology foundation model trained on 1.2 million histopathology images, achieving state-of-the-art results across multiple benchmarks despite not being the largest model.

Contribution

The paper introduces Atlas, a novel vision foundation model for digital pathology trained on a large dataset from two institutions, demonstrating superior performance.

Findings

Achieves state-of-the-art performance on 21 benchmark datasets

Trained on 1.2 million histopathology images from Mayo Clinic and Charité

Outperforms larger models despite smaller size

Abstract

Recent advances in digital pathology have demonstrated the effectiveness of foundation models across diverse applications. In this report, we present Atlas, a novel vision foundation model based on the RudolfV approach. Our model was trained on a dataset comprising 1.2 million histopathology whole slide images, collected from two medical institutions: Mayo Clinic and Charit\'e - Universt\"atsmedizin Berlin. Comprehensive evaluations show that Atlas achieves state-of-the-art performance across twenty-one public benchmark datasets, even though it is neither the largest model by parameter count nor by training dataset size.