Atlas 2 -- Foundation models for clinical deployment

TL;DR

Atlas 2 introduces three pathology foundation models that achieve state-of-the-art prediction, robustness, and efficiency, trained on the largest dataset of 5.5 million histopathology images from multiple institutions.

Contribution

The paper presents Atlas 2 models that significantly improve performance and resource efficiency in computational pathology, trained on the largest dataset to date.

Findings

State-of-the-art prediction accuracy

Enhanced robustness across benchmarks

Improved resource efficiency

Abstract

Pathology foundation models substantially advanced the possibilities in computational pathology -- yet tradeoffs in terms of performance, robustness, and computational requirements remained, which limited their clinical deployment. In this report, we present Atlas 2, Atlas 2-B, and Atlas 2-S, three pathology vision foundation models which bridge these shortcomings by showing state-of-the-art performance in prediction performance, robustness, and resource efficiency in a comprehensive evaluation across eighty public benchmarks. Our models were trained on the largest pathology foundation model dataset to date comprising 5.5 million histopathology whole slide images, collected from three medical institutions Charit\'e - Universt\"atsmedizin Berlin, LMU Munich, and Mayo Clinic.