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.
@article{arxiv.2501.05409,
title = {Atlas: A Novel Pathology Foundation Model by Mayo Clinic, Charit\'e, and Aignostics},
author = {Maximilian Alber and Stephan Tietz and Jonas Dippel and Timo Milbich and Timothée Lesort and Panos Korfiatis and Moritz Krügener and Beatriz Perez Cancer and Neelay Shah and Alexander Möllers and Philipp Seegerer and Alexandra Carpen-Amarie and Kai Standvoss and Gabriel Dernbach and Edwin de Jong and Simon Schallenberg and Andreas Kunft and Helmut Hoffer von Ankershoffen and Gavin Schaeferle and Patrick Duffy and Matt Redlon and Philipp Jurmeister and David Horst and Lukas Ruff and Klaus-Robert Müller and Frederick Klauschen and Andrew Norgan},
journal= {arXiv preprint arXiv:2501.05409},
year = {2025}
}