Atlas 2 -- Foundation models for clinical deployment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909984994885632 |
|---|---|
| author | Alber, Maximilian Milbich, Timo Carpen-Amarie, Alexandra Tietz, Stephan Dippel, Jonas Muttenthaler, Lukas Cancer, Beatriz Perez Benetti, Alessandro Korfiatis, Panos Eulig, Elias Lüscher, Jérôme Wu, Jiasen Hashimi, Sayed Abid Dernbach, Gabriel Schallenberg, Simon Shah, Neelay Krügener, Moritz Jammoria, Aniruddh Matras, Jake Duffy, Patrick Redlon, Matt Jurmeister, Philipp Horst, David Ruff, Lukas Müller, Klaus-Robert Klauschen, Frederick Norgan, Andrew |
| author_facet | Alber, Maximilian Milbich, Timo Carpen-Amarie, Alexandra Tietz, Stephan Dippel, Jonas Muttenthaler, Lukas Cancer, Beatriz Perez Benetti, Alessandro Korfiatis, Panos Eulig, Elias Lüscher, Jérôme Wu, Jiasen Hashimi, Sayed Abid Dernbach, Gabriel Schallenberg, Simon Shah, Neelay Krügener, Moritz Jammoria, Aniruddh Matras, Jake Duffy, Patrick Redlon, Matt Jurmeister, Philipp Horst, David Ruff, Lukas Müller, Klaus-Robert Klauschen, Frederick Norgan, Andrew |
| contents | 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 Charité - Universtätsmedizin Berlin, LMU Munich, and Mayo Clinic. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05148 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Atlas 2 -- Foundation models for clinical deployment Alber, Maximilian Milbich, Timo Carpen-Amarie, Alexandra Tietz, Stephan Dippel, Jonas Muttenthaler, Lukas Cancer, Beatriz Perez Benetti, Alessandro Korfiatis, Panos Eulig, Elias Lüscher, Jérôme Wu, Jiasen Hashimi, Sayed Abid Dernbach, Gabriel Schallenberg, Simon Shah, Neelay Krügener, Moritz Jammoria, Aniruddh Matras, Jake Duffy, Patrick Redlon, Matt Jurmeister, Philipp Horst, David Ruff, Lukas Müller, Klaus-Robert Klauschen, Frederick Norgan, Andrew Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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 Charité - Universtätsmedizin Berlin, LMU Munich, and Mayo Clinic. |
| title | Atlas 2 -- Foundation models for clinical deployment |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2601.05148 |