Atlas: A Novel Pathology Foundation Model by Mayo Clinic, Charité, and Aignostics
This work addresses the need for effective AI tools in medical diagnostics, specifically for pathology, and is incremental as it builds on existing foundation model approaches.
The researchers tackled the challenge of developing a foundation model for digital pathology by introducing Atlas, a vision foundation model trained on 1.2 million histopathology images, which achieves state-of-the-art performance across 21 public benchmark datasets.
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 Charité - Universtätsmedizin 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.