Journal Article

A foundation model for clinical-grade computational pathology and rare cancers detection

Robert, Eric, Zimmermann, Eric, Hall, James, Klimstra, David S., Casson, Adam, van Eck, Alexander, Millar, Ewan, Wen, Hannah, Kunz, Jeremy D., Tenenholtz, Neil, Retamero, Juan A., Wang, Yi Kan, Shaikovski, George, Rothrock, Brandon, Oakley, Gerard, Lee, Donghun, Yousfi, Razik, Mathieu, Philippe, Liu, Siqi, Vorontsov, Eugene, Bernhard, Jan H., Moye, William A., Bozkurt, Alican, Viret, Julian, Fuchs, Thomas J., Fusi, Nicolo, Hanna, Matthew, Severson, Kristen, Godrich, Ran A., Kanan, Christopher, Zelechowski, Michal, Yang, Ellen, Lee, Matthew C. H.

2024

Overview

The analysis of histopathology images with artificial intelligence aims to enable clinical decision support systems and precision medicine. The success of such applications depends on the ability to model the diverse patterns observed in pathology images. To this end, we present Virchow, the largest foundation model for computational pathology to date. In addition to the evaluation of biomarker prediction and cell identification, we demonstrate that a large foundation model enables pan-cancer detection, achieving 0.95 specimen-level area under the (receiver operating characteristic) curve across nine common and seven rare cancers. Furthermore, we show that with less training data, the pan-cancer detector built on Virchow can achieve similar performance to tissue-specific clinical-grade models in production and outperform them on some rare variants of cancer. Virchow’s performance gains highlight the value of a foundation model and open possibilities for many high-impact applications with limited amounts of labeled training data. Trained on 1.5 million whole-slide images from 100,000 patients, a pathology foundation model is shown to improve performance of specialized models in detection of rare cancers.

• Publisher: Nature Publishing Group US,Nature Publishing Group
• Subject: 692/53/2421 / 692/699/67/2322 / 692/700/139/422 / Artificial Intelligence / Biomarkers / Biomarkers, Tumor / Biomedical and Life Sciences / Biomedicine / Cancer / Cancer Research / Computational Biology - methods / Computer applications / Decision support systems / Histopathology / Humans / Infectious Diseases / Medical imaging / Metabolic Diseases / Molecular Medicine / Neoplasm Grading / Neoplasms - diagnosis / Neoplasms - genetics / Neoplasms - pathology / Neurosciences / Pathology / Pathology, Clinical - methods / Performance enhancement / Precision Medicine / Rare Diseases - diagnosis / Rare Diseases - genetics / Rare Diseases - pathology / ROC Curve