Generalizable biomarker prediction from cancer pathology slides with self-supervised deep learning: A retrospective multi-centric study
Jan Niehues, Philip Quirke, Nicholas P. West, Heike I. Grabsch, Marko van Treeck, Yoni Schirris, Gregory Patrick Veldhuizen, Gordon Hutchins, Susan D. Richman, Sebastian Foersch, Titus J. Brinker, Junya Fukuoka, Andrey Bychkov, Wataru Uegami, Daniel Truhn, Hermann Brenner, Alexander Brobeil, Michael Hoffmeister, Jakob Nikolas Kather
Abstract
Deep learning (DL) can predict microsatellite instability (MSI) from routine histopathology slides of colorectal cancer (CRC). However, it is unclear whether DL can also predict other biomarkers with high performance and whether DL predictions generalize to external patient populations. Here, we acquire CRC tissue samples from two large multi-centric studies. We systematically compare six different state-of-the-art DL architectures to predict biomarkers from pathology slides, including MSI and mutations in BRAF, KRAS, NRAS, and PIK3CA. Using a large external validation cohort to provide a realistic evaluation setting, we show that models using self-supervised, attention-based multiple-instance learning consistently outperform previous approaches while offering explainable visualizations of the indicative regions and morphologies. While the prediction of MSI and BRAF mutations reaches a clinical-grade performance, mutation prediction of PIK3CA, KRAS, and NRAS was clinically insufficient.