Generalizable biomarker prediction from cancer pathology slides with self-supervised deep learning: A retrospective multi-centric study
Research output: Contribution to journal › Research article › Contributed › peer-review
Contributors
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.
Details
Original language | English |
---|---|
Article number | 100980 |
Journal | Cell Reports : Medicine |
Volume | 4 |
Issue number | 4 |
Publication status | Published - 18 Apr 2023 |
Peer-reviewed | Yes |
External IDs
PubMedCentral | PMC10140458 |
---|---|
Scopus | 85152732214 |
Keywords
Sustainable Development Goals
Keywords
- Humans, Retrospective Studies, Proto-Oncogene Proteins B-raf/genetics, Deep Learning, Proto-Oncogene Proteins p21(ras)/genetics, Colorectal Neoplasms/genetics, Biomarkers, Microsatellite Instability, Class I Phosphatidylinositol 3-Kinases/genetics