Pan-cancer image-based detection of clinically actionable genetic alterations

Precision treatment of cancer relies on genetic alterations which are diagnosed by molecular biology assays. These tests can be a bottleneck in oncology workflows because of high turnaround time, tissue usage and costs. Here, we show that deep learning can predict point mutations, molecular tumor subtypes and immune-related gene expression signatures directly from routine histological images of tumor tissue. We developed and systematically optimized a one-stop-shop workflow and applied it to more than 4000 patients with breast, colon and rectal, head and neck, lung, pancreatic, prostate cancer, melanoma and gastric cancer. Together, our findings show that a single deep learning algorithm can predict clinically actionable alterations from routine histology data. Our method can be implemented on mobile hardware, potentially enabling point-of-care diagnostics for personalized cancer treatment in individual patients.