AI-driven integration of omics and histopathology for biomarker discovery in cancer

Tumors of the same cell type, origin, and stage have unique genetic features that impact course of disease and treatment response. However, management of cancer is still largely dictated by a patient’s tumor cell type and stage without further refinement.

We intend to take advantage of the unique opportunities afforded by BC’s cancer care system (with a single payer system and uniform treatment protocols, together with high quality patient outcome data) to build an artificial intelligence (AI)-based cancer biomarker discovery platform. The proposed platform will integrate the images of the tumor tissues along with their genetic markers through AI to identify novel biomarkers for cancer patient risk stratification and management. Our program will:

1. Improve efficiency in pathology laboratories.
2. Identify tissue image features that correlate with tumor genetics which can rapidly and accurately classify patients into clinically relevant groups.
3. Generate new biomarkers for precision medicine by combining tumor genetics and tissue imaging.

Ultimately, this program will improve patient outcomes, alleviate the need to perform expensive genetic profiling tests, and lead to significant cost-savings in the healthcare system.