AI Image Recognition Moves from Radiology to Pathology

Researchers from Memorial Sloan Kettering Cancer Center in New York City and med-tech computational pathology startup Paige say they’ve developed a clinical-grade artificial intelligence model to detect cancer in tissue slides with near-perfect accuracy.

The study, published July 15 in Nature Medicine, used an AI-based detection system that employs deep learning to analyze slides from more than 15,000 patients with prostate, skin and breast cancer. Tech Crunch reports that the system is novel in that it can eschew the need to curate data sets for training first, which greatly reduces cost and the time required to build accurate AI-based diagnostic tools.

In February, Paige announced $25 million in Series A funding and a partnership with Memorial Sloan Kettering to gain access to one of the largest single repositories of pathology slides in the world. Paige is reportedly working to commercialize its technology and the Food and Drug Administration is reviewing the work described in the MSK study.