Currently, pathologists examine and characterise the features of tissue samples taken from cancer patients on slides under a microscope. An international team of AI specialists and cancer scientists, led by researchers from the University of Glasgow and New York University, have developed a new system, which they call histomorphological phenotype learning (HPL). The algorithm broke down the slide images into thousands of tiny tiles, each representing a small amount of human tissue. Human pathologists tasked with the same prediction drew the correct conclusions with 64% accuracy. “The insight provided by human expertise and AI analysis working together could provide faster, more accurate cancer diagnoses and evaluations of patients’ likely outcomes.

Source: The Star June 11, 2024 11:57 UTC