AI Is Now As Good At Detecting Breast Cancer As Humans

Since the nineteenth century, the primary tool used to identify cells has always been the microscope but the report, by the Harvard team, identified many problems with this system. Using this technique they were able to make the AI accurate in 92 per cent of diagnosis and decrease the human rate of error by 85 per cent. Importantly, the errors made by the deep learning system did not generally correlate with the errors made by humans. The report concluded: "Although the pathologist alone is currently superior to our deep learning system alone, combining deep learning with the pathologist produced a major reduction in pathologist error rate."