AI discovers previously unknown features linked to cancer recurrence

In a new study, researchers found that artificial intelligence (AI) technology could successfully discover features in pathology images from human cancer patients, without annotation, that could be understood by human doctors. The AI identified features relevant to cancer prognosis that were not previously noted by pathologists, leading to higher accuracy of prostate cancer recurrence compared to pathologist-based diagnosis. Further, Combining the predictions made by the AI with predictions by human pathologists led to even greater accuracy. The AI tech was developed by a team at the RIKEN Center for Advanced Intelligence Project (AIP) in Japan and elsewhere. According to the team, this technology could contribute to personalized medicine by making a highly accurate prediction of cancer recurrence possible by acquiring new knowledge from images.