Bram van Ginneken

Title: From machine to deep learning: impact on ophthalmology, pathology, and radiology

Abstract: For more than half a century, researchers have attempted to analyze medical images with a computer as accurately and precisely as human experts can do this. Only as of recently, after the field switched from machine learning techniques to deep learning techniques, this has actually become achievable. What's more, it has become scalable, i.e. such systems can be developed quickly when a sufficient amount of well-annotated training data is available. This development will be illustrated with examples from ophthalmology, pathology, and radiology that my group has been involved in. I believe this will have a profound impact on medicine, but also on the field of medical image analysis research.

Bio: Bram van Ginneken is Professor of Medical Image Analysis at Radboud University Medical Center. Since 2010 he is chair of the Diagnostic Image Analysis Group. He also works for Fraunhofer MEVIS in Bremen, Germany, and is a founder of Thirona, a company that develops software and provides services for medical image analysis. He is Associate Editor of IEEE Transactions on Medical Imaging, member of the Editorial Board of Medical Image Analysis, and member of the Fleischner Society. He pioneered the concept of challenges in medical image analysis.