Speaker
Description
Over the last decade, machine learning (ML) methods have become increasingly important in medical imaging. In addition to more traditional classification tasks, ML is now being used in many other applications including object search and segmentation, image registration and even image reconstruction. Recent advances in deep learning have accelerated this trend and it is now possible to achieve human level performance in several diagnostic tasks where large databases of labelled images are available. This talk will provide an overview of this rapidly changing field and will describe how convolutional neural networks can be used for classification and segmentation in radiology and digital pathology. The challenges associated with translating deep learning applications into clinical practice will also be explored.
