Speaker: Maria Vakalopoulou

Title: Deep Learning on Medical Imaging. From Image Segmentation and Registration to Patient Treatment

Abstract:

Machine learning, visual computing and biomedical image analysis have made tremendous progress of the past decade. This is mostly due the development of efficient learning and inference algorithms that allow better representations and a richer modelling of visual perception tasks. In this talk, we will briefly introduce recently developed methods based mainly on deep learning architectures that are able to extract meaningful representations from the medical images providing accurate and efficient algorithms for variety of tasks. In particular, we will discuss their strength and limitations together with their applications on segmentation and registration of medical volumes and response to treatment.