Talk by Prof. Dr. Kerstin Ritter (Charité - Universitätsmedizin Berlin)
From machine learning to deep learning in clinical neuroimaging
Machine learning techniques have become increasingly popular for diagnosing / characterizing neurological and psychiatric diseases based on structural or functional MRI data. In this talk, I will review research from machine learning to deep learning in clinical neuroimaging including own work on multiple sclerosis, Alzheimer's disease and mental health. I will focus on transparent convolutional neural network models and several challenges in applying deep learning to neuroimaging data will be discussed.