Deep learning on large neuroimaging datasets

Abstract: Magnetic resonance imaging (MRI) is a medical imaging method that has become increasingly more important during the last 4 decades. This is partly because it allows us to acquire a 3D-representation of a part of the body without exposing patients to ionizing radiation. Furthermore, it also typically gives better contrast between soft tissues than x-ray based techniques such as CT. The image acquisition procedure of MRI is also much more flexible. One can vary the signal sequence, not only to change how different types of tissue map to different intensities, but also to measure flow, diffusion or even brain activity over time. Machine learning has gained great impetus the last decade and a half. This is probably partly because of the work done on the mathematical foundations of machine learning done at the end of last century in conjunction with the availability of specialized massively parallel processors, originally developed as graphical processing units (GPUs), which are ideal for training or running machine learning models. The work presented in this thesis combines MRI and machine learning in order to leverage the large amounts of MRI-data available in open data sets, to address questions of clinical relevance about the brain. The thesis comprises three studies. In the first one the subproblem which augmentation methods are useful in the larger context of classifying autism, was investigated. The second study is about predicting brain age. In particular it aims to construct light-weight models using the MRI volumes in a condensed form, so that the model can be trained in a short time and still reach good accuracy. The third study is a development of the previous that investigates other ways of condensing the brain volumes.