For investigating brain abnormalities in various brain regions, machine learning approaches are used extensively in neuroimaging studies of brain disorders. However, the performance of these methods is often limited due to many technical challenges in the analysis of neuroimaging data. We consider different machine learning approaches including dimensionality reduction, semi-supervised learning and domain adaptation for dealing with the existing challenges in neuroimaging studies.

The presentation will cover the developed methods based on different machine leaning algorithms for predicting Alzheimer’s disease in early stage and detecting disease severity in Autism spectrum disorder using mainly magnetic resonance imaging data