MVLS/EPSRC - Neural Networks models to predict individual behaviour and stroke impairment from Multimodal MRI Data

Understanding and predicting individual complex behaviour in healthy and pathological conditions is a key goal in neuroscience and psychology. Multimodal Magnetic Resonance Imaging (MRI) allows us to image functional and structural human brain properties in vivo and to relate them to behavioural performance and impairment. Machine Learning (ML) methods have seen major breakthroughs in the last decade in the domain of natural image understanding, making its way to medical image analysis. Most ML-based MRI analysis use large data sets with hundreds or thousands of individuals, making it less than ideal for MRI-based studies that, with some exceptions, rely on small sample sizes. Recent advances in ML focus on learning from smaller datasets through approaches like self-supervised/unsupervised learning and data augmentation. 

In this PhD project the student will leverage multimodal MRI using ML methods to perform data augmentation and to discover participant-specific data features that relate to the performance in different cognitive-motor tasks in healthy individuals and develop models to predict impairment in stroke survivors in small sample studies.