Dr Rezvan Farahibozorg - University of Oxford

Resources such as the UK Biobank make available functional brain imaging from thousands of individuals and provides unprecedented resources to examine the brain at a population-scale. This holds great promise for addressing fundamental questions in brain health: how do differences in brain function result in individual variability in cognition and brain disorders? Can these differences be used to predict neurodegenerative disorders, ideally before clinical onset?

To realise this potential, Dr Farahibozorg’s research designs a new machine learning framework for brain function mapping, to characterise between-person differences across large populations, and extract accurate and clinically relevant information from each person’s brain activity.

This framework aims to address three key challenges: (1) teasing apart common brain function patterns across the population, from each person’s unique characteristics; (2) integrating information from multiple brain imaging modalities to disentangle spatial versus temporal signatures of brain function; and (3) building on the knowledge learned from big datasets, to help characterise brain function in new individuals in smaller clinical cohorts and provide quantitative person- and subtype-specific profiles for disorders.

This framework aims to bridge the gap between population-level imaging and individuals, working towards an imaging-based platform for personalised predictions in neurological disorders.