I graduated from the University of Manchester with the MPhys in Theoretical Physics degree. My first interest in health related science developed at the Met Office, where I had the summer internship in the health team. In the Met office I worked on the method for forecasting of the spores releases and their effect on people with asthma and allergy. During final year of my studies I completed a master's thesis in the field of medical imaging while I was working on the method of automated digital mammography analysis.
Alteration in brain connectivity, as captured for instance by functional MR imaging, has been found to be associated with a variety of clinical disorders. However only a handful of suitable statistical models and machine learning techniques for predicting a disease status or other clinical outcome from brain networks have been developed so far. The aim of this project is two-fold: (a) to develop statistical models for the estimation of time-varying brain connectivity networks from functional MRI data, which do not pose the unrealistic assumption of time series stationarity, and (b) to develop machine learning techniques for the analysis of time-varying networks with the purpose of extracting connectivity patterns that are highly predictive of a clinical outcome. The resulting methods and tools will be tested and validated on a number of publicly available data sets, such as those generated by the Human Connectome Project (HCP) and Alzheimer’s Disease Neuroimaging Initiative (ADNI).