Predicting cognitive decline using brain imaging
Identifying biomarkers of brain disorders from neuroimaging data is an exciting and
rapidly growing research area at the intersection of machine learning, biomedical
engineering and neuroscience. Detecting brain disorders before clinical symptoms
appear is projected to be possible by combining brain imaging
and advanced computational techniques as minute changes in
the brain structure and function precede visible symptoms.
My team develops advanced machine learning approaches for finding patterns that are predictive of disease
from brain images. Our major focus is in Alzheimer's disease and there are several possible projects suitable
for MSc thesis work. The exact topic and the scope can be decided based on the interests and skills of the student.
Basic computational skills are required (Matlab/Python/R).
Inter-subject correlation based analysis of fMRI
In the inter-subject correlation (ISC) based analysis of the functional magnetic resonance
imaging (fMRI) data, the extent of shared processing across subjects during the experiment
is determined by calculating correlation coefficients between the fMRI time series of the
subjects in the corresponding brain locations. This implies that ISC can be used to analyze
fMRI data without explicitly modeling the stimulus and thus ISC is a potential method to analyze
fMRI data acquired under complex naturalistic stimuli. We have developed a graphical user interface (GUI)
based software package, ISC Toolbox https://www.nitrc.org/projects/isc-toolbox/, implemented in Matlab for computing various ISC based analyses. Currently,
we are preparing the release of the version 3.0 of the toolbox and would welcome a MSc thesis worker to validate
new functionalities of the toolbox. Familiarity with Matlab is required.