We propose a matrix factorization technique that decom-poses the resting state fMRI (rs-fMRI) correlation matrices for a patient population into a sparse set of representative subnetworks, as modeled by rank one outer products. The subnetworks are combined using pa-tient specific non-negative coecients; these coecients are also used to model, and subsequently predict the clinical severity of a given patient via a linear regression. Our generative-discriminative framework is able to exploit the structure of rs-fMRI correlation matrices to capture group level e ects, while simultaneously accounting for patient variability. We employ ten fold cross validation to demonstrate the predictive power of our model on a cohort of fifty eight patients diagnosed with Autism Spectrum Disorder. Our method outperforms classical semi-supervised frameworks, which perform dimensionality reduction on the correlation features followed by non-linear regression to predict the clinical scores.
|Original language||English (US)|
|State||Published - Jul 24 2018|
ASJC Scopus subject areas