Exploring New Methodologies for the Analysis of Functional Magnetic Resonance Imaging (fMRI) Following Closed-Head Injuries

An increasing amount of research has focused on the use of newer and alternative data analytic approaches to multi-dimensional data sets. The primary aim of this paper is to introduce two data analytic approaches as they have been applied to image scans from functional Magnetic Resonance Imaging (fMRI). The first approach involves loading data from fMRI scans into multidimensional cubes and performing tensor decomposition. In addition, we introduce a second approach involving the use of network modeling that attempts to identify stable networks in fMRI scans across time. Discussion will be focused on the application of these approaches to the modeling and rehabilitation following closed-head injury.