A Feature-Based Fusion Method for Making Group Inference in Epileptic fMRI and DTI using Canonical Correlation Analysis

In recent years, there have been a great interest for combined analysis of functional magnetic resonance imaging (fMRI) and structural MRI (sMRI) data, because they presentcomplementary information of different tissue types. Canonical correlation analysis (CCA) is a simple data fusionscheme to evaluate brain connectivity. We specify theversatility of CCA to extract features of resting state fMRI and Diffusion Tensor Imaging (DTI). The most informativefeatures, ALFF and FA, are extracted from datasets of epilepsy and healthy subjects. CCA has been successfullyutilized for joint data analysis such as combined analysis ofEEG and fMRI of a single subject. In the current work, we present a new technique for combination of two modalitiesacross subjects and back reconstruction of components for each group and each subject. Our results indicate thattemporal gyrus, cuneus, posterior cingulate cortex andcingulate gyrus are highly correlated with white matter integrity between two hemispheres (corpus callosum) andcerebro-spinal fluid. In addition, there are significant changes in the thalamus that shows extensive damages in this brainstructure.

کلیدواژه ها:

Functional magnetic resonance imaging ، diffusion tensor imaging ، fusion ، canonical correlation analysis