Eigenvector centrality (EC) is a parameter-free method to measure the centrality of complex brain network structures without a priori assumption. It is here applied to resting state fMRI data acquired from normal controls (NC) and Parkinson’s disease (PD) subjects for the purpose of detecting centrality abnormality in PD, a disease known to impact neural networks diffusely. The features extracted from EC were able to accurately classify subjects when used with linear discriminant analysis and support vector machine.
This abstract and the presentation materials are available to members only; a login is required.