Alzheimer’s disease classification using features extracted from nonsubsampled contourlet subband-based individual networks

Morphological networks constructed with structural magnetic resonance imaging (sMRI) images have been widely investigated by exploring interregional alterations of different brain regions interest (ROI) in the spatial domain for Alzheimer’s disease (AD) classification. However, few attentions are attracted to construct a subband-based individual network sMRI image frequency domain. In order verify feasibility constructing subbands and extract features from AD classification, this study, we propose novel method capture correlations abnormal energy distribution patterns related nonsubsampled contourlet (NCSINs) Specifically, 2-dimensional representation preprocessed is firstly reshaped downsampling reconstruction steps. Then, transform performed on obtain directional subbands, each subband at one scale described column feature vector (CV) regarded as node NCSIN. Subsequently, edge between any two nodes weighted connection strength (CS). Finally, concatenation NCSINs scales used Meanwhile, support machine (SVM) classifier radial basis function (RBF) kernel applied categorizing 680 subjects Disease Neuroimaging Initiative (ADNI) database. Experimental results demonstrate that it feasible also show our NCSIN outperforms five other state-of-the-art approaches.