Characterization Multimodal Connectivity of Brain Network by Hypergraph GAN for Alzheimer’s Disease Analysis

Using multimodal neuroimaging data to characterize brain network is currently an advanced technique for Alzheimer’s disease(AD) Analysis. Over recent years the community has made tremendous progress in study of resting-state functional magnetic resonance imaging (rs-fMRI) derived from blood-oxygen-level-dependent (BOLD) signals and Diffusion Tensor Imaging (DTI) white matter fiber tractography. However, Due heterogeneity complexity between BOLD tractography, Most existing fusion algorithms can not sufficiently take advantage complementary information rs-fMRI DTI. To overcome this problem, a novel Hypergraph Generative Adversarial Networks (HGGAN) proposed paper, which utilizes Interactive Hyperedge Neurons module (IHEN) Optimal Homomorphism algorithm (OHGH) generate connectivity Brain Network combination with evaluate performance model, We use publicly available ADNI database demonstrate that model only identify discriminative regions AD but also effectively improve classification performance.