Graph-Based Method for Anomaly Detection in Functional Brain Network using Variational Autoencoder
share
Functional neuroimaging techniques have accelerated progress in the study of brain disorders and dysfunction, often measured using resting-state functional MRI (rs-fMRI). Because there are slight differences between healthy and disorder brains, investigating in the complex topology of human brain functional networks is difficult and complicated task with the growth of evaluation criteria. Meanwhile, graph theory and deep learning applications have recently spread widely to understanding human cognitive functions are linked to gene expression and related distributed spatial patterns. Irregular graph analysis has been widely applied in many domain, these applications might involve both node-centric and graph-centric tasks. In this work we explore Variational Autoencoder and Graph Convolutional Networks (GCNs) for the task of region of interest (ROI) brain identification Areas which do not have normal connection. For the learning of a powerful rigid graphs among large-scale data and underlying non-Euclidean structure, here used a framework of Graph Auto-Encoder (GAE) base on graph with hyper sphere distributer for functional of brain analyzing. we also obtain the correlation and possible modes between abnormal connections.
READ FULL TEXT
