A Schizophrenia Detection System Based on Hybrid Higher-order Brain Networks

Abstract

The invention provides a schizophrenia detection system based on a mixed high-order brain network, and relates to the technical field of electroencephalogram signals. The system includes an EEG signal preprocessing module for preprocessing the acquired original EEG signal, a brain function network building block for constructing a static low-order multi-layer brain function network and a dynamic high-order multi-layer brain function network; The topological structure metrics of the static low-order multi-layer brain function network model and the dynamic high-order multi-layer brain function network model of the subjects were tested by K-S, and the topological structure metrics smaller than the set threshold were selected and spliced ​​into a feature matrix The feature extraction module; the detection module for schizophrenia is realized by training the classifier through the feature matrix. This system overcomes the shortcomings of insufficient expression of brain interval information and insufficient utilization of time information in the previous brain functional network, so that the information of EEG signals can be fully utilized, and it can better serve medical disease detection.

Description

Technical field [0001] The present invention relates to the field of EEG signaling technology, in particular to a schizophrenia detection system based on a mixed high-order brain network. Background [0002] In recent years, neuroimaging technology has made rapid progress, which provides corresponding technology for studying the functions of various brain regions in patients with schizophrenia. Electroencephalogram (EEG) is an important tool for monitoring brain activity, low cost, easy to meet environmental requirements, convenient for patient collection, no need to confine the subject to a small space, so as to avoid the advantages of claustrophobia in the subject. Moreover, EEG analysis is a noninvasive and non-radioactive tool that is often used for functional nerve examinations to detect brain dysfunction caused by non-structural lesions of the brain. [0003] The combination of EEG technology and complex network is one of the current research hotspots in brain science, bra...

AI Technical Summary

Problems solved by technology

However, the number of electrodes for collecting EEG signals is generally small, and the connection rules of the brain cannot be fully explored, resulting in low classification accuracy.

Images