An auxiliary diagnosis system for Alzheimer's disease based on fnirs and graph neural network

Abstract

The disclosure discloses an auxiliary diagnosis system for Alzheimer's disease based on fNIRS and a graph neural network, including an EEG detection module using a functional near-infrared spectrum imaging device to oxygenate the brains of AD patients and normal people in an active state Multi-channel detection of hemoglobin, deoxygenated hemoglobin and total hemoglobin, and construction of the fNIRS dataset; the adjacency matrix construction module uses the correlation between channels to construct the adjacency matrix for the fNIRS dataset; the node feature matrix construction module performs feature extraction on the fNIRS dataset, Construct the node feature matrix; the graph structure building module constructs the AD patient graph structure and the normal person graph structure respectively according to the adjacency matrix and the node feature matrix to form a training data set; the Alzheimer's disease recognition module constructs a graph neural network based on the training data set pair Carry out training, use the trained graph neural network to identify the test data set of the person to be tested, and output the auxiliary diagnosis result. Realize the use of graph neural networks in the classification of fNIRS data.

Description

technical field [0001] The present disclosure relates to the technical field of deep learning, in particular to an auxiliary diagnosis system for Alzheimer's disease based on fNIRS and a graph neural network. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Graph Convolutional Neural Network (GCN) directly acts on the graph structure through a feature extractor, which is used to model the dependencies between graph nodes. Currently, most graph convolutional neural networks have a similar structure due to the use of convolution operators that can share weights across the graph. Compared with cumbersome fully-connected models, this neural network structure has at least three advantages in graph data: 1) it avoids the parameter explosion associated with fully-connected layers; 2) it allows parameters to be shared across the network and avoid...

AI Technical Summary

Problems solved by technology

The inventors found that patients with cognitive impairment have differences in physiological signals such as EEG signals and normal people, and the parameters of EEG signals in the time domain and frequency domain are different from those of normal people; at present, there is no use of fNIRS data as Based on the input of the GCN network, and according to the fact that patients with cognitive impairment have differences in physiological signals such as EEG signals and normal people, a scheme for auxiliary diagnosis of Alzheimer's disease is proposed.

Images