Subject classification method fusing multiple human brain atlases based on graph convolutional neural network

Abstract

The invention discloses a subject classification method fusing multiple human brain atlases based on a graph convolutional neural network. The human brain atlas is a data structure and represents interaction information between different brain regions in the human brain. The method performs classification prediction on a subject by identifying five human brain atlases of the subject, and belongs to the field of brain science research and deep learning research. The classification method comprises the following steps: acquiring and preprocessing human brain functional magnetic resonance time sequence signals; constructing five types of human brain atlases for each sample according to different functional connection strength calculation methods so as to obtain five data sets; constructing five graph convolutional neural network classifiers; carrying out training on the corresponding human brain atlas data sets separately, and therefore obtaining the binary classification capacity of thespecific human brain atlas; and integrating prediction results of the five graph convolutional neural network classifiers, and performing classification prediction on the subject, i.e., predicting which kind of person the subject belongs to.

Description

technical field [0001] The invention relates to the technical fields of brain science and deep learning, in particular to a subject classification method based on graph convolutional neural network fusion of multiple human brain atlases. Background technique [0002] Functional magnetic resonance imaging is a fast imaging technology. When a certain part of the brain is active, the blood flow increases, resulting in an enhanced functional magnetic resonance signal. Therefore, functional magnetic resonance imaging (fMRI) technology is widely used to detect blood oxygen in the brain activity, and then examine the functional activity changes in the relevant regions of the brain. A large number of experimental results show that some individual characteristics, such as age, are related to the functional connectivity network of the individual, so the functional connectivity network of the human brain is closely related to physiological characteristics, and the analysis of brain fun...

AI Technical Summary

Problems solved by technology

[0007] 1. Most of the existing classification studies based on human brain functional networks only use a single functional connection strength index, which is easily affected by its inherent shortcomings, which limits the classification performance of the classification model

[0008] 2. Most of the existing classification methods for human brain functional networks require a feature screening process. When the physiological mechanism is not clear, the classification accuracy and generalization performance of the model are easily limited by the feature screening process

[0009] 3. In the graph convolutional neural network classification model, there is a lack of consideration of the relationship between nodes at different levels

Images