Brain network classification method based on graph convolutional neural network

Abstract

The invention discloses a brain network classification method based on a graph convolutional neural network. The brain network classification method comprises the following steps that firstly, blood oxygenation level dependent signals of various brain regions are extracted from a brain function magnetic resonance image; secondly, a brain mapping capable of reflecting the topological structure features of functional connections between the brain regions is established; and finally, the established brain mapping and an actual diagnostic label are input into the graph convolutional neural networkfor feature learning and model training. The brain network classification method is used for brain network classification.

Description

technical field [0001] The invention relates to a brain network classification method based on a graph convolutional neural network, which belongs to the technical field of digital images. Background technique [0002] With the further development of society and science and technology, more and more diseases that were once considered incurable have been discovered and corresponding treatment methods have been proposed accordingly. As people pay more attention to their physical health, they also have higher requirements for medical technology. Especially at this stage, people are paying more and more attention to the medical methods of brain diseases. Because the human brain has an extremely complex structure and function, people hope to understand the pathological characteristics and diagnostic methods of brain diseases by understanding the mechanism of the brain. Countries around the world have invested a lot of manpower and material resources in research. For example, the ...

AI Technical Summary

Problems solved by technology

At present, the commonly used method is to directly use the functional connection weights of different brain regions as features for

Images