Graph convolutional neural network evolution method for dynamic brain structure

Abstract

The invention discloses a graph convolutional neural network evolution method for a dynamic brain structure. A graph convolutional neural network is adopted to simulate an evolution process of evolving a normal human brain structure network into depression. A direction vector is introduced in the evolution process, the vector not only contains brain structure network information of a normal person, but also contains brain structure network information of a depression patient, the characteristics of the normal person and the depression patient can be extracted at the same time through graph convolution operation, and the evolution direction and the evolution degree can be controlled. The invention provides a graph convolutional neural network model of brain structure network evolution. A deep learning method based on a tensorflow framework is utilized, the cross entropy of a first evolution result and a real brain network of a depression patient is calculated, and a gradient descent optimization method is utilized to enable the evolution of the network to always face the direction of the brain network of the depression patient. And finally, a brain structure network close to a realdepression patient is outputted, and an evolution model closer to the real network is obtained.

Description

technical field [0001] The invention relates to a network evolution method, in particular to a graph convolutional neural network evolution method of a dynamic brain structure. Background technique [0002] Major depressive disorder is a serious illness second only to schizophrenia. Patients will experience pessimism, despair, hallucinations, delusions, functional decline, and severe suicide attempts, even suicide behaviors, posing a serious threat to human health. At present, the pathological mechanism of depression is still unclear, and there is still a lack of quantitative biomarkers to clearly define depression. But an important symptom of major depressive disorder is mood disturbance caused by changes in functional connectivity between brain regions. Therefore, brain network analysis is of great significance to the study of the pathological mechanism and diagnostic methods of major depressive disorder. Specifically, by constructing a brain structural network and estab...

AI Technical Summary

Problems solved by technology

But these changes only reveal the differences between the patients and the healthy population at a certain moment, and the consequences of the disease can not be traced back to the whole process of the disease

Images