Graph-convolutional-neural-network-based auxiliary diagnosis method for Alzheimer's disease

Abstract

The invention relates to a graph-convolutional-neural-network-based auxiliary diagnosis method for the Alzheimer's disease. The method comprises the following steps: processing a brain function magnetic resonance image to obtain a time sequence of each brain region; calculating a Pearson correlation coefficient between any two time sequences in the time sequences of the brain regions to obtain a brain function connection network using each time sequence as a node and the Pearson correlation coefficient as a weight of a connection edge between the two nodes; removing all edges with the weightssmaller than a set threshold and simplifying the brain function connection network to obtain graph structure data; and designing a graph convolutional neural network model, training the designed graphconvolutional neural network model by using the graph structure data, using a training result with the best performance in a verification set as an auxiliary diagnosis model, and outputting a diseasestate corresponding to the whole graph structure. Therefore, compared with the traditional method, the method has the advantages that the detection accuracy is higher, and the advanced auxiliary diagnosis classification level on the disease is obtained.

Description

technical field [0001] The invention relates to the technical field of computer-aided diagnosis, in particular to a method for aided diagnosis of Alzheimer's disease based on a graph convolutional neural network. Background technique [0002] Alzheimer's disease is the main cause of senile dementia, and it is a neurodegenerative disease with insidious onset and progressive development. After the disease progresses to an advanced stage, it will seriously affect the interpersonal communication, work, study and daily life of the elderly, and bring a relatively heavy burden to family members and society. The incidence rate of the disease is about 5% among people over the age of 65, and it is as high as about 20% over the age of 85. Today, the problem of population aging is becoming more and more serious, and the prevention and treatment of Alzheimer's disease has attracted governments all over the world. and the general attention of the medical community. As of 2016, there wer...

AI Technical Summary

Problems solved by technology

It is difficult for these methods to further mine the large amount of information contained in the brain neuroimaging data. At the same time, due to the manual feature extraction, the classification performance of the model is also unsatisfactory.

Images