Brain effect connection network learning method based on space-time diagram convolution model

Abstract

The invention discloses a brain effect connection network learning method based on a space-time diagram convolution model, and belongs to the application fields of deep learning algorithms, brain science and artificial intelligence. The method specifically comprises the following steps: setting parameters, extracting time features of fMRI data by a time convolution network, extracting space features of the fMRI data by a graph convolution network, and learning a brain effect connection network in a training process of minimizing a joint loss function. According to the method, the advantages of strong feature learning ability and good model generalization of the time convolution network and the graph convolution network are utilized, deep time and space features of the fMRI data are effectively extracted, and the model accurately and automatically learns the effect connection network in the process of predicting the brain region time sequence. Therefore, the method provided by the invention has the advantages of strong feature extraction capability, high accuracy, good model generalization capability and the like, and can effectively relieve the problems in the conventional brain effect connection network learning method.

Description

technical field [0001] The invention belongs to the fields of brain science research, neural network deep learning theory and application research, and specifically relates to a brain effect connection learning method based on a spatiotemporal graph convolution model. Background technique [0002] The human brain connectome research attempts to establish a brain network group map that describes different living human brain functions and structures from multiple levels; the brain effect connection network is a graph model composed of nodes and directed edges, in which nodes are usually defined as brains. Areas, directed edges describe the causal effect of one brain area on the neural activity of another brain area. At present, using computational methods to learn brain effect connection networks from functional magnetic resonance imaging (fMRI) data of the human brain has become a frontier hotspot in this research. [0003] In recent years, with the continuous integration of...

AI Technical Summary

Problems solved by technology

However, these current methods fail to fully extract the temporal and spatial features of fMRI data, which greatly restricts the accuracy of model learning.

Images