Weighted graph regularization sparse brain network construction method

Abstract

The invention discloses a weighted graph regularization sparse brain network construction method. According to the method, on the basis of analysis of keeping similar local manifold characteristics ofsimilar data in original data space after projection, constrained modeling is carried out on association between brain connection by using a graph regularization item; with consideration of correlation analysis, the similarity degree of essences in a time sequence signal sequence of a brain area can be measured, sparse modeling is constrained by using measured functional connection strength priorinformation, and a weighted sparse regularization item is established; and then combined modeling is carried out on the whole brain function network and a brain network with the biological significance is constructed. According to the invention, on the basis of integration of correlation analysis, sparsity and graph regularization constraint into the unified modeling frame, a brain function network is constructed effectively by utilizing the similarity and locality of functional magnetic resonance brain image data fully; and the method is also used for neurological disease identification andbiological marker analysis.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a weighted graph regularization sparse brain network construction method. Background technique [0002] Functional magnetic resonance imaging (fMRI) is an emerging neuroimaging modality that uses magnetic resonance imaging to measure brain activity by detecting changes associated with blood flow. The blood oxygen level-dependent (BOLD) signal in the resting-state functional magnetic resonance image (rs-fMRI) can reflect the low-frequency spontaneous fluctuation of the brain in the resting state, which is related to the brain's intrinsic neural Activities are closely related. Analysis of functional brain connectivity (that is, the interrelationships between brain regions in brain networks) based on resting-state fMRI images has shown great promise in understanding the function of brain regions and identifying biomarkers in patients with neuropsychiatric disorders...

AI Technical Summary

Problems solved by technology

[0004] However, in l 1 In a norm-regularized linear regression model, the sparsity constraint term penalizes constraints equally for each connected edge, which means that when learning the sparse representation of the target ROI, the BOLD signals of all remaining ROIs are treated equally, and brain-by-brain Under the constraints of sparsity, independent modeling and solving of regions can easily cause similar brain region signals to be sparsely reconstructed into coefficient expressions with large differences

Network modeling methods based on correlation and sparsity are not very effective in predicting and classifying mental disorders in practical applications

Images