Abnormal brain connection prediction system, method and device and readable storage medium

Abstract

The invention discloses an abnormal brain connection prediction system, method and device and a readable storage medium, and the method comprises the steps: automatically extracting high-order correlation features in different modes and high-order complementary features between different modes through a deep learning method; and realizing the analysis of abnormal connection of the multi-modal brain network and prediction of different cognitive diseases through an adversarial training method. The method solves the problem that an existing method cannot accurately evaluate the change rule of brain structural morphology and functional connection. According to the method, a prior knowledge guide model is used for learning interpretable characterization, the consistency of different modal characterization distribution is restrained through a paired collaborative discriminator, and then brain graph data is reconstructed for feature codes through a reverse generator and a decoder; and finally, inter-modal and intra-modal high-order correlation features are extracted through a hypergraph perception fusion module, and an adversarial loss function, a reconstruction loss function and a classification loss function are set to guide model learning so as to achieve the purpose of mining the abnormal brain connectivity of the Alzheimer's disease.

Description

technical field [0001] The invention belongs to the technical field of brain science and image modeling, relates to adversarial learning and hypergraph perception fusion technology, and specifically relates to an abnormal brain connection prediction system, method, device and readable storage medium. Background technique [0002] The existing auxiliary diagnosis and treatment models for Alzheimer's disease only achieve sample classification and prediction tasks, and cannot accurately evaluate the changes in brain structure, morphology, and functional connectivity. Diagnostics provide key biomarkers. Clinical research in brain science has shown that early Alzheimer's patients exhibit changes in brain structure or functional connectivity. [0003] At present, the research on the diagnosis of AD (Alzheimer's disease) using graph-based methods can be divided into two categories: methods based on graph convolution (GCN, Graph convolutional network) and methods based on hypergrap...

AI Technical Summary

Problems solved by technology

[0005] (1) Existing data-driven methods have completed the tasks of sample classification and prediction, which may ignore the accurate evaluation of different features of brain structure or functional connectivity, and lack biological explanations

[0006] (2) Existing hypergraph-based methods can analyze the abnormal connection characteristics of brain networks, but cannot establish high-order correlations within multimodal data and between modalities, so that they cannot fully mine the potential complementary information in the data

Images