Brain disease classification method and system

Through the brain disease classification method of multimodal data fusion and dynamic modeling, the problem of difficulty in comprehensively characterizing the pathological characteristics of brain diseases in the prior art is solved, and accurate brain disease diagnosis and explainable clinical support are achieved.

CN120473071AActive Publication Date: 2025-08-12THE FIRST AFFILIATED HOSPITAL OF FUJIAN MEDICAL UNIV
4 Cites 14 Cited by

Patent Information

Application Number
CN202510969533.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-15
Publication Date
2025-08-12
Estimated Expiration
2045-07-15

AI Technical Summary

Technical Problem

The existing brain disease diagnosis methods mainly rely on a single type of brain scan data, which is difficult to fully reflect the complex pathological mechanisms of brain diseases. In addition, traditional computer-aided diagnostic systems have limited integration capabilities for multi-source data, and lack an explanation of the underlying biological mechanisms of the disease.

Method used

By collecting multimodal brain imaging information and cognitive behavior information, a time-varying neural network model is constructed, and resting state fused timing signals, diffusion tensor imaging structure connection matrix and T1 weighted anatomical features are dynamically fused, and multi-task joint learning is performed to output quantitative diagnostic results of disease classification probability, neural circuit abnormal markers and cognitive function decay trajectory.

Benefits of technology

It realizes a comprehensive representation of the pathological mechanism of brain diseases, provides accurate classification results and interpretable clinical decision support, and improves the accuracy of diagnosis and biological interpretation ability.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a brain disease classification method and system. Precise diagnosis is realized through multi-modal data fusion and dynamic modeling. The method comprises the following steps: collecting multi-modal brain image information and cognitive behavior information of a user; performing dynamic function connection analysis on the resting state functional magnetic resonance time sequence signal to obtain a time-varying brain network feature matrix, and performing white matter fiber bundle topology reconstruction on a structure connection matrix; constructing a four-dimensional correlation tensor by using the time-varying network features, the structural connection weights and the anatomical features through a neurodynamic model; performing multi-task learning on the four-dimensional correlation tensor based on a time-varying graph neural network model, and outputting a quantitative diagnosis result; and finally generating a clinical classification report integrating the individualized brain network remodeling target, the disease progress risk layering and the treatment response prediction. By dynamically fusing the structure and functional features, comprehensive characterization of the pathological mechanism of the brain disease is realized, and decision support with both accuracy and interpretation is provided for clinical diagnosis.
Need to check novelty before this filing date? Find Prior Art