A personalized brain function network construction and evaluation method for brain-computer interface regulation

By combining neurodynamic equations and diffusion models with self-supervised learning, a personalized dynamic brain function network is constructed, which solves the problem of insufficient brain function network in personalized partitioning and cross-scenario generalization, and realizes the precise and large-scale application of brain-computer interface neural modulation.

CN121766152BActive Publication Date: 2026-06-23SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF 4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
Filing Date
2026-03-03
Publication Date
2026-06-23

AI Technical Summary

Technical Problem

Existing methods for constructing brain functional networks suffer from deficiencies in personalized partitioning, insufficient characterization of nonlinear relationships, and weak generalization ability across scenarios, making it difficult to support the precise and large-scale clinical application of brain-computer interface neuromodulation.

Method used

We employ a personalized neural activity pattern representation based on neurodynamic equations, combined with a diffusion model and a self-supervised learning framework, to construct a personalized dynamic brain function network. The network performance is then evaluated using a digital twin brain simulation environment.

Benefits of technology

It significantly improves the personalized expressiveness and physiological rationality of functional connectivity, enhances the consistency of activities within the region and the ability to generalize across domains, and supports precise target localization and multi-scenario personalized modeling of brain-computer interface neuromodulation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121766152B_ABST
    Figure CN121766152B_ABST
Patent Text Reader

Abstract

The application belongs to a network construction evaluation method, aiming at the technical problems that the existing brain function network construction method lacks personalized partition, the nonlinear neural correlation is not well described, the cross-scene generalization ability is weak, and it is difficult to support the precision and large-scale clinical application of brain-computer interface neural regulation, a personalized brain function network construction and evaluation method for brain-computer interface regulation is provided, the personalized brain function network is constructed based on the neural activity mode representation, the personalized brain function network construction for heterogeneous fMRI data is realized by fusing the neural dynamics knowledge constraint and the data-driven modeling, and the personalized brain function network construction for heterogeneous fMRI data can be used as a general modeling tool, and reliable technical support is provided for brain-computer interface neural regulation.
Need to check novelty before this filing date? Find Prior Art