Brain disease classification method based on multi-template brain function and effect network fusion
CN119830108AActive Publication Date: 2025-04-15BEIJING UNIV OF TECH
Patent Information
- Application Number
- CN202411917924.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-24
- Publication Date
- 2025-04-15
- Estimated Expiration
- 2044-12-24
Smart Images
Figure CN119830108A_ABST
Abstract
The invention discloses a brain disease diagnosis method based on multi-template brain function and effect network fusion. The brain disease diagnosis method comprises the following steps: step 1, data acquisition; and step 2, multi-template data fusion. And step 3, FC network construction. And step 4, constructing an EC network. And step 5, carrying out FC EC network fusion. The double-branch function and effect connection construction method designed by the invention can accurately identify and construct the brain function and effect connection network. According to the functional effect fusion method based on self-adaption and self-attention, two kinds of network data can be effectively fused, and then the problem that the accuracy rate of diagnosing ASD through rs-fMRI data is still low is effectively solved. The brain disease diagnosis accuracy is high, and good interpretability is achieved in an ASD task.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Brain function network classification method based on variational auto-encoder
CN110188836A
Human brain function network classification method based on convolutional neural network
CN113040715A
Brain effect connection network learning method based on automatic variational auto-encoder
CN114219069A
Alzheimer's disease recognition method based on brain imaging genome characteristics
CN114596253A
Intelligent dynamic brain function monitoring system and method based on multi-modal data fusion
CN118526162A