A method and apparatus for predicting early alzheimer's disease based on sfc features
By constructing a neural network model based on brain region sets and brain atlases, and using big data training with multimodal MRI images of the brain, the problem of insufficient accuracy in early Alzheimer's disease prediction in existing technologies has been solved, and in-depth mining and accurate prediction of the relationship between SC and FC networks have been achieved.
Patent Information
- Application Number
- CN202511697795.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-19
- Publication Date
- 2026-07-24
- Estimated Expiration
- 2045-11-19
AI Technical Summary
Existing technologies cannot effectively uncover the structural-functional coupling relationship between the brain's structural and functional connectivity networks, resulting in insufficient accuracy in early Alzheimer's disease prediction.
Based on brain region sets and brain atlases of multiple brain regions of interest, a structural matrix, a functional matrix, and a structural-functional coupling feature vector are constructed. A neural network model is designed, and big data acquisition and model training are carried out using multimodal MRI images of the brain to perform binary classification prediction.
By deeply exploring the SFC relationship between SC and FC networks, the accuracy of early Alzheimer's disease prediction was improved.