一种基于电路自举和SNN的脑肿瘤分类方法及系统
By employing a brain tumor classification method based on circuit bootstrapping and SNN, and utilizing bootstrap circuits and temporal coding techniques, the problems of noise accumulation and high computational resource consumption in the encrypted domain are solved, achieving efficient and secure brain tumor classification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUAZHONG UNIV OF SCI & TECH
- Filing Date
- 2025-04-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing brain tumor classification methods suffer from excessive noise accumulation and high computational resource requirements in encrypted domains, resulting in low classification efficiency.
A brain tumor classification method based on circuit bootstrapping and SNN is adopted. The encrypted magnetic resonance images are processed through feature extraction layer, spiking neural unit and output spiking neuron layer. The bootstrap circuit suppresses noise and combines it with temporal coding to achieve efficient brain tumor classification.
It reduces the computational resource requirements, improves the efficiency of brain tumor classification in the encrypted domain, protects patient data privacy, and ensures the security and accuracy of the classification process.
Smart Images
Figure CN120543907B_ABST
Abstract
Citation Information
Patent Citations
Circuit bootstrapping method, and apparatus
WO2025030531A1