基于多模态信号融合的踝关节痉挛动态评估方法及系统

By using multimodal signal fusion technology, electromyographic and angular signals during walking are collected and processed to generate a dynamic spasticity index. This solves the problem of inaccurate static assessment in existing technologies and enables real-time, dynamic assessment of the degree of ankle spasticity after stroke, supporting precise rehabilitation treatment.

CN120501386BActive Publication Date: 2026-07-17XIEHE HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI & TECH UNIV +1

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
XIEHE HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI & TECH UNIV
Filing Date
2025-07-21
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing spasticity assessment techniques mainly rely on subjective scale assessments in a resting state, lacking fusion analysis of multimodal signals. This results in incomplete and inaccurate assessment results, failing to accurately reflect the state of spasticity in daily activities after stroke, and limiting the development of refined rehabilitation programs.

Method used

The high-precision electromyography (EMG) signal acquisition module and ankle kinematics measurement module acquire EMG and angular signals during walking. These signals are then processed in depth using a signal processing and feature extraction unit. A dynamic spasticity index is generated using a multimodal fusion and spasticity assessment model, enabling real-time, dynamic, and quantitative assessment of the degree of ankle spasticity.

Benefits of technology

It enables real-time, dynamic, and quantitative assessment of the degree of ankle spasticity after stroke, breaking through the limitations of traditional static assessment, providing precise quantitative tools and real-time feedback, and supporting more accurate rehabilitation treatment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120501386B_ABST
    Figure CN120501386B_ABST
Patent Text Reader

Abstract

本申请公开了基于多模态信号融合的踝关节痉挛动态评估方法,包括:通过高精度肌电信号采集模块采集步行过程中的肌电信号,同时通过踝关节运动学测量模块采集踝关节的角度信号;对采集的肌电信号提取包括时域特征和频域特征的肌电特征,捕捉痉挛瞬态特征,采用动态时间规整算法检测角度轨迹偏离度;采用注意力机制自动分配多模态权重,生成融合特征向量;将融合特征向量输入动态痉挛指数模型,获取实时动态痉挛指数,实现痉挛状态的动态评估。本发明还公开了基于多模态信号融合的踝关节痉挛动态评估系统、相应的设备及存储介质。本发明能够实现对脑卒中后踝关节痉挛程度的实时、动态、量化评估。
Need to check novelty before this filing date? Find Prior Art