北京大学学报自然科学版 ›› 2024, Vol. 60 ›› Issue (1): 109-117.DOI: 10.13209/j.0479-8023.2023.089

上一篇    下一篇

基于足底压力和卷积长短期记忆神经网络的前交叉韧带断裂智能辅助诊断

李玳1, 王天牧2,3, 张思1, 秦跃2,3, 谢福贵2,3, 刘辛军2,3, 聂振国2,3,†, 黄红拾1,†   

  1. 1. 北京大学第三医院运动医学科, 北京大学运动医学研究所, 运动医学关节伤病北京市重点实验室, 运动创伤治疗技术与器械教育部工程研究中心, 北京 100191 2. 摩擦学国家重点实验室, 清华大学机械工程系, 北京 100084 3. 精密/超精密制造设备与控制北京市重点实验室, 清华大学机械工程系, 北京 100084
  • 收稿日期:2022-12-26 修回日期:2023-05-20 出版日期:2024-01-20 发布日期:2024-01-20
  • 通讯作者: 聂振国, E-mail: zhenguonie(at)tsinghua.edu.cn, 黄红拾, E-mail: huanghs(at)bjmu.edu.cn
  • 基金资助:
    国家自然科学基金–区域创新发展联合基金(U23A20471)、北京市科技新星计划交叉合作课题(20230484412)、北京市自然科学基金–海淀原始创新联合基金(L222138)、北京大学第三医院创新转化基金(BYSYZHKC2022119)和北京大学第三医院临床重点项目(BYSYZD2021012)资助 

Intelligent Diagnosis on Anterior Cruciate Ligament Deficiency Based on Plantar Pressure and ConvLSTM Neural Network

LI Dai1, WANG Tianmu2,3, ZHANG Si1, QIN Yue2,3, XIE Fugui2,3, LIU Xinjun2,3, NIE Zhenguo2,3,†, HUANG Hongshi1,†   

  1. 1. Department of Sports Medicine, Peking University Third Hospital, Institute of Sports Medicine of Peking University, Beijing Key Laboratory of Sports Injuries, Engineering Research Center of Sports Trauma Treatment Technology and Devices (Ministry of Education), Beijing 100191 2. The State Key Laboratory of Tribology, Department of Mechanical Engineering, Tsinghua University, Beijing 100084 3. Beijing Key Lab of Precision/Ultra-precision Manufacturing Equipments and Control, Department of Mechanical Engineering, Tsinghua University, Beijing 100084
  • Received:2022-12-26 Revised:2023-05-20 Online:2024-01-20 Published:2024-01-20
  • Contact: NIE Zhenguo, E-mail: zhenguonie(at)tsinghua.edu.cn, HUANG Hongshi, E-mail: huanghs(at)bjmu.edu.cn

摘要:

提出一种基于卷积长短期记忆神经网络的深度学习模型PressureConvLSTM, 用来提取行走过程中足底压力的空间特征和时序特征, 并进行步态分类。通过对前交叉韧带断裂患者的足底压力数据分析, 实现智能辅助诊断。结合临床数据的实验结果表明, PressureConvLSTM模型对前交叉韧带断裂的辅助诊断, 能够达到95%的预测准确度; 与卷积神经网络等其他模型相比, 准确度得到大幅度提升。

关键词: 智能诊断, 前交叉韧带断裂, 足底压力, 深度学习, 卷积长短期记忆神经网络

Abstract:

Based on Convolutional Long-Short Term Memory Neural Network, the authors proposed a deep learning method PressureConvLSTM to extract features during walking in both spatial and temporal dimensions. Classification based on plantar pressure of anterior cruciate ligament deficiency (ACLD) was applied to distinguish walking gait information. Experiment results combined with clinical data showed that PressureConvLSTM model obtained 95% test accuracy when diagnosing ACLD, which was well performed over other traditional deep learning models.

Key words: intelligent diagnosis, anterior cruciate ligament deficiency (ACLD), plantar pressure, deep learning; ConvLSTM neural network