摘要
为了充分挖掘轻度认知障碍(MCI)患者的神经振荡耦合特征,本文分析对比了28名MCI患者(MCI组)与21名正常人(正常对照组)在六种异频组合下的耦合特征强度。结果表明,与正常对照组相比,MCI组在δ-θ节律组合下交叉频率耦合的全局相位同步指数差异具有统计学意义(P=0.025,d=0.398)。为了进一步验证此耦合特征,本文提出一种优化的卷积神经网络模型,该模型融入了时频数据增强模块与批归一化层,在防止过拟合的同时增强了模型的鲁棒性。基于此优化模型,以δ-θ节律组合下的锁相值矩阵作为模型输入的单一特征,对MCI患者的诊断正确率达(95.49±4.15)%,敏感性与特异性分别为(93.71±7.21)%和(97.50±5.34)%。本文研究结果表明,δ-θ节律组合下的锁相值矩阵特征能够充分反映MCI患者的认知状态,有利于辅助MCI诊断。
In order to fully explore the neural oscillatory coupling characteristics of patients with mild cognitive impairment(MCI),this paper analyzed and compared the strength of the coupling characteristics for 28 MCI patients and 21 normal subjects under six different-frequency combinations.The results showed that the difference in the global phase synchronization index of cross-frequency coupling under-0 rhythm combination was statistically significant in the MCI group compared with the normal control group(P=0.025,d=0.398).To further validate this coupling feature,this paper proposed an optimized convolutional neural network model that incorporated a time-frequency data enhancement module and batch normalization layers to prevent overfitting while enhancing the robustness of the model.Based on this optimized model,with the phase locking value matrix of 8-rhythm combination as the single input feature,the diagnostic accuracy of MCI patients was(95.49±4.15)%,sensitivity and specificity were(93.71±7.21)%and(97.50±5.34)%,respectively.The results showed that the characteristics of the phase locking value matrix under the combination of S-0 rhythms can adequately reflect the cognitive status of MCI patients,which is helpful to assist the diagnosis of MCI.
作者
李昕
王凯
景军
尹立勇
张莹
谢平
LI Xin;WANG Kai;JING Jun;YIN Liyong;ZHANG Ying;XIE Ping(School of Electrical Engineering,Yanshan University,Qinhuangdao,Hebei 066004,P.R.China;Measurement Technology and Instrumentation Key Lab of Hebei Province,Qinhuangdao,Hebei 066004,P.R.China;The First Hospital of Qinhuangdao,Qinhuangdao,Hebei 066004,P.R.China;Engineering Training Centre,Yanshan University,Qinhuangdao,Hebei 066004,P.R.China;Institute of Health and Wellness Industry Technology,Yanshan University,Qinhuangdao,Hebei 066004,P.R.China)
出处
《生物医学工程学杂志》
EI
CAS
北大核心
2023年第5期843-851,共9页
Journal of Biomedical Engineering
基金
国家自然科学基金资助项目(62076216)
河北省自然科学基金资助项目(F2019203515,F2022203005)
河北省科技计划项目(236Z2004G)
燕山大学秦皇岛市第一医院医工交叉特色专项(UY202201)。
关键词
交叉频率耦合
锁相值
数据增强
批标准化
Cross-frequency coupling
Phase locking value
Data enhancement
Batch normalization
