基于脑网络参数优化的青少年抑郁症患者与健康人群分类识别研究  

Study on classification and identification of depressed patients and healthy people among adolescents based on optimization of brain characteristics of network

作　　者：沈潇童 王玥 毕卉 曹音[3] 王苏弘[4] 邹凌[1,2] SHEN Xiaotong;WANG Yue;BI Hui;CAO Yin;WANG Suhong;ZOU Ling(School of Information Science and Engineering,Chang Zhou University,Changzhou,Jiangsu 213164,P.R.China;Changzhou Key Laboratory of Biomedical Information Technology,Changzhou,Jiangsu 213164,P.R.China;Changzhou NO.2 People's Hospital,Chang Zhou,Jiangsu 213003,P.R.China;The First People's Hospital of Changzhou,Chang Zhou,Jiangsu 213003,P.R.China)

机构地区：[1]常州大学信息科学与工程学院,江苏常州213164 [2]常州市生物医学信息技术重点实验室,江苏常州213164 [3]常州市第二人民医院,江苏常州213003 [4]常州市第一人民医院,江苏常州213003

出　　处：《生物医学工程学杂志》2020年第6期1037-1044,1055,共9页Journal of Biomedical Engineering

基　　金：江苏省科技厅社会发展项目(BE2018638);常州市社会发展项目(CE20195025);首批中外合作办学平台联合科研项目“人机智能与交互国际联合实验室”;江苏省研究生培养创新计划项目(KYCX20_2559)。

摘　　要：为了增强基于脑电图信号的青少年抑郁症计算机辅助诊断精度,本研究采集了32名女性青少年静息状态下闭眼4 min的脑电图信号,其中抑郁症患者16名(抑郁组)、健康受试者16名(对照组),年均(16.3±1.3)岁。首先,根据信号之间的相位同步性,使用相位锁定值(PLV)方法,分别在θ和α频段下计算脑功能连接。然后基于图论方法,再分别计算加权网络的强度、平均特征路径长度和平均聚类系数(P<0.05)。接下来,利用多重阈值和网络参数的关系,提取各个网络参数的曲线下面积(AUC)作为新特征(P<0.05)。最后,使用支持向量机(SVM),将两组受试者的网络参数和网络参数的AUC作为特征进行分类。研究结果显示,使用强度、平均特征路径长度、平均聚类系数作为特征,在θ频段,其分类精度分别由69%提高到71%、66%提高到77%、50%提高到68%;在α频段,其精度分别由72%提高到79%、69%提高到82%、65%提高到75%;且整体来看,在α频段使网络参数的AUC作为特征,分类精度比网络参数特征提升了10%左右,而在θ频段,仅平均聚类系数AUC的分类精度提升了18%。本研究结果证明,基于图论量化脑功能网络并对网络参数特征优化,能够对青少年抑郁症的计算机辅助诊断提供一定的帮助和理论支撑。To enhance the accuracy of computer-aided diagnosis of adolescent depression based on electroencephalogram signals,this study collected signals of 32 female adolescents(16 depressed and 16 healthy,age:16.3±1.3)with eyes colsed for 4 min in a resting state.First,based on the phase synchronization between the signals,the phase-locked value(PLV)method was used to calculate brain functional connectivity in theθandαfrequency bands,respectively.Then based on the graph theory method,the network parameters,such as strength of the weighted network,average characteristic path length,and average clustering coefficient,were calculated separately(P<0.05).Next,using the relationship between multiple thresholds and network parameters,the area under the curve(AUC)of each network parameter was extracted as new features(P<0.05).Finally,support vector machine(SVM)was used to classify the two groups with the network parameters and their AUC as features.The study results show that with strength,average characteristic path length,and average clustering coefficient as features,the classification accuracy in theθband is increased from 69%to 71%,66%to 77%,and 50%to 68%,respectively.In theαband,the accuracy is increased from 72%to 79%,69%to 82%,and 65%to 75%,respectively.And from overall view,when AUC of network parameters was used as a feature in theαband,the classification accuracy is improved compared to the network parameter feature.In theθband,only the AUC of average clustering coefficient was applied to classification,and the accuracy is improved by 17.6%.The study proved that based on graph theory,the method of feature optimization of brain function network could provide some theoretical support for the computer-aided diagnosis of adolescent depression.

关 键 词：抑郁症 脑电图 网络 阈值 特征优化 计算机辅助诊断 

分 类 号：R749.4[医药卫生—神经病学与精神病学]