基于变分自编码器的异常颈动脉早期识别和预测  

Early identification and prediction of abnormal carotid arteries based on variational autoencoder

作　　者：黄晓祥 胡咏梅[1] 吴丹[2] 任力杰[3] HUANG Xiaoxiang;HU Yongmei;WU Dan;REN Lijie(School of Control Science and Engineering,Shandong University,Jinan Shandong 250061,China;Shenzhen Institutes of Advanced Technology,Chinese Academy of Science,Shenzhen Guangdong 518055,China;Neurology Department,The Second People’s Hospital of Shenzhen,Shenzhen Guangdong 518028,China)

机构地区：[1]山东大学控制科学与工程学院,济南250061 [2]中国科学院深圳先进技术研究院,广东深圳518055 [3]深圳市第二人民医院神经内科,广东深圳518028

出　　处：《计算机应用》2021年第10期3082-3088,共7页journal of Computer Applications

基　　金：国家自然科学基金资助项目(81701788);深圳市科创委应用示范项目(KJYY20180703165202011)。

摘　　要：颈动脉狭窄、颈动脉内中膜厚度增加(CIMT)或颈动脉斑块等可导致脑卒中的发生。为实现脑卒中大规模初步筛查,提出基于医疗数据的改进的变分自编码器(VAE)来识别和预测异常颈动脉。首先,针对医疗数据存在缺失的情况,采用K近邻(KNN)、均值和众数相混合的方法(MKNN)以及改进的VAE对缺失数据进行填补以得到完整的数据集,从而提高数据的应用范围;接着,分析特征属性,并依据重要性对特征进行排序;然后,运用逻辑回归(LR)、支持向量机(SVM)、随机森林(RF)和极限梯度提升树(XGBT)这四种有监督学习方法结合遗传算法(GA)来建立异常颈动脉识别模型;最后,基于改进的VAE建立预测异常颈动脉的半监督模型。相较于基线模型,基于改进的VAE的半监督模型性能提升明显,灵敏度达到0.8938,特异性达到0.9272,F1值达到0.9105,分类准确率达到0.9105。实验结果表明,所建立的半监督模型可以用来识别异常颈动脉,进而作为一种识别脑卒中高危人群的工具,预防和减少脑卒中的发生。Carotid artery stenosis,Carotid Intima Media Thickness(CIMT)or carotid artery plaque may lead to stroke.For large-scale preliminary screening of stroke,an improved Variational AutoEncoder(VAE)based on medical data was proposed to predict and identify abnormal carotid arteries.Firstly,for the missing values in medical data,K-Nearest Neighbor(KNN),Mixture of mean,mode and KNN(MKNN)method and improved VAE were respectively used to impute the missed values to obtain the complete dataset,improving the application range of the data.Secondly,the feature attributes were analyzed and the features were ranked in order of importance.Thirdly,four supervised algorithms,Logistic Regression(LR),Support Vector Machine(SVM),Random Forest(RF)and eXtreme Gradient Boosting Tree(XGBT),were combined with Genetic Algorithm(GA)to build the abnormal carotid artery identification models.Finally,based on the improved VAE,a semi-supervised abnormal carotid artery prediction model was built.Compared to the performance of baseline model,the performance of the semi-supervised model based on the improved VAE improves significantly with sensitivity of 0.8938,specificity of 0.9272,F1-measure of 0.9105 and classification accuracy of 0.9105.Experimental results show that this semi-supervised model can be used to identify the abnormal carotid arteries and thus serves as a tool to recognize high-risk groups of stroke,preventing and reducing the occurrence of stroke.

关 键 词：颈动脉 脑卒中 变分自编码器 遗传算法 半监督模型 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]