Automatic Detection of COVID-19 Using a Stacked Denoising Convolutional Autoencoder

作     者：Habib Dhahri Besma Rabhi Slaheddine Chelbi Omar Almutiry Awais Mahmood Adel M.Alimi 

作者机构：College of Applied Computer Sciences(CACS)King Saud UniversityRiyadh11543Saudi Arabia Faculty of Sciences and Technology of Sidi BouzidUniversity of KairouanKairouanTunisia National School of Engineers(ENIS)University of SfaxTunisia Department of Computer SciencesCollege of Sciences and Arts in UnaizahQassim UniversityAl-QassimKingdom of Saudi Arabia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2021年第69卷第12期

页      面：3259-3274页

核心收录：

学科分类：0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0701[理学-数学] 0801[工学-力学（可授工学、理学学位）] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through research Group No.RG-1441-379 and for their technical support 

主　　题：Stacked autoencoder augmentation multiclassification COVID-19 convolutional neural network 

摘      要：The exponential increase in new coronavirus disease 2019(COVID-19)cases and deaths has made COVID-19 the leading cause of death in many ***,in this study,we propose an efficient technique for the automatic detection of COVID-19 and pneumonia based on X-ray images.A stacked denoising convolutional autoencoder(SDCA)model was proposed to classify X-ray images into three classes:normal,pneumonia,and *** SDCA model was used to obtain a good representation of the input data and extract the relevant features from noisy *** proposed model’s architecture mainly composed of eight autoencoders,which were fed to two dense layers and SoftMax *** proposed model was evaluated with 6356 images from the datasets from different *** experiments and evaluation of the proposed model were applied to an 80/20 training/validation split and for five cross-validation data splitting,*** metrics used for the SDCA model were the classification accuracy,precision,sensitivity,and specificity for both *** results demonstrated the superiority of the proposed model in classifying X-ray images with high accuracy of 96.8%.Therefore,this model can help physicians accelerate COVID-19 diagnosis.