Residual Attention Deep SVDD for COVID-19 Diagnosis Using CT Scans

作     者：Akram Ali Alhadad Omar Tarawneh Reham R.Mostafa Hazem M.El-Bakry 

作者机构：Information Systems DepartmentFaculty of Computers and InformationMansoura UniversityMansoura35511Egypt Computer Science DepartmentIbb UniversityIbbYemen SE DepartmentFaculty of Computer Sciences and InformaticsAmman Arab UniversityAmman11953Jordan 

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

年 卷 期：2023年第74卷第2期

页      面：3333-3350页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 1002[医学-临床医学] 081104[工学-模式识别与智能系统] 08[工学] 100201[医学-内科学(含：心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 10[医学] 

主　　题：Deep learning deep SVDD residual attention anomaly detection COVID-19 Coronavirus 

摘      要：COVID-19 is the common name of the disease caused by the novel coronavirus(2019-nCoV)that appeared in Wuhan,China in *** the infected people is the most important factor in the fight against the *** gold-standard test to diagnose COVID-19 is polymerase chain reaction(PCR),but it takes 5–6 h and,in the early stages of infection,may produce false-negative *** Computed Tomography(CT)images to diagnose patients infected with COVID-19 has become an urgent *** this study,we propose a residual attention deep support vector data description SVDD(RADSVDD)approach to diagnose *** is a novel approach combining residual attention with deep support vector data description(DSVDD)to classify the CT *** the best of our knowledge,we are the first to combine residual attention with DSVDD in general,and specifically in the diagnosis of *** attention with DSVDD naively may cause model *** in the proposed RADSVDD guides the network during training and enables quick learning,residual connectivity prevents vanishing *** approach consists of three models,each model is devoted to recognizing one certain disease and classifying other diseases as *** models learn in an end-to-end *** proposed approach attained high performance in classifying CT images into intact,COVID-19,and non-COVID-19 *** evaluate the proposed approach,we created a dataset from published datasets and had it assessed by an experienced *** proposed approach achieved high performance,with the normal model attained sensitivity(0.96–0.98),specificity(0.97–0.99),F1-score(0.97–0.98),and area under the receiver operator curve(AUC)0.99;the COVID-19 model attained sensitivity(0.97–0.98),specificity(0.97–0.99),F1-score(0.97–0.99),and AUC 0.99;and the non-COVID pneumoniamodel attained sensitivity(0.97–1),specificity(0.98–0.99),F1-score(0.97–0.99),and AUC 0.99.