An Efficient CNN-Based Automated Diagnosis Framework from COVID-19 CT Images

作     者：Walid El-Shafai Noha A.El-Hag Ghada M.El-Banby Ashraf A.M.Khalaf Naglaa F.Soliman Abeer D.Algarni Fathi E.Abd El-Samie 

作者机构：Department Electronics and Electrical CommunicationsFaculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Electronics and Electrical CommunicationsFaculty of EngineeringMinia UniversityEgypt Department of Industrial Electronics and Control EngineeringFaculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Information TechnologyCollege of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi 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10期

页      面：1323-1341页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This research was funded by the Deanship of Scientific Research at Princess Nourah Bint Abdulrahman University through the Fast-track Research Funding Program 

主　　题：Classification segmentation COVID-19 CNN deep learning diagnosis applications 

摘      要：Corona Virus Disease-2019(COVID-19)continues to spread rapidly in the *** has dramatically affected daily lives,public health,and the world *** paper presents a segmentation and classification framework of COVID-19 images based on deep ***,the classification process is employed to discriminate between COVID-19,non-COVID,and pneumonia by Convolutional Neural Network(CNN).Then,the segmentation process is applied for COVID-19 and pneumonia CT ***,the resulting segmented images are used to identify the infected region,whether COVID-19 or *** proposed CNN consists of four Convolutional(Conv)layers,four batch normalization layers,and four Rectified Linear Units(ReLUs).The sizes of Conv layer used filters are 8,16,32,and *** maxpooling layers are employed with a stride of 2 and a 2×2 *** classification layer comprises a Fully-Connected(FC)layer and a soft-max activation function used to take the classification decision.A novel saliencybased region detection algorithm and an active contour segmentation strategy are applied to segment COVID-19 and pneumonia CT *** acquired findings substantiate the efficacy of the proposed framework for helping the specialists in automated diagnosis applications.