Covid-19 Classification System using Deep Convolutional Neural Networks (DCNN)

Date
2020
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
The effect of Covid-19 pandemic on the health and well-being of the global population was devastating and is still continuing. An important step to fight this COVID-19 is to implement a successful and less time-consuming screening process of contaminated patients, and one of the vital screening processes is radiological imaging using chest radiography. The main goal of this project was to automatically detect COVID‐19 patients using digital chest x‐ ray images while maximizing the accuracy in detection using deep convolutional neural networks (DCNN). The dataset consists 8723 chest x‐ray images. In this project, DCNN based model VGG-19, Resnet-50 and a custom CNN model with transfer learning have been proposed for the detection of coronavirus infected patients using chest X-ray radiographs and gives a classification accuracy of more than 97% training accuracy. All images were of the same size and stored in JPEG and PNG. The average sensitivity, specificity, and accuracy of the lung classification using the proposed models’ has shown very good results. The results demonstrate that transfer learning showed robust performance and finally because of the smaller size of our custom model it is easily deployable for COVID-19 detection
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN