Hybridization of Convolutional Neural Networks with Wavelet Architecture for COVID-19 Detection

Abstract

Coronavirus disease is an infectious disease caused by perilous viruses. According to the World Health Organization (WHO) updated reports, the number of people infected with Coronavirus-2019 (COVID-19) and death rate rises rapidly every day. The limited number of COVID-19 test kits available in hospitals could not meet with the demand of daily growing cases. The ability to diagnose COVID-19 suspected cases accurately and quickly is essential for prompt quarantine and medical treatment. The goal of this research is to implement a novel system called Convolution Neural Network with Wavelet Transformation (CNN-WT) to assist radiologists for the automatic COVID-19 detection through chest X-ray images to counter the outbreak of SARS-CoV-2. The proposed CNN-WT method employing X-ray imaging has the potential to be very beneficial for the medical sector in dealing with mass testing circumstances in pandemics like COVID-19. The dataset used for experimentation consists of 219 chest X-Ray images with confirmed COVID-19 cases and 219 images of healthy people. The suggested model's efficacy is evaluated using 5-fold cross-validation. The CNN-WT model yielded an average accuracy of 98.63%, which is 1.36% higher than the general CNN architecture.