Deep Learning Models-Based CT-Scan Image Classification for Automated Screening of COVID-19

COVID-19 (coronavirus) is the most transmissible disease, caused by the SARS-CoV-2 virus that severely infects the lungs and the upper respiratory tract of the human body. This virus badly affected the lives and wellness of millions of people worldwide and spread widely. Early diagnosis and timely treatment is the only way to control the spreading of coronavirus. Computed tomography (CT) scanning is the most emerging tool to diagnose several respiratory lungs problems, including COVID-19 infections. Manual scanning of COVID-19 subjects with chest CT scans is tedious and subject to human mistakes. Automated screening of COVID-19 using chest CT images may reduce the clinician's load and save the lives of thousands of people. Therefore, this paper presents the applications of deep learning models (DLMs) for the automated screening of Covid-19 using CT-scan images. In this work, two benchmarked DLMs namely, DarkNet19 and MobileNetV2, along with a newly developed less complex DLM are used for the screening of COVID-19 using CT-scan images. Transfer-learning is employed to train the benchmark DLMs. A repeated ten-fold holdout validation method is utilized to develop the DLMs. The highest classification accuracy of 98.91% is achieved using DarkNet19. The simulation results with the publicly available COVID-19 CT scan image dataset are included to show the effectiveness of the presented study.