Covid-19 Detection using Deep Convolutional Neural Networks from X-Ray Images

Abstract— The Novel Coronavirus generally, knows as COVID-19 which first appeared in Wuhan city of China December 2019, spread quickly around the world and became a pandemic. It has caused an overwhelming effect on daily lives, Public health, global economy. Many people have been affected died. is critical to control prevent disease by applying quick alternative diagnostic techniques. cases are rising day world, on-time diagnosis patients increasingly long difficult process. patient test kits costly not available for every individual poor countries. For this purpose, screening with established techniques like Chest X-ray images seems be effective method. This study used deep learning data augmentation publicly set train advanced CNN models it. proposed model was tested using state-of-the-art evaluation measures obtained better results. Our model, at (https://github.com/ieee8023/covid-chestxray-dataset) Non-COVID-19 (https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia). maximum accuracy achieved validation 96.67%. detection average F measure 98%, Area Under Curve (AUC) 99%. results demonstrate that proved easily deployable approach detection.