COVID-19 prediction from chest X-ray images using deep convolutional neural network

ABSTRACT

One of the biggest challenges that the world is facing right now is the identification of COVID-19 infection, given no potential vaccine for the fast-spreading virus. Ongoing insights demonstrate that the number of individuals infected with COVID-19 is expanding exponentially, with more than 40 million confirmed cases around the world. One of the pivotal steps in battling COVID-19 is the capacity to recognize the infected patients sufficiently early and put them under isolation. One of the quickest approaches is to predict the illness from radiography and radiology pictures. Propelled by prior works, I present a machine learning binary classification model-driven deep convolutional neural network to predict COVID-19 from chest X-Ray images. A blend of Dr. Joseph Paul Cohen’s open-sourced database and Kaggle’s Chest X-ray competitions dataset were used to train our model. The predictions result of the model exhibit promising performance with an accuracy of 95.61%. Training and validation accuracy graphs along with training and validation loss graphs were plotted for a better comprehension of our model. Further evaluation of the model was done by calculating standard evaluation metrics where 100% sensitivity, 93.33% specificity, 93.75% precision, and F1-score of 96.77% were achieved. The results exhibit that advanced machine learning methods combined with radiological imaging proved to be a deployable methodology for correct diagnosis of COVID-19, and can likewise be assistive to defeat the issues like shortage of testing kits, time-consuming, and expensive testing methods. © 2022 Elsevier Inc. All rights reserved.