COVID-19 Disease Detection Based on Machine Learning and Chest X-Ray Images

Abstract

Due to increasing population, automated illness identification has become a critical problem in medical research. An automated illness detection framework aids physicians in disease diagnosis by providing precise, consistent, and quick findings, as well as lowering the mortality rate. Coronavirus (COVID-19) has expanded worldwide and is now one of the most severe and acute disorders. To avoid COVID-19 from spreading, making an automatic detection system based on X-ray chest pictures ought to be the quickest diagnostic alternative. The goal of this research is to come up with the best model for detecting COVID-19 diagnosis with the greatest accuracy. Therefore, four models, Convolutional Neural Networks, Residual Network 50, Visual Geometry Group 16 (VGG16), and VGG19, have been evaluated using the same images preprocessing method. In this study, performance metrics include accuracy, precision, recall, and F1 scores are used for evaluating proposed method. According to our findings, the VGG16 model is a viable candidate for detecting COVID-19 instances, because it has highest accuracy; in result overall accuracy of 98.44% in training phase, 98.05% invalidation phase and 96.05% in testing phase is obtained. The results of other performance measurements are shown in the result section, demonstrating that the majority of the approaches are more than 90% accurate. Based on these results, radiologists may find the proposed VGG16 model to be an intriguing and a helpful tool for detecting and diagnosing COVID-19 patients quickly.

Keywords

• covid-19
• convolutional neural networks
• residual network 50
• visual geometry group 19
• visual geometry group 16
• x-ray image
• machine learning