Automatic Detection of COVID-19 Disease in Chest X-Ray Images using Deep Neural Networks
Mohammad Mahmudur Rahman Khan, Shadman Sakib, Md. Abu Bakr Siddique, Madiha Chowdhury, Ziad Hossain, Anas Aziz, Nowrin Yasmin
Abstract
The worldwide spread of COVID-19 has marked a devastating impact on the global economy and public health. One of the significant steps of COVID-19 affected patient's treatment is the faster and accurate detection of the symptoms which is the motivational center of this study. In this paper, we have analyzed the performances of six artificial deep neural networks (2-D CNN, ResNet-50, InceptionResNetV2, InceptionV3, DenseNet201, and MobileNetV2) for COVID-19 detection from the chest X-rays. Our dataset consists of 2905 chest X-rays of three categories: COVID-19 affected (219 cases), Viral Pneumonia affected (1345 cases), and Normal Chest X-rays (1341 cases). Among the implemented neural networks, ResNet-50 demonstrated reasonable performance in classifying different cases with an overall accuracy of 96.91%. Most importantly, the model has shown a significantly good performance in detecting the COVID-19 cases in the test dataset (Precision = 1.00, Sensitivity = 1.00, Specificity = 1.00, and F1-score = 1.00). Therefore, among the deep neural networks presented in this paper, ResNet-50 can be adapted as a reliable method for faster and accurate COVID-19 affected case detection.