Transfer learning approach to COVID-19 prediction from chest X-ray images

All countries and societies have been severely affected by the COVID-19 pandemic in many several different ways especially in sectors like healthcare, education, tourism, and so on. During this period, researchers all over the world have been conducting studies, investigating and developing techniques to solve the problems caused by the pandemic. In this work, making use of real-world images, we applied Convolutional Neural Networks to chest X-ray images to predict whether a patient has COVID-19, Viral Pneumonia, or no infection. Initially, we utilized transfer learning to fine tune a number of pre-trained DenseNet, Inception-v3, Inception-ResNet-v2, ResNet, VGG, and Xception models, which are very well-known architectures due to their success in image processing tasks. While the achieved performance with these models was encouraging, we ensembled three models to obtain more accurate and reliable results. Finally, our ensemble model outperformed all other models with an F -Score of 99%.