Automated Methods for Detection and Classification Pneumonia Based on X-Ray Images Using Deep Learning

Recently, researchers, specialists, and companies around the world are rolling out deep learning and image processing-based systems that can fastly process hundreds of X-Ray and Computed Tomography (CT) images to accelerate the diagnosis of pneumonia such as SARS, covid-19, etc., and aid in its containment. Medical image analysis is one of the most promising research areas; it provides facilities for diagnosis and making decisions of several diseases such as MERS, covid-19, etc. In this paper, we present a comparison of recent deep convolutional neural network (CNN) architectures for automatic binary classification of pneumonia images based on fined tuned versions of (VGG16, VGG19, DenseNet201, Inception_ResNet_V2, Inception_V3, Resnet50, MobileNet_V2 and Xception) and a retraining of a baseline CNN. The proposed work has been tested using chest X-Ray & CT dataset, which contains 6087 images (4504 pneumonia and 1583 normal). As a result, we can conclude that the fine-tuned version of Resnet50 shows highly satisfactory performance with rate of increase in training and testing accuracy (more than 96% of accuracy).