Lung Disease Detection in Chest X-ray Images Using Transfer Learning

Abstract

Lung disease is a major health problem due to air pollution, smoking, and an aging population. For this reason, early and accurate detection is essential to achieve overall control of the disease and greatly increase the chances of successful medical treatment. This study proposes two convolutional neural network (CNN) models that rely on transfer learning to classify and detect the presence of pneumonia from a collection of chest X-ray (or CXR) images belonging to 4 classes. The data augmentation algorithm is used to increase the size of the training dataset in order to reduce overfitting and improve the model's generalization capacity.Using the data augmentation algorithm, we conducted a detailed evaluation of two pre-trained deep neural networks: VGGNet-16 and MobileNet. Deep learning (DL) is excellent in detecting infections, according to the findings. The MobileNet model outperforms the VGGNet-16 model where it achieved 82% accuracy, 83.5% recall, and 82.5% F1 score, while VGGNet-16 version gave the highest precision value which equals 84.5% but accuracy, recall and F1 score were respectively equal to 80%, 76% and 79%. On the other hand, and by calculating the AUC of the two models, MobileNet presents the best score which is 95% while VGGNet-16 has a score of 94%.