Convolutional Neural Network for Chest X-ray Pneumonia Detection

Abstract

Deep learning techniques are widely used to design robust classification models in several arias such as medical diagnosis tasks in which it achieves good performance. In recent years Pneumonia causes 15% of the total number of deaths in children under the age of 5. It can be caused by viruses, bacteria or fungi, which led the researchers to focus their studies on identifying pneumonia basing on Chest X-ray images, using deep learning techniques. In this paper, we propose a CNN model (Convolutional Neural Network) for the classification of Chest X-ray images. The proposed method is based on a non-complex CNN and without the use of transfer learning. Our proposed model uses fewer parameters and thus reduces the training time. In this study, and because of the low availability of data, we used the data augmentation method to eliminate overfitting and to improve the accuracy of the validation and classification of the model. The obtained results prove the efficiency of the proposed architecture compared with the state of the art methods.