DETECTION OF PNEUMONIA FROM X-RAY IMAGES USING DEEP LEARNING TECHNIQUES

Abstract

X-ray images is one of the most common utilities used by health care specialists for detecting healthy problems in patients’ chest. In this work, deep learning techniques have been adopted for diagnosing and detecting of lung diseases. First, an experimental study has been conducted for selecting the best artificial neural network ANN model that can be used for lung X-Ray image classification. The obtained best model has been used for classifying the lung X-Ray images into three classes (Multi class classification) namely bacterial pneumonia, viral pneumonia, and healthy lung. After that, three well-known CNN architectures, namely ResNet, Inception, and MobileNet have been adopted and used as a feature extractor for the selected best ANN model. Moreover, the above-mentioned ANN model (both with and without the features extraction phase) has been used for classifying the lung X-Ray images as healthy and pneumonia lungs (Binary classification). As a result of the study, the proposed ANN model with ResNet feature extraction phase gave the highest classification accuracy rate of 81.67% when multi-class classification has been conducted on the lung X-Ray dataset. On the other hand, the proposed ANN model with MobileNet feature extraction phase gave the highest accuracy rate of 95.67% when a binary classification has been conducted on the X-Ray image dataset.