Identification and Classification of Pneumonia in Chest X-Ray Images Using Deep Learning Techniques

Abstract

Pneumonia is a bacterial or viral respiratory infection that affects a huge number of individuals, particularly in developing and disadvantaged countries where pollution, poor living conditions, congestion, and a lack of medical infrastructure are all too frequent. Pneumonia produces pleural effusion, which is a condition in which fluids fill the lung and create breathing problems. It is critical to diagnose pneumonia early in order to receive curative treatment and boost survival chances. The most common method for detecting pneumonia is chest X-ray imaging. However, examining chest X-rays is a difficult task that is vulnerable to subjective variability. In this study, we used chest X-ray pictures to develop a computer-aided diagnosis approach for automatic pneumonia detection. We used deep transfer learning and developed a Convolutional Neural Network (CNN) model with the four transfer learning methods: CovXNet, RNN, and VGG16 to deal with the lack of accessible data. ResNet 50 is utilised in existing approaches, but it does not attain the requisite accuracy and needs to be improved. As a result, the current method is proposed, as well as additional transfer learning methods. A publicly available pneumonia X-ray dataset was used to test the suggested approach.