Pneumonia Detection Using enhanced CNN Model on Chest X-Ray Images

Abstract

Objective: Pneumonia, caused by microorganisms, is a severely contagious disease that damages one or both the lungs of the patients. Early detection and treatment are typically favoured to recover infected patients since untreated pneumonia can lead to major complications in the older (>65 years) and children (<5 years). The objectives of this work are to develop several models to evaluate X-ray Images (XRIs) of the chest, determine whether the images show/ do not show signs of pneumonia and compare the models based on their accuracy, precision, recall, loss, and ROC AUC scores. Methods: CNN, VGG-19, ResNet-50, and ResNet-50 with fine-tuning are some of the deep learning algorithms employed in this study. By training the transfer learning model and upgraded CNN model using a dataset, these techniques are used to identify pneumonia. The data set for the study was obtained from Kaggle. This dataset included 5,863 chest XRIs, which were categorised into 3 different folders (i.e., train, val, test). Results: According to the experimental findings, the ResNet50 model showed the lowest accuracy, i.e., 82.8%; while the upgraded CNN model showed the highest accuracy of 92.4%. Owing to its high accuracy, CNN was regarded as the best model in this study. The techniques developed in this study outperformed the popular ensemble techniques, and the models showed better results than those generated by cutting-edge methods. Deep learning models can detect the progression of pneumonia, which improves the general diagnostic accuracy and gives patients new hope for speedy treatment. Conclusions: Since enhanced CNN and ResNet50 showed the highest accuracy compared to other algorithms, it was concluded that these techniques could be effectively used to identify pneumonia after performing fine-tuning. It should be noted that the improved CNN would be more helpful in diagnosing pneumonia than the conventional method, which involves the healthcare provider reviewing the patient's medical history, performing a physical exam, and ordering diagnostic procedures like a chest X-ray. This information helps in identifying the form of pneumonia affecting the patient. Furthermore, pneumonia can take a severe turn and become fatal.