Pneumonia is a respiratory disease that causes infection in both the upper respiratory tract and the lungs. It is considered one of the leading causes of infection-related deaths in children. Chest X-ray images have proven helpful in diagnosing pneumonia. It is essential for early diagnosis of pneumonia to control the spread of the disease and save the patient. Therefore, there is a need for deep learning artificial intelligent systems to assist clinicians in early and better diagnosis. In this study, Residual Neural Network (ResNet) and Swin Transformer are used to classify pneumonia and healthy chest X-ray images from the Chest X-Ray Images dataset. Experimental results show that the ResNet achieved a maximum accuracy of 99.00% in detecting pneumonia after ten epochs. Whereas the Swin transformer achieved a maximum accuracy of 98.46% in detecting pneumonia after ten epochs.
목차
Abstract 1. Introduction 2. Related works 3. Methods 3.1. Dataset 3.2. Experiment setup 4. Experiment result 5. Conclusions Acknowledgement References