Detecting Pneumonia using Vision Transformer and comparing with other techniques
Khushal Tyagi, Gaurav Pathak, Rahul Nijhawan, Ankush Mittal
Abstract
Pneumonia is life-threatening. It's critical for infants, young children, elders, and people with health problems or enfeebles immune systems. However, someone who has been infected with coronavirus can get intense Pneumonia in each lung. The best way to stumble on Pneumonia is via chest X-ray. Radiotherapist is required for an examination of chest X-Ray. An automated pneumonia detection device would be helpful for early detection in far-off places. The proposed method makes it possible to train ViT models with enhanced performance. Nowadays, ViT is an alternative method of CNN in the field of computer vision. In this research, three models have been proposed, namely convolutional neural network (CNN), VGG16, and Visual Transformer were constructed. Statistical results are obtained after the comparison of all three models. Results indicate that ViT can identify Pneumonia with an accuracy of 96.45%. And also can be used to recognize other lung-related diseases. All the models were trained and tested on a dataset that contains standard chest X-Rays and pneumonia chest X-Rays.