Detection of Tuberculosis Based on X-Ray Image Using the Vision Transformer Method

Tuberculosis, or TB, is an infectious disease caused by the Mycobacterium tuberculosis bacteria, which can attack the human body regardless of age and gender. This bacterium is a very strong bacillus, requiring a long time to treat. The types of radiological examinations commonly used today to detect tuberculosis are chest X-rays and CT scans. However, not all hospitals have CT scan machines due to their higher cost, while almost every hospital has an X-ray machine. This research aims to develop an assistive device with a high level of accuracy in detecting the disease through the analysis of X-ray images. The solution is to develop a tuberculosis detection assistive device based on X-ray images using the Vision Transformer classification model. The dataset used is obtained from four references and contains chest X-ray images categorized into four classes: Normal, Tuberculosis, Pneumonia, and Covid-19. This Vision Transformer model is designed to classify chest X-ray images to predict lung diseases according to the specified labels. From this research, the model can predict with an accuracy of up to 89%. The result of this research can help doctors in making decisions and also serve as a learning tool for detecting diseases in X-ray images.