Tuberculosis Disease Detection from Chest X-rays Using Deep Learning Techniques

Abstract

Millions of cases of tuberculosis (TB) are recorded each year, making it a significant worldwide health concern. Early and accurate TB detection is essential for the disease to be effectively treated and controlled. Deep learning methods have recently become effective tools for analyzing medical images, and they have a lot of potential for use in the field of TB detection. This study describes a revolutionary deep-learning method for detecting TB illness. We used a dataset of 3500 chest X-ray images from individuals with tuberculosis. There are two classes in the dataset: Tuberculosis and Normal. We used the highly regarded deep learning models VGG16, VGG19, MobileNetV2, and InceptionV3 to categorize such elements. Out of all of them, MobileNetV2 has obtained the highest accuracy, which is accurate in training of 99.99% and a test's reliability of 98.93%. Furthermore, in VGG16, VGG19, and Inception-V3, we achieved test accuracy of 98.90%, 99.14%, and 97.87%, respectively.