<![CDATA[Tuberculosis (TB) is a serious infectious disease that is still one of the main causes of death in the world, especially in developing countries. X-ray image analysis is an important step in controlling this disease. This research aims to classify X-ray images of tuberculosis using a deep learning approach with three Convolutional Neural Networks (CNN) architectures: DenseNet201, Xception, and MobileNetV2. The dataset used consists of 3,000 X-ray images, divided into two categories: normal and TBC, obtained from Kaggle, which are then processed through normalization, augmentation, and data division using the hold-out method with a ratio of 70:30, 80:20 , and 90:10. The research results show that DenseNet201 with the Nadam optimizer at 90:10 data division produces the highest accuracy of 100%, making it the best combination for TBC X-ray image classification. Xception achieved the best accuracy of 96.66% with the Nadam optimizer at a data split of 80:20. MobileNetV2 shows an optimal accuracy of 98.69% using the Adam optimizer at a 90:10 data split. This research proves that DenseNet201 with the Nadam optimizer is very effective in handling medical image classification, especially for tuberculosis. These results provide an important contribution to the development of deep learning-based technology to improve the accuracy of tuberculosis diagnosis.]]>
Copyrights © 2025
