<![CDATA[Chronic diseases are the leading cause of death worldwide, accounting for 73% of deaths in 2020. Tuberculosis (TB), caused by the bacterium Mycobacterium tuberculosis, is one of these diseases and has a significant impact on countries with a high TB burden due to a lack of radiologists and medical equipment. Early diagnosis of TB is crucial but challenging because of its similarity to lung cancer and the shortage of radiologists. A semi-automatic TB detection system is needed to support medical diagnosis and improve public health services. Deep learning technology, such as Convolutional Neural Networks (CNN), offers an effective solution for disease diagnosis with high accuracy. This study compares deep learning methods using an 8-layer CNN and VGG-19, both enhanced with Histogram Equalization (HE) for improved image quality. The study utilizes chest X-ray images of normal lungs and TB-affected lungs from Kaggle. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. Results indicate that the VGG-19 model outperforms the 8-layer CNN across all evaluation metrics, achieving an accuracy of 72.00% compared to 65.00% for the 8-layer CNN. VGG-19 also demonstrates better precision, recall, and F1-score, making it a more suitable choice for TB detection with enhanced image quality.]]>
