<![CDATA[Tuberculosis (TB) is a contagious disease caused by the bacterium Mycobacterium tuberculosis. If not adequately managed, TB can become a fatal, life-threatening condition. In Indonesia, TB remains a critical public health issue, with millions affected and the country ranking third globally in TB cases, following India and China. Symptoms of TB include persistent cough lasting more than three weeks, hemoptysis (bloody sputum), fever, chest pain, and night sweats. The widely used diagnostic method in Indonesia is the Ziehl-Neelsen stained sputum smear technique, which processes sputum samples with specific reagents, allowing acid-fast bacilli to be visualized through microscopic examination. However, this process is labor-intensive and time-consuming, often requiring between half an hour and several hours for an accurate diagnosis. To address these challenges, there is a crucial need to develop technology that accelerates the TB diagnosis process, facilitating easier labor for healthcare workers. This study focuses on employing YOLOv8 to automate the detection of acid-fast bacilli. The system acquires sputum sample images from a microscope, and the acquired data is then used to train the model for detecting tuberculosis bacteria. The proposed real-time approach, employing the YOLOv8 algorithm, has demonstrated adequate performance for one of our specialized models, achieving a precision score of 0.88, a recall score of 0.77, and an F1 score of 0.82. This research aims to enhance TB case detection and increase treatment coverage, thereby improving overall public health outcomes in Indonesia.]]>
Copyrights © 2025
