Detection of Tuberculosis Disease in Lung X-ray Images Using the DenseNet121 Method

Tuberculosis (TB) is a lung infection caused by Mycobacterium tuberculosis and can be detected through chest X-ray imaging. In this study, tuberculosis disease detection was carried out using the DenseNet121 method, a deep-learning architecture proven effective in medical image classification tasks. This study used a dataset of 4,200 lung X-ray images classified as positive or negative for TB. The DenseNet121 model was trained with this data to identify patterns in the X-ray images indicating tuberculosis infection. The results of the model evaluation showed high performance with a precision value of 0.91, a recall of 0.90, and an f1-score of 0.89. In addition, the model achieved an overall accuracy of 90.4%. The results of this study indicate that the DenseNet121 method can be a reliable tool in detecting tuberculosis from chest X-ray images so that it can assist medical personnel in the diagnosis process more quickly and accurately.