부산대학교 도서관

The stealthy Mycobacterium tuberculosis breeds an infectious scourge known as Tuberculosis (TB). It is a bacterial infection related chronic lung disease. An early and accurate diagnosis of TB is essential. chest X-ray images are used to detect this disease. However, manual detection takes longer, which occasionally leads to errors. In this article, we proposed a deep learning approach for TB classification using chest X-rays. Some deep learning algorithms search through a hypothesis space in search of an appropriate hypothesis that will produce accurate predictions for a certain disease scenario. To detect tuberculosis in chest X-rays, we use Res Net a deep learning architecture recognized for its capacity to make use of feature reuse and overcome vanishing gradient issues. In order to provide a more exact hypothesis for the prediction of tuberculosis using the Res Net, a deep learning technique, this proposed model is developed on top of prior research. We were able to reach 99% accuracy with the classifier that was based on deep learning.