Tuberculosis bacteria detection based on Random Forest using fluorescent images

Tuberculosis (TB) is an infectious disease in low and middle-income countries. There are many methods of physical examinations for tuberculosis detection, but the most effective method is visual examination using microscopes, including fluorescent microscopy and bright field microscopy. However, according to the analysis of previous research work, the method based on fluorescent microscopes can yield on average 10% on sensitiveness than the bright field microscopy. In this paper, we present a TB detection method based on Random Forest using fluorescent microscopic images. We have conducted experiments on three types of classifiers, in terms of Random Forest (RF), linear SVM (LinSVM), and Cross-Validation SVM (CVSVM). The experimental results show that the machine learning method of Random Forest for TB segmentation and detection using fluorescent images has obtained better performance than other two methods.