Medical Image Analysis for TB Diagnosis System

Tuberculosis (TB) is a disease caused by bacteria called Mycobacterium tuberculosis. It usually spreads through the air & attacks low immune bodies. Recently, several techniques are applied to diagnosis the TB diseases. Unfortunately, diagnosing TB is still a major challenge. In recent years, a variety of techniques have been developed. In this paper, texture feature set is obtained using three different categories like statistical, structural and gray level dependent features. After that, the feature selection scheme is carried out and TB classification is done using GANN classifier. In GA-NN, genetic algorithm and neural network are combined to do the classification process. Once the abnormal TB is classified via GA-NN classifier, the TB region is identified via morphological operator. Experimental results demonstrate that the proposed method outperforms than the existing method.