Tuberculosis Disease Detection Using Image Processing

Tuberculosis is one of the deadliest disease in this world especially in developing countries. Sputum smear microscopy is the main diagnostic tool in developing countries and high burden countries for the detection of tuberculosis. Previous studies shows that the manual screening for sputum smear microscopic images lead to misdiagnosis and false result. Image processing techniques are applied in this research to enhance, segment and classify the sputum smear images for computerized process of tuberculosis bacilli identification. Image processing algorithm which used for sputum smear image include a series of enhancement techniques, segmentation methods and morphological operation. As the non-bacillus objects in sputum smear image can bias the detection, it should be suppressed from the smear image. This paper employs color image segmentation technique for segmenting the tuberculosis bacillus objects from the background. Tuberculosis bacillus objects are segmented from the background in two stages based on color space conversion and k-means clustering to identify the tuberculosis bacilli. The proposed method uses thirteen texture feature extraction and makes the judgement using multi-support vector machine. The experiment result confirmed the superior performance of the proposed method.