Computer Aided Diagnosis for lung tuberculosis identification based on thoracic X-ray

This paper presents research on lung tuberculosis (TB) identification by using computer. This research was attempt to reduce patient waiting time in receiving X-ray diagnosis result on lung TB disease, due to mismatch ratio of radiologic experts to the number of patient, especially from remote areas in Indonesia. We used textural features calculated by computer to be used as descriptor in classifying image as TB or non-TB. We used statistical features of image histogram by calculates five features: mean, standar deviation (std), skewness, kurtosis, and entropy. These features were calculated from ROI images using pre defined ROI shape from thresholding method. Features calculated was then reduced down to one principal feature using Principal Componen Analysis (PCA) method. Finally, we used Mahalanobis distance classifier as classifier method based on one principal feature as descriptor. This research results show that it was possible to classify TB and non-TB image based on statistical feature on image histogram.