Segmentation of X-ray image using city block distance measure

Abstract

Tuberculosis (TB) is an infectious disease caused by mycobacterium which can be diagnosed by analyzing medical test report of patient that take more than a month to get the result. The aim of this study is to propose a solution which can be used to identify TB's presence and start treating such suspected patients. In this paper, we propose a method to use city block measure for segmenting x-ray image which helps in diagnosis of TB. Initially image processing concepts like canny edge detection techniques are applied to x-ray image for preprocessing it. Later K-means clustering algorithm is applied on preprocessed x-ray image to get segmented x-ray image. The outputs of TB x-ray and normal x-ray image are compared and analyzed with sqEuclidean and city block distance measure. Finally the City block distance measure results are found to be more appropriate for segmenting TB x-ray and normal x-ray image. Segmented x-ray image helps doctors in identifying tuberculosis presence, so that early treatment planning can be made on suspected patients without waiting for the exact medical test reports. The advantage of this approach is the ability to interpret x-ray image to know whether it is a TB affected x-ray or normal x-ray.