%0 Journal Article
%T Smart Spotting of Pulmonary TB Cavities Using CT Images
%A V. Ezhil Swanly
%A L. Selvam
%A P. Mohan Kumar
%A J. Arokia Renjith
%A M. Arunachalam
%A K. L. Shunmuganathan
%J Computational and Mathematical Methods in Medicine
%D 2013
%I Hindawi Publishing Corporation
%R 10.1155/2013/864854
%X One third of the worldĄŻs population is thought to have been infected with mycobacterium tuberculosis (TB) with new infection occurring at a rate of about one per second. TB typically attacks the lungs. Indication of cavities in upper lobes of lungs shows the high infection. Traditionally, it has been detected manually by physicians. But the automatic technique proposed in this paper focuses on accurate detection of disease by computed tomography (CT) using computer-aided detection (CAD) system. The various steps of the detection process include the following: (i) image preprocessing, which is done by techniques such as resizing, masking, and Gaussian smoothening, (ii) image egmentation that is implemented by using mean-shift model and gradient vector flow (GVF) model, (iii) feature extraction that can be achieved by Gradient inverse coefficient of variation and circularity measure, and (iv) classification using Bayesian classifier. Experimental results show that its perfection of detecting cavities is very accurate in low false positive rate (FPR). 1. Introduction Even though many effective methods have been taken to reduce the effect of TB, it is a third high rated disease causing death every year since just X-rays are used for detection process. TB cavities near clavicles will not be visible in X-rays. So, dosage estimation for patients would probably go wrong, which results in drug resistance problem. To overcome this problem, an automated segmentation technique is proposed in this work by using CT images. Gradient inverse coefficient of variation and circularity measures is used to classify detected features and confirm true TB cavities. Classification of the infectious stages based on their intensity is very important to recover from the disease based on the stage of its infection level [1]. Chest radiograph is the primary detection tool [2]. TB diagnosis usually occurs after a combination of skin, blood, and imaging tests. In routine diagnosis, skin and blood tests are taken in case of latent stage of disease in which patients does not show symptoms. CXR is usually taken when the patient shows pulmonary complications. The combination of radiographic findings and demographic/clinical data helps physicians to decide the possibility of infectious TB [3]. Manually the detection of TB cavities is done by just looking at the X-rays/CT images by the doctors/technicians. So by means of looking at the images by the naked eye there is more chance for wrong prediction of the intensity of the cavities. Hence, because of this wrong prediction of the cavities,
%U http://www.hindawi.com/journals/cmmm/2013/864854/