Inherent Selection Of Tuberculosis Using Graph Cut Segmentation

Apply

Inherent Selection Of Tuberculosis Using Graph Cut Segmentation

Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2015, Vol 3, Issue 4

Abstract

Tuberculosis (TB) is a major global health threat. An estimated one-third of the world’s population has been exposed to TB, and millions of new infections are occurring every year. Tuberculosis naturally affects the lungs it also affects the other parts of the body. It is spread through air when infectious people cough, sneeze etc. The advent of new powerful hardware and software techniques has triggered attempts to develop computer-aided diagnostic systems for TB detection in support of inexpensive mass screening in developing countries. In this paper the medical background of TB detection in conventional posterior anterior chest X-rays has been described. In the first step the chest x-rays has been given as an input. In the second step, the selected images are segmented using graph cut segmentation method. In the last step a set of features such as area, dispersion, entropy, energy, correlation has been extracted and calculated. Lastly, the support vector machine is applied to classify the extracted feature vectors as normal or abnormal lungs and therefore it also reduced the false positive rate. It achieved 95.28% sensitivity with only 2.27 false positives per scan.

Authors and Affiliations

V. N. Ilakkiya, Dr. P. Raviraj

Keywords

EP ID EP20151
DOI -
Views 282
Downloads 5