Downloads: 112 | Views: 183
Research Paper | Computer Science & Engineering | India | Volume 3 Issue 10, October 2014
Level Set Segmentation Method for Automatic Tuberculosis Screening Using Chest Radiographs
Sajmi Salam
Abstract: Tuberculosis is a major global health problem worldwide, after HIV. Diagnosing tuberculosis is still remains a challenge because of the multi-drug-resistant bacteria which cause this disease. Tuberculosis is an infectious disease caused by the bacillus Mycobacterium tuberculosis which mainly affects the lungs. Mortality rates of the patients with tuberculosis are high when left undiagnosed and thus untreated. Standard diagnosis still remain slow and often unreliable. In an effort to reduce the disease, this paper presents an automated approach for detecting tuberculosis in chest radiographs. In this paper, we first extract the lung region using a level set segmentation method. We compute a set of texture and shape features, which enable the X-rays to be classified as normal or abnormal using a binary classifier for this lung region. Many antibiotics exists for TB. Unfortunately, diagnosing TB is still a major problem. For this problem, we are using a cost effective screening technology to monitor progress during treatment. Level Sets are an important category of modern image segmentation techniques are based on partial differential equations (PDE), i. e. progressive evaluation of the differences among neighboring pixels to find object boundaries. The level set method was initially proposed to track moving interfaces. It can be used to efficiently address the problem of curve/surface/etc. Initial contour is taken over the object that time the level will be zero then this contour is moving towards the object boundary then it settle down in the boundary of the object well. At first we take the outside contour. Then move towards the object. If the gray level changing, move it else not. Stop when gray level changes.
Keywords: Computer-aided detection and diagnosis, lung pattern recognition and classification, segmentation, tuberculosis TB, X-ray imaging
Edition: Volume 3 Issue 10, October 2014,
Pages: 1633 - 1636