The innovation 2d chest image segmentation for identification of tuberculosis by graph cut method

• Published in: 2015 International Conference on Soft-Computing and Networks Security (ICSNS) pp. 1 - 7
• Main Authors: Shiny, R. Nina, Chandra, B. Vasantha, Athinarayanan, S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-02-2015
• Subjects: Biomedical imaging; Computational modeling; Cross-layer strategies; Feature extraction; Histograms; Image segmentation; Lungs; Markov Decision Process; Reinforcement learning; Shape
• ISBN: 1479917524; 9781479917525
• DOI: 10.1109/ICSNS.2015.7292429

Tuberculosis (TB) is the second leading cause of death from an infectious disease worldwide, after HIV. TB is an infectious disease caused by the bacillus Mycobacterium tuberculosis, which typically affects the lungs. Several antibiotics exist for treating TB. While mortality rates are high when left untreated, treatment with antibiotics greatly improves the chances of survival. When left undiagnosed and thus untreated, mortality rates of patients with tuberculosis are high and diagnosing tuberculosis still remains a challenge. An automated approach for detecting tuberculosis in conventional posteroanterior chest radiographs is proposed. First it extracts the lung region using a graph cut segmentation method. For this lung region, a set of texture and shape features are computed, which enable the X-rays to be classified as normal or abnormal using a binary classifier. The proposed computer-aided diagnostic system for TB screening, which is ready for field deployment, achieves a performance that approaches the performance of human experts.