Enhancement of Tuberculosis Detection Using Ensemble Classifier with Quadtree Method: A Preliminary Study
Chong Joon Hou1, Laura P. Jack1, Aslina Baharum1 and Noorsidi Aizuddin Mat Noor2
1UXRL, Faculty of Computing and Informatics, Universiti Malaysia Sabah, Malaysia; 2UTM CRES, Faculty of Built Environment and Surveying, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor, Malaysia
Abstract: Tuberculosis is an infectious disease caused by a bacillus called Mycobacterium tuberculosis. It can lead to death in untreated and inappropriately treated patients. An early diagnosis of the disease not only improves treatment success but also reduces death rates. Lung region is the most affected part of Tuberculosis and the process of medical image classification is still carried out manually using the knowledge of the physician or radiologist, which leads to inaccurate and slow process of TB identification. Therefore, this study proposed to enhance tuberculosis detection using a different combination of machine learning and image processing methods on the image dataset.
Keywords: Tuberculosis, Ensemble classifier, Quadtree, Convolutional Neural Network (CNN