Identification of Tuberculosis (TB) Disease Based on Lung X-Rays using Extreme Learning Machine

• Published in: Journal of physics. Conference series 2020-06, Vol.1566 (1), p.12085
• Main Authors: Nasution, M K M, Elveny, M, Hardi, S M, Jaya, I, Siregar, M A
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Bacteria; Image processing; Lungs; Machine learning; Physics; Tuberculosis; X-rays
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/1566/1/012085

Tuberculosis is a disease caused by a bacterium called Mycobacterium Tuberculosis. Most Tuberculosis bacteria not only attack the lungs, but also attack other organs. Tuberculosis disease can spread and contaminate through the salivary and bacterial when the sufferer coughs and sneezes. Thus, the contagion of tuberculosis can take place either through contact directly with the sufferer or through the air. The examination system of Tuberculosis is still done manually. Therefore, a computational method is necessary to examine and identify Tuberculosis suffered by the patient through X-ray images of human lungs. The method used in this research is the Extreme Learning Machine. Lung X-ray images are used as input for image processing. The steps taken before identification were image pre- processing and Thresholding. The external results of this research include HKI in the form of software (registered), international conference presenter (done). In addition, the results of this study can assist public in determining the types of tuberculosis suffered so that it will be more efficient in early treatment of the disease.