Cover Image

Ensemble deep learning for tuberculosis detection

Tuberculosis (TB) is one of the deadliest infectious disease in the world. TB is caused by a type of tubercle bacillus called Mycobacterium Tuberculosis. Early detection of TB is pivotal to decrease the morbidity and mortality. TB is diagnosed by using the chest x-ray and a sputum test. Challenges f...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmad Hijazi, Mohd Hanafi, Yang, Leong Qi, Alfred, Rayner, Mahdin, Hairulnizam, Yaakob, Razali
Format: Article
Published: Institute of Advanced Engineering and Science 2020
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:psasir.upm.edu.my:79706
record_format eprints
spelling oai:psasir.upm.edu.my:79706 http://psasir.upm.edu.my/id/eprint/79706/ Ensemble deep learning for tuberculosis detection Ahmad Hijazi, Mohd Hanafi Yang, Leong Qi Alfred, Rayner Mahdin, Hairulnizam Yaakob, Razali Tuberculosis (TB) is one of the deadliest infectious disease in the world. TB is caused by a type of tubercle bacillus called Mycobacterium Tuberculosis. Early detection of TB is pivotal to decrease the morbidity and mortality. TB is diagnosed by using the chest x-ray and a sputum test. Challenges for radiologists are to avoid confused and misdiagnose TB and lung cancer because they mimic each other. Semi-automated TB detection using machine learning found in the literature requires identification of objects of interest. The similarity of tissues, veins and small nodules presenting the image at the initial stage may hamper the detection. In this paper, an approach to detect TB, that does not require segmentation of objects of interest, based on ensemble deep learning, is presented. Evaluation on publicly available datasets show that the proposed approach produced a model that recorded the best accuracy, sensitivity and specificity of 91.0%, 89.6% and 90.7% respectively. Institute of Advanced Engineering and Science 2020 Article PeerReviewed Ahmad Hijazi, Mohd Hanafi and Yang, Leong Qi and Alfred, Rayner and Mahdin, Hairulnizam and Yaakob, Razali (2020) Ensemble deep learning for tuberculosis detection. Indonesian Journal of Electrical Engineering and Computer Science, 17 (2). pp. 1014-1020. ISSN 2502-4752; ESSN: 2502-4760 https://ijeecs.iaescore.com/index.php/IJEECS/article/view/20625 10.11591/ijeecs.v17.i2.pp1014-1020
institution UPM IR
collection UPM IR
description Tuberculosis (TB) is one of the deadliest infectious disease in the world. TB is caused by a type of tubercle bacillus called Mycobacterium Tuberculosis. Early detection of TB is pivotal to decrease the morbidity and mortality. TB is diagnosed by using the chest x-ray and a sputum test. Challenges for radiologists are to avoid confused and misdiagnose TB and lung cancer because they mimic each other. Semi-automated TB detection using machine learning found in the literature requires identification of objects of interest. The similarity of tissues, veins and small nodules presenting the image at the initial stage may hamper the detection. In this paper, an approach to detect TB, that does not require segmentation of objects of interest, based on ensemble deep learning, is presented. Evaluation on publicly available datasets show that the proposed approach produced a model that recorded the best accuracy, sensitivity and specificity of 91.0%, 89.6% and 90.7% respectively.
format Article
author Ahmad Hijazi, Mohd Hanafi
Yang, Leong Qi
Alfred, Rayner
Mahdin, Hairulnizam
Yaakob, Razali
spellingShingle Ahmad Hijazi, Mohd Hanafi
Yang, Leong Qi
Alfred, Rayner
Mahdin, Hairulnizam
Yaakob, Razali
Ensemble deep learning for tuberculosis detection
author_facet Ahmad Hijazi, Mohd Hanafi
Yang, Leong Qi
Alfred, Rayner
Mahdin, Hairulnizam
Yaakob, Razali
author_sort Ahmad Hijazi, Mohd Hanafi
title Ensemble deep learning for tuberculosis detection
title_short Ensemble deep learning for tuberculosis detection
title_full Ensemble deep learning for tuberculosis detection
title_fullStr Ensemble deep learning for tuberculosis detection
title_full_unstemmed Ensemble deep learning for tuberculosis detection
title_sort ensemble deep learning for tuberculosis detection
publisher Institute of Advanced Engineering and Science
publishDate 2020
_version_ 1819299612225175552
score 13.4562235

Similar Items