Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study

Seifedine Kadry; Venkatesan Rajinikanth; A. Chandrasekar; A. Nandhini

doi:10.1109/ICCTA54562.2021.9916622

Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study

Seifedine Kadry
, Venkatesan Rajinikanth
, A. Chandrasekar
, A. Nandhini

Noroff University College
Anna University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

In human, the abnormality in lung causes a severe respiratory problem and breathing difficulties. Tuberculosis (TB) is one of the common lung abnormality caused due a bacterium named Mycobacterium tuberculosis. TB infection will cause harsh breathing issues and untreated TB will lead to death. Detection of the TB using Chest X-ray is one of the common techniques and in this research work; TB detection using Deep-Learning-Technique (DLT) is demonstrated. The various phases of this research involve; (i) Image collection and resizing, (ii) Deep-Feature (DF) extraction with chosen technique, (iii) Classification using SoftMax classifier and (iv) Performance evaluation with existing technique. The proposed work employs a 5-fold cross validation and the best value is considered as the result. The outcome of this study confirms that, the classification accuracy achieved with ResNetl8 and K-Nearest Neighbor (ResNet+KNN) offered better outcome >97% compared to other DLT of this study.

Original language	English
Title of host publication	31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	172-175
Number of pages	4
ISBN (Electronic)	9781665478540
DOIs	https://doi.org/10.1109/ICCTA54562.2021.9916622
State	Published - 2021
Externally published	Yes
Event	31st International Conference on Computer Theory and Applications, ICCTA 2021 - Alexandria, Egypt Duration: 11 Dec 2021 → 13 Dec 2021

Publication series

Name	31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings

Conference

Conference	31st International Conference on Computer Theory and Applications, ICCTA 2021
Country/Territory	Egypt
City	Alexandria
Period	11/12/21 → 13/12/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Accuracy
Chest X-ray
Deep learning
SoftMax
Tuberculosis

Access to Document

10.1109/ICCTA54562.2021.9916622

Cite this

Kadry, S., Rajinikanth, V., Chandrasekar, A., & Nandhini, A. (2021). Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study. In 31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings (pp. 172-175). (31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCTA54562.2021.9916622

Kadry, Seifedine ; Rajinikanth, Venkatesan ; Chandrasekar, A. et al. / Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme : A Study. 31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 172-175 (31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings).

@inproceedings{028aca9e69e844e8ae096d403dbc2823,

title = "Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study",

abstract = "In human, the abnormality in lung causes a severe respiratory problem and breathing difficulties. Tuberculosis (TB) is one of the common lung abnormality caused due a bacterium named Mycobacterium tuberculosis. TB infection will cause harsh breathing issues and untreated TB will lead to death. Detection of the TB using Chest X-ray is one of the common techniques and in this research work; TB detection using Deep-Learning-Technique (DLT) is demonstrated. The various phases of this research involve; (i) Image collection and resizing, (ii) Deep-Feature (DF) extraction with chosen technique, (iii) Classification using SoftMax classifier and (iv) Performance evaluation with existing technique. The proposed work employs a 5-fold cross validation and the best value is considered as the result. The outcome of this study confirms that, the classification accuracy achieved with ResNetl8 and K-Nearest Neighbor (ResNet+KNN) offered better outcome >97\% compared to other DLT of this study.",

keywords = "Accuracy, Chest X-ray, Deep learning, SoftMax, Tuberculosis",

author = "Seifedine Kadry and Venkatesan Rajinikanth and A. Chandrasekar and A. Nandhini",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 31st International Conference on Computer Theory and Applications, ICCTA 2021 ; Conference date: 11-12-2021 Through 13-12-2021",

year = "2021",

doi = "10.1109/ICCTA54562.2021.9916622",

language = "English",

series = "31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "172--175",

booktitle = "31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings",

address = "United States",

}

Kadry, S, Rajinikanth, V, Chandrasekar, A & Nandhini, A 2021, Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study. in 31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings. 31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 172-175, 31st International Conference on Computer Theory and Applications, ICCTA 2021, Alexandria, Egypt, 11/12/21. https://doi.org/10.1109/ICCTA54562.2021.9916622

Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study. / Kadry, Seifedine; Rajinikanth, Venkatesan; Chandrasekar, A. et al.
31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 172-175 (31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme

T2 - 31st International Conference on Computer Theory and Applications, ICCTA 2021

AU - Kadry, Seifedine

AU - Rajinikanth, Venkatesan

AU - Chandrasekar, A.

AU - Nandhini, A.

PY - 2021

Y1 - 2021

N2 - In human, the abnormality in lung causes a severe respiratory problem and breathing difficulties. Tuberculosis (TB) is one of the common lung abnormality caused due a bacterium named Mycobacterium tuberculosis. TB infection will cause harsh breathing issues and untreated TB will lead to death. Detection of the TB using Chest X-ray is one of the common techniques and in this research work; TB detection using Deep-Learning-Technique (DLT) is demonstrated. The various phases of this research involve; (i) Image collection and resizing, (ii) Deep-Feature (DF) extraction with chosen technique, (iii) Classification using SoftMax classifier and (iv) Performance evaluation with existing technique. The proposed work employs a 5-fold cross validation and the best value is considered as the result. The outcome of this study confirms that, the classification accuracy achieved with ResNetl8 and K-Nearest Neighbor (ResNet+KNN) offered better outcome >97% compared to other DLT of this study.

AB - In human, the abnormality in lung causes a severe respiratory problem and breathing difficulties. Tuberculosis (TB) is one of the common lung abnormality caused due a bacterium named Mycobacterium tuberculosis. TB infection will cause harsh breathing issues and untreated TB will lead to death. Detection of the TB using Chest X-ray is one of the common techniques and in this research work; TB detection using Deep-Learning-Technique (DLT) is demonstrated. The various phases of this research involve; (i) Image collection and resizing, (ii) Deep-Feature (DF) extraction with chosen technique, (iii) Classification using SoftMax classifier and (iv) Performance evaluation with existing technique. The proposed work employs a 5-fold cross validation and the best value is considered as the result. The outcome of this study confirms that, the classification accuracy achieved with ResNetl8 and K-Nearest Neighbor (ResNet+KNN) offered better outcome >97% compared to other DLT of this study.

KW - Accuracy

KW - Chest X-ray

KW - Deep learning

KW - SoftMax

KW - Tuberculosis

UR - https://www.scopus.com/pages/publications/85141436149

U2 - 10.1109/ICCTA54562.2021.9916622

DO - 10.1109/ICCTA54562.2021.9916622

M3 - Conference contribution

AN - SCOPUS:85141436149

T3 - 31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings

SP - 172

EP - 175

BT - 31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 11 December 2021 through 13 December 2021

ER -

Kadry S, Rajinikanth V, Chandrasekar A, Nandhini A. Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study. In 31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 172-175. (31st International Conference on Computer Theory and Applications, ICCTA 2021 - Proceedings). doi: 10.1109/ICCTA54562.2021.9916622

Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this