Pulmonary tuberculosis detection using deep learning convolutional neural networks

Michael Norval; Zenghui Wang; Yanxia Sun

doi:10.1145/3376067.3376068

Pulmonary tuberculosis detection using deep learning convolutional neural networks

Michael Norval
, Zenghui Wang
, Yanxia Sun

Electrical and Electronic Engineering Science

University of South Africa

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

27 Citations (Scopus)

Abstract

Tuberculosis (TB) is classified as one of the top ten reasons for death from an infectious agent. This paper is to investigate the accuracy of two methods to detect Pulmonary Tuberculosis based on the patient chest X-ray images using Convolutional Neural Networks (CNN). Various image preprocessing methods are tested to find the combination that yields the highest accuracy. Moreover, a hybrid approach using the original statistical computer-aided detection method combined with Neural Networks was also investigated. Simulations have been carried out based on 406 normal images & 394 abnormal images. The simulations show that a cropped region of interest coupled with contrast enhancement yields excellent results. When further enhancing the images with the hybrid method even better results are achieved.

Original language	English
Title of host publication	Proceedings of the 2019 3rd International Conference on Video and Image Processing, ICVIP 2019
Publisher	Association for Computing Machinery
Pages	47-51
Number of pages	5
ISBN (Electronic)	9781450376822
DOIs	https://doi.org/10.1145/3376067.3376068
Publication status	Published - 20 Dec 2019
Event	3rd International Conference on Video and Image Processing, ICVIP 2019 - Shanghai, China Duration: 20 Dec 2019 → 23 Dec 2019

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	3rd International Conference on Video and Image Processing, ICVIP 2019
Country/Territory	China
City	Shanghai
Period	20/12/19 → 23/12/19

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Artificial Intelligence
Chest
Lung X-Ray
Neural Network
Pulmonary
Rectification Linear Unit
Tuberculosis

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3376067.3376068

Cite this

@inproceedings{9db16fd5659f4d66aeee8737cc62a099,

title = "Pulmonary tuberculosis detection using deep learning convolutional neural networks",

abstract = "Tuberculosis (TB) is classified as one of the top ten reasons for death from an infectious agent. This paper is to investigate the accuracy of two methods to detect Pulmonary Tuberculosis based on the patient chest X-ray images using Convolutional Neural Networks (CNN). Various image preprocessing methods are tested to find the combination that yields the highest accuracy. Moreover, a hybrid approach using the original statistical computer-aided detection method combined with Neural Networks was also investigated. Simulations have been carried out based on 406 normal images \& 394 abnormal images. The simulations show that a cropped region of interest coupled with contrast enhancement yields excellent results. When further enhancing the images with the hybrid method even better results are achieved.",

keywords = "Artificial Intelligence, Chest, Lung X-Ray, Neural Network, Pulmonary, Rectification Linear Unit, Tuberculosis",

author = "Michael Norval and Zenghui Wang and Yanxia Sun",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 3rd International Conference on Video and Image Processing, ICVIP 2019 ; Conference date: 20-12-2019 Through 23-12-2019",

year = "2019",

month = dec,

day = "20",

doi = "10.1145/3376067.3376068",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "47--51",

booktitle = "Proceedings of the 2019 3rd International Conference on Video and Image Processing, ICVIP 2019",

}

Norval, M, Wang, Z & Sun, Y 2019, Pulmonary tuberculosis detection using deep learning convolutional neural networks. in Proceedings of the 2019 3rd International Conference on Video and Image Processing, ICVIP 2019. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 47-51, 3rd International Conference on Video and Image Processing, ICVIP 2019, Shanghai, China, 20/12/19. https://doi.org/10.1145/3376067.3376068

Pulmonary tuberculosis detection using deep learning convolutional neural networks. / Norval, Michael; Wang, Zenghui; Sun, Yanxia.
Proceedings of the 2019 3rd International Conference on Video and Image Processing, ICVIP 2019. Association for Computing Machinery, 2019. p. 47-51 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Pulmonary tuberculosis detection using deep learning convolutional neural networks

AU - Norval, Michael

AU - Wang, Zenghui

AU - Sun, Yanxia

PY - 2019/12/20

Y1 - 2019/12/20

N2 - Tuberculosis (TB) is classified as one of the top ten reasons for death from an infectious agent. This paper is to investigate the accuracy of two methods to detect Pulmonary Tuberculosis based on the patient chest X-ray images using Convolutional Neural Networks (CNN). Various image preprocessing methods are tested to find the combination that yields the highest accuracy. Moreover, a hybrid approach using the original statistical computer-aided detection method combined with Neural Networks was also investigated. Simulations have been carried out based on 406 normal images & 394 abnormal images. The simulations show that a cropped region of interest coupled with contrast enhancement yields excellent results. When further enhancing the images with the hybrid method even better results are achieved.

AB - Tuberculosis (TB) is classified as one of the top ten reasons for death from an infectious agent. This paper is to investigate the accuracy of two methods to detect Pulmonary Tuberculosis based on the patient chest X-ray images using Convolutional Neural Networks (CNN). Various image preprocessing methods are tested to find the combination that yields the highest accuracy. Moreover, a hybrid approach using the original statistical computer-aided detection method combined with Neural Networks was also investigated. Simulations have been carried out based on 406 normal images & 394 abnormal images. The simulations show that a cropped region of interest coupled with contrast enhancement yields excellent results. When further enhancing the images with the hybrid method even better results are achieved.

KW - Artificial Intelligence

KW - Chest

KW - Lung X-Ray

KW - Neural Network

KW - Pulmonary

KW - Rectification Linear Unit

KW - Tuberculosis

UR - https://www.scopus.com/pages/publications/85081181752

U2 - 10.1145/3376067.3376068

DO - 10.1145/3376067.3376068

M3 - Conference contribution

AN - SCOPUS:85081181752

T3 - ACM International Conference Proceeding Series

SP - 47

EP - 51

BT - Proceedings of the 2019 3rd International Conference on Video and Image Processing, ICVIP 2019

PB - Association for Computing Machinery

T2 - 3rd International Conference on Video and Image Processing, ICVIP 2019

Y2 - 20 December 2019 through 23 December 2019

ER -

Pulmonary tuberculosis detection using deep learning convolutional neural networks

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this