An algorithm for detection of Tuberculosis bacilli in Ziehl-Neelsen sputum smear images

Christian del Carpio, Erwin Dianderas, Mirko Zimic, Patricia Sheen, Jorge Coronel, Roberto Lavarello, Guillermo Kemper

Research output: Contribution to journalArticle

Abstract

This work proposes an algorithm oriented to the detection of tuberculosis bacilli in digital images of sputum samples, inked with the Ziehl Neelsen method and prepared with the direct, pellet and diluted pellet methods. The algorithm aims at automating the optical analysis of bacilli count and the calculation of the concentration level. Several algorithms have been proposed in the literature with the same objective, however, in no case is the performance in sensitivity and specificity evaluated for the 3 preparation methods. The proposed algorithm improves the contrast of the colors of interest, then thresholds the image and segments by labeling the objects of interest (bacilli). Each object then has its geometrical descriptors and photometric descriptors. With all this, a characteristic vector is formed, which are used in the training and classification process of an SVM. For the training 225 images obtained by the 3 preparation methods were used. The proposed algorithm reached, for the direct method, a sensitivity level of 93.67% and a specificity level of 89.23%. In the case of the Pellet method, a sensitivity of 92.13% and a specificity of 82.58% was obtained, while for diluted Pellet the sensitivity was 92.81% and the specificity 83.61%.

Original languageEnglish (US)
Pages (from-to)2968-2981
Number of pages14
JournalInternational Journal of Electrical and Computer Engineering
Volume9
Issue number4
DOIs
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Bacilli
Labeling
Color

Keywords

  • Baciloscopy
  • Image processing
  • Sputum smear
  • Tuberculosis
  • Ziehl-Neelsen

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

An algorithm for detection of Tuberculosis bacilli in Ziehl-Neelsen sputum smear images. / del Carpio, Christian; Dianderas, Erwin; Zimic, Mirko; Sheen, Patricia; Coronel, Jorge; Lavarello, Roberto; Kemper, Guillermo.

In: International Journal of Electrical and Computer Engineering, Vol. 9, No. 4, 01.01.2019, p. 2968-2981.

Research output: Contribution to journalArticle

del Carpio, Christian ; Dianderas, Erwin ; Zimic, Mirko ; Sheen, Patricia ; Coronel, Jorge ; Lavarello, Roberto ; Kemper, Guillermo. / An algorithm for detection of Tuberculosis bacilli in Ziehl-Neelsen sputum smear images. In: International Journal of Electrical and Computer Engineering. 2019 ; Vol. 9, No. 4. pp. 2968-2981.
@article{7b98851609b246998eaeec874e775a6f,
title = "An algorithm for detection of Tuberculosis bacilli in Ziehl-Neelsen sputum smear images",
abstract = "This work proposes an algorithm oriented to the detection of tuberculosis bacilli in digital images of sputum samples, inked with the Ziehl Neelsen method and prepared with the direct, pellet and diluted pellet methods. The algorithm aims at automating the optical analysis of bacilli count and the calculation of the concentration level. Several algorithms have been proposed in the literature with the same objective, however, in no case is the performance in sensitivity and specificity evaluated for the 3 preparation methods. The proposed algorithm improves the contrast of the colors of interest, then thresholds the image and segments by labeling the objects of interest (bacilli). Each object then has its geometrical descriptors and photometric descriptors. With all this, a characteristic vector is formed, which are used in the training and classification process of an SVM. For the training 225 images obtained by the 3 preparation methods were used. The proposed algorithm reached, for the direct method, a sensitivity level of 93.67{\%} and a specificity level of 89.23{\%}. In the case of the Pellet method, a sensitivity of 92.13{\%} and a specificity of 82.58{\%} was obtained, while for diluted Pellet the sensitivity was 92.81{\%} and the specificity 83.61{\%}.",
keywords = "Baciloscopy, Image processing, Sputum smear, Tuberculosis, Ziehl-Neelsen",
author = "{del Carpio}, Christian and Erwin Dianderas and Mirko Zimic and Patricia Sheen and Jorge Coronel and Roberto Lavarello and Guillermo Kemper",
year = "2019",
month = "1",
day = "1",
doi = "10.11591/ijece.v9i4.pp2968-2981",
language = "English (US)",
volume = "9",
pages = "2968--2981",
journal = "International Journal of Electrical and Computer Engineering",
issn = "2088-8708",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "4",

}

TY - JOUR

T1 - An algorithm for detection of Tuberculosis bacilli in Ziehl-Neelsen sputum smear images

AU - del Carpio, Christian

AU - Dianderas, Erwin

AU - Zimic, Mirko

AU - Sheen, Patricia

AU - Coronel, Jorge

AU - Lavarello, Roberto

AU - Kemper, Guillermo

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This work proposes an algorithm oriented to the detection of tuberculosis bacilli in digital images of sputum samples, inked with the Ziehl Neelsen method and prepared with the direct, pellet and diluted pellet methods. The algorithm aims at automating the optical analysis of bacilli count and the calculation of the concentration level. Several algorithms have been proposed in the literature with the same objective, however, in no case is the performance in sensitivity and specificity evaluated for the 3 preparation methods. The proposed algorithm improves the contrast of the colors of interest, then thresholds the image and segments by labeling the objects of interest (bacilli). Each object then has its geometrical descriptors and photometric descriptors. With all this, a characteristic vector is formed, which are used in the training and classification process of an SVM. For the training 225 images obtained by the 3 preparation methods were used. The proposed algorithm reached, for the direct method, a sensitivity level of 93.67% and a specificity level of 89.23%. In the case of the Pellet method, a sensitivity of 92.13% and a specificity of 82.58% was obtained, while for diluted Pellet the sensitivity was 92.81% and the specificity 83.61%.

AB - This work proposes an algorithm oriented to the detection of tuberculosis bacilli in digital images of sputum samples, inked with the Ziehl Neelsen method and prepared with the direct, pellet and diluted pellet methods. The algorithm aims at automating the optical analysis of bacilli count and the calculation of the concentration level. Several algorithms have been proposed in the literature with the same objective, however, in no case is the performance in sensitivity and specificity evaluated for the 3 preparation methods. The proposed algorithm improves the contrast of the colors of interest, then thresholds the image and segments by labeling the objects of interest (bacilli). Each object then has its geometrical descriptors and photometric descriptors. With all this, a characteristic vector is formed, which are used in the training and classification process of an SVM. For the training 225 images obtained by the 3 preparation methods were used. The proposed algorithm reached, for the direct method, a sensitivity level of 93.67% and a specificity level of 89.23%. In the case of the Pellet method, a sensitivity of 92.13% and a specificity of 82.58% was obtained, while for diluted Pellet the sensitivity was 92.81% and the specificity 83.61%.

KW - Baciloscopy

KW - Image processing

KW - Sputum smear

KW - Tuberculosis

KW - Ziehl-Neelsen

UR - http://www.scopus.com/inward/record.url?scp=85073413231&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073413231&partnerID=8YFLogxK

U2 - 10.11591/ijece.v9i4.pp2968-2981

DO - 10.11591/ijece.v9i4.pp2968-2981

M3 - Article

AN - SCOPUS:85073413231

VL - 9

SP - 2968

EP - 2981

JO - International Journal of Electrical and Computer Engineering

JF - International Journal of Electrical and Computer Engineering

SN - 2088-8708

IS - 4

ER -