Classification of bacterial morphotypes from images of ZN-stained sputum-smears towards diagnosing drug-resistant TB

Rijul Saurabh Soans, A. G. Ramakrishnan, V. P. Shenoy, Ramesh R. Galigekere

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We describe a method for identifying and classifying acid-fast bacilli (AFB) and their associated morphotypes in the microscope-images of Ziehl-Neelsen stained sputum smears, in the context of tuberculosis (TB) screening by image processing. The importance of our work stems from the fact that the transformation of the classical rod-shaped AFB into certain other shapes is said to be related to TB drug-resistance. The first stage of processing involves color-segmentation in the HSV space by using Neural Networks and RUS-Boosted Decision Trees. The latter is used to alleviate the effects of class-imbalance between the pixels belonging to the AFB and the background. The second stage involves categorizing the bacilli into regular rod-shaped ones (possibly beaded), their morphotypes ("V-shaped" or "Y-shaped" bacilli), and clumps. The main, and novel contribution in this paper involves identifying and classifying the bacterial morphotypes. For that purpose, we propose and investigate three different methods: The first involves assuming the morphotypes to be letters of the English alphabet, and using a letter-recognition technique based on the Hotelling Transform and the Discrete Cosine Transform on the color-segmented bacilli. The second method uses moment-based invariants on the silhouettes, boundaries and skeletons, respectively. We use Support Vector Machine and Weighted K-NN classifiers in both the cases. In addition, we describe a new method based on the ends of the skeleton. Experiments on 72 images of sputum-smears revealed that the skeleton-based approach performed better than the other methods.

Original languageEnglish
Title of host publication2016 International Conference on Signal Processing and Communications, SPCOM 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509017461
DOIs
Publication statusPublished - 16-11-2016
Event11th International Conference on Signal Processing and Communications, SPCOM 2016 - Bangalore, India
Duration: 12-06-201615-06-2016

Conference

Conference11th International Conference on Signal Processing and Communications, SPCOM 2016
CountryIndia
CityBangalore
Period12-06-1615-06-16

Fingerprint

Bacilli
Acids
Color
Discrete cosine transforms
Decision trees
Support vector machines
Screening
Image processing
Microscopes
Classifiers
Pixels
Mathematical transformations
Neural networks
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing

Cite this

Soans, R. S., Ramakrishnan, A. G., Shenoy, V. P., & Galigekere, R. R. (2016). Classification of bacterial morphotypes from images of ZN-stained sputum-smears towards diagnosing drug-resistant TB. In 2016 International Conference on Signal Processing and Communications, SPCOM 2016 [7746682] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SPCOM.2016.7746682
Soans, Rijul Saurabh ; Ramakrishnan, A. G. ; Shenoy, V. P. ; Galigekere, Ramesh R. / Classification of bacterial morphotypes from images of ZN-stained sputum-smears towards diagnosing drug-resistant TB. 2016 International Conference on Signal Processing and Communications, SPCOM 2016. Institute of Electrical and Electronics Engineers Inc., 2016.
@inproceedings{0381870945054fa8ae71eda430949a1c,
title = "Classification of bacterial morphotypes from images of ZN-stained sputum-smears towards diagnosing drug-resistant TB",
abstract = "We describe a method for identifying and classifying acid-fast bacilli (AFB) and their associated morphotypes in the microscope-images of Ziehl-Neelsen stained sputum smears, in the context of tuberculosis (TB) screening by image processing. The importance of our work stems from the fact that the transformation of the classical rod-shaped AFB into certain other shapes is said to be related to TB drug-resistance. The first stage of processing involves color-segmentation in the HSV space by using Neural Networks and RUS-Boosted Decision Trees. The latter is used to alleviate the effects of class-imbalance between the pixels belonging to the AFB and the background. The second stage involves categorizing the bacilli into regular rod-shaped ones (possibly beaded), their morphotypes ({"}V-shaped{"} or {"}Y-shaped{"} bacilli), and clumps. The main, and novel contribution in this paper involves identifying and classifying the bacterial morphotypes. For that purpose, we propose and investigate three different methods: The first involves assuming the morphotypes to be letters of the English alphabet, and using a letter-recognition technique based on the Hotelling Transform and the Discrete Cosine Transform on the color-segmented bacilli. The second method uses moment-based invariants on the silhouettes, boundaries and skeletons, respectively. We use Support Vector Machine and Weighted K-NN classifiers in both the cases. In addition, we describe a new method based on the ends of the skeleton. Experiments on 72 images of sputum-smears revealed that the skeleton-based approach performed better than the other methods.",
author = "Soans, {Rijul Saurabh} and Ramakrishnan, {A. G.} and Shenoy, {V. P.} and Galigekere, {Ramesh R.}",
year = "2016",
month = "11",
day = "16",
doi = "10.1109/SPCOM.2016.7746682",
language = "English",
booktitle = "2016 International Conference on Signal Processing and Communications, SPCOM 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Soans, RS, Ramakrishnan, AG, Shenoy, VP & Galigekere, RR 2016, Classification of bacterial morphotypes from images of ZN-stained sputum-smears towards diagnosing drug-resistant TB. in 2016 International Conference on Signal Processing and Communications, SPCOM 2016., 7746682, Institute of Electrical and Electronics Engineers Inc., 11th International Conference on Signal Processing and Communications, SPCOM 2016, Bangalore, India, 12-06-16. https://doi.org/10.1109/SPCOM.2016.7746682

Classification of bacterial morphotypes from images of ZN-stained sputum-smears towards diagnosing drug-resistant TB. / Soans, Rijul Saurabh; Ramakrishnan, A. G.; Shenoy, V. P.; Galigekere, Ramesh R.

2016 International Conference on Signal Processing and Communications, SPCOM 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7746682.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Classification of bacterial morphotypes from images of ZN-stained sputum-smears towards diagnosing drug-resistant TB

AU - Soans, Rijul Saurabh

AU - Ramakrishnan, A. G.

AU - Shenoy, V. P.

AU - Galigekere, Ramesh R.

PY - 2016/11/16

Y1 - 2016/11/16

N2 - We describe a method for identifying and classifying acid-fast bacilli (AFB) and their associated morphotypes in the microscope-images of Ziehl-Neelsen stained sputum smears, in the context of tuberculosis (TB) screening by image processing. The importance of our work stems from the fact that the transformation of the classical rod-shaped AFB into certain other shapes is said to be related to TB drug-resistance. The first stage of processing involves color-segmentation in the HSV space by using Neural Networks and RUS-Boosted Decision Trees. The latter is used to alleviate the effects of class-imbalance between the pixels belonging to the AFB and the background. The second stage involves categorizing the bacilli into regular rod-shaped ones (possibly beaded), their morphotypes ("V-shaped" or "Y-shaped" bacilli), and clumps. The main, and novel contribution in this paper involves identifying and classifying the bacterial morphotypes. For that purpose, we propose and investigate three different methods: The first involves assuming the morphotypes to be letters of the English alphabet, and using a letter-recognition technique based on the Hotelling Transform and the Discrete Cosine Transform on the color-segmented bacilli. The second method uses moment-based invariants on the silhouettes, boundaries and skeletons, respectively. We use Support Vector Machine and Weighted K-NN classifiers in both the cases. In addition, we describe a new method based on the ends of the skeleton. Experiments on 72 images of sputum-smears revealed that the skeleton-based approach performed better than the other methods.

AB - We describe a method for identifying and classifying acid-fast bacilli (AFB) and their associated morphotypes in the microscope-images of Ziehl-Neelsen stained sputum smears, in the context of tuberculosis (TB) screening by image processing. The importance of our work stems from the fact that the transformation of the classical rod-shaped AFB into certain other shapes is said to be related to TB drug-resistance. The first stage of processing involves color-segmentation in the HSV space by using Neural Networks and RUS-Boosted Decision Trees. The latter is used to alleviate the effects of class-imbalance between the pixels belonging to the AFB and the background. The second stage involves categorizing the bacilli into regular rod-shaped ones (possibly beaded), their morphotypes ("V-shaped" or "Y-shaped" bacilli), and clumps. The main, and novel contribution in this paper involves identifying and classifying the bacterial morphotypes. For that purpose, we propose and investigate three different methods: The first involves assuming the morphotypes to be letters of the English alphabet, and using a letter-recognition technique based on the Hotelling Transform and the Discrete Cosine Transform on the color-segmented bacilli. The second method uses moment-based invariants on the silhouettes, boundaries and skeletons, respectively. We use Support Vector Machine and Weighted K-NN classifiers in both the cases. In addition, we describe a new method based on the ends of the skeleton. Experiments on 72 images of sputum-smears revealed that the skeleton-based approach performed better than the other methods.

UR - http://www.scopus.com/inward/record.url?scp=85004028295&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85004028295&partnerID=8YFLogxK

U2 - 10.1109/SPCOM.2016.7746682

DO - 10.1109/SPCOM.2016.7746682

M3 - Conference contribution

BT - 2016 International Conference on Signal Processing and Communications, SPCOM 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Soans RS, Ramakrishnan AG, Shenoy VP, Galigekere RR. Classification of bacterial morphotypes from images of ZN-stained sputum-smears towards diagnosing drug-resistant TB. In 2016 International Conference on Signal Processing and Communications, SPCOM 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7746682 https://doi.org/10.1109/SPCOM.2016.7746682