Automatic assessment of the degree of TB-infection using images of ZN-stained sputum smear: New results

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

1 Citation (Scopus)

Abstract

We present new results in the context of automatic assessment of the presence of acid fast bacilli (AFB) in images of ZN-stained sputum smears. Specifically, the first phase involving color segmentation in the HSV space is improved in terms of quality by using a decision-Tree classifier. Further, we have recognized the possibility of staining artifacts of large size, and propose a method of discriminating the same from clumps of AFB. The method involves the use of Haralick's texture features. Its importance lies in the fact that the presence of large clumps or even several small clumps in an image of a sputum smear generally indicates a higher degree of infection. The results of segmentation-as assessed by the Sorenson-Dice coefficient & the Hausdorff distance-are better than those pertaining to our previous work. The counts of AFB are close to those based on visual inspection, and the clumps could be separated from large staining artifacts successfully.

Original languageEnglish
Title of host publication2016 International Conference on Systems in Medicine and Biology, ICSMB 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages22-25
Number of pages4
ISBN (Electronic)9781467376662
DOIs
Publication statusPublished - 28-04-2017
Event2016 International Conference on Systems in Medicine and Biology, ICSMB 2016 - Kharagpur, India
Duration: 04-01-201607-01-2016

Conference

Conference2016 International Conference on Systems in Medicine and Biology, ICSMB 2016
CountryIndia
CityKharagpur
Period04-01-1607-01-16

Fingerprint

Bacilli
Sputum
Bacillus
Artifacts
Acids
Infection
Staining and Labeling
Decision Trees
Decision trees
Classifiers
Color
Textures
Inspection

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Health Informatics
  • Radiology Nuclear Medicine and imaging
  • Assessment and Diagnosis
  • Human-Computer Interaction

Cite this

Soans, R. S., Shenoy, V. P., & Galigekere, R. R. (2017). Automatic assessment of the degree of TB-infection using images of ZN-stained sputum smear: New results. In 2016 International Conference on Systems in Medicine and Biology, ICSMB 2016 (pp. 22-25). [7915079] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSMB.2016.7915079
Soans, Rijul Saurabh ; Shenoy, Vishnu Prasad ; Galigekere, Ramesh R. / Automatic assessment of the degree of TB-infection using images of ZN-stained sputum smear : New results. 2016 International Conference on Systems in Medicine and Biology, ICSMB 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 22-25
@inproceedings{e60acc928cef459bba6b7fa0b2dc10dc,
title = "Automatic assessment of the degree of TB-infection using images of ZN-stained sputum smear: New results",
abstract = "We present new results in the context of automatic assessment of the presence of acid fast bacilli (AFB) in images of ZN-stained sputum smears. Specifically, the first phase involving color segmentation in the HSV space is improved in terms of quality by using a decision-Tree classifier. Further, we have recognized the possibility of staining artifacts of large size, and propose a method of discriminating the same from clumps of AFB. The method involves the use of Haralick's texture features. Its importance lies in the fact that the presence of large clumps or even several small clumps in an image of a sputum smear generally indicates a higher degree of infection. The results of segmentation-as assessed by the Sorenson-Dice coefficient & the Hausdorff distance-are better than those pertaining to our previous work. The counts of AFB are close to those based on visual inspection, and the clumps could be separated from large staining artifacts successfully.",
author = "Soans, {Rijul Saurabh} and Shenoy, {Vishnu Prasad} and Galigekere, {Ramesh R.}",
year = "2017",
month = "4",
day = "28",
doi = "10.1109/ICSMB.2016.7915079",
language = "English",
pages = "22--25",
booktitle = "2016 International Conference on Systems in Medicine and Biology, ICSMB 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Soans, RS, Shenoy, VP & Galigekere, RR 2017, Automatic assessment of the degree of TB-infection using images of ZN-stained sputum smear: New results. in 2016 International Conference on Systems in Medicine and Biology, ICSMB 2016., 7915079, Institute of Electrical and Electronics Engineers Inc., pp. 22-25, 2016 International Conference on Systems in Medicine and Biology, ICSMB 2016, Kharagpur, India, 04-01-16. https://doi.org/10.1109/ICSMB.2016.7915079

Automatic assessment of the degree of TB-infection using images of ZN-stained sputum smear : New results. / Soans, Rijul Saurabh; Shenoy, Vishnu Prasad; Galigekere, Ramesh R.

2016 International Conference on Systems in Medicine and Biology, ICSMB 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 22-25 7915079.

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

TY - GEN

T1 - Automatic assessment of the degree of TB-infection using images of ZN-stained sputum smear

T2 - New results

AU - Soans, Rijul Saurabh

AU - Shenoy, Vishnu Prasad

AU - Galigekere, Ramesh R.

PY - 2017/4/28

Y1 - 2017/4/28

N2 - We present new results in the context of automatic assessment of the presence of acid fast bacilli (AFB) in images of ZN-stained sputum smears. Specifically, the first phase involving color segmentation in the HSV space is improved in terms of quality by using a decision-Tree classifier. Further, we have recognized the possibility of staining artifacts of large size, and propose a method of discriminating the same from clumps of AFB. The method involves the use of Haralick's texture features. Its importance lies in the fact that the presence of large clumps or even several small clumps in an image of a sputum smear generally indicates a higher degree of infection. The results of segmentation-as assessed by the Sorenson-Dice coefficient & the Hausdorff distance-are better than those pertaining to our previous work. The counts of AFB are close to those based on visual inspection, and the clumps could be separated from large staining artifacts successfully.

AB - We present new results in the context of automatic assessment of the presence of acid fast bacilli (AFB) in images of ZN-stained sputum smears. Specifically, the first phase involving color segmentation in the HSV space is improved in terms of quality by using a decision-Tree classifier. Further, we have recognized the possibility of staining artifacts of large size, and propose a method of discriminating the same from clumps of AFB. The method involves the use of Haralick's texture features. Its importance lies in the fact that the presence of large clumps or even several small clumps in an image of a sputum smear generally indicates a higher degree of infection. The results of segmentation-as assessed by the Sorenson-Dice coefficient & the Hausdorff distance-are better than those pertaining to our previous work. The counts of AFB are close to those based on visual inspection, and the clumps could be separated from large staining artifacts successfully.

UR - http://www.scopus.com/inward/record.url?scp=85003806944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85003806944&partnerID=8YFLogxK

U2 - 10.1109/ICSMB.2016.7915079

DO - 10.1109/ICSMB.2016.7915079

M3 - Conference contribution

AN - SCOPUS:85003806944

SP - 22

EP - 25

BT - 2016 International Conference on Systems in Medicine and Biology, ICSMB 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Soans RS, Shenoy VP, Galigekere RR. Automatic assessment of the degree of TB-infection using images of ZN-stained sputum smear: New results. In 2016 International Conference on Systems in Medicine and Biology, ICSMB 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 22-25. 7915079 https://doi.org/10.1109/ICSMB.2016.7915079