skip to main content
10.1145/3555776.3578609acmconferencesArticle/Chapter ViewAbstractPublication PagessacConference Proceedingsconference-collections
poster

Estimating Phenotypic Characteristics of Tuberculosis Bacteria

Published: 07 June 2023 Publication History

Abstract

Microscopy analysis of sputum images for bacilli screening is a common method used for both diagnosis and therapy monitoring of tuberculosis (TB). Nonetheless, it is a challenging procedure, since sputum examination is time-consuming and needs highly competent personnel to provide accurate results which are important for clinical decision-making. In addition, manual fluorescence microscopy examination of sputum samples for tuberculosis diagnosis and treatment monitoring is a subjective operation. In this work, we automate the process of examining fields of view (FOVs) of TB bacteria in order to determine the lipid content, and bacterial length and width. We propose a modified version of the UNet model to rapidly localise potential bacteria inside a FOV. We introduce a novel method that uses Fourier descriptors to exclude contours that do not belong to the class of bacteria, hence minimising the amount of false positives. Finally, we propose a new feature as a means of extracting a representation fed into a support vector multi-regressor in order to estimate the length and width of each bacterium. Using a real-world data corpus, the proposed method i) outperformed previous methods, and ii) estimated the cell length and width with a root mean square error of less than 0.01%.

References

[1]
B. B. Aldridge et al. 2012. Asymmetry and Aging of Mycobacterial Cells Lead to Variable Growth and Antibiotic Susceptibility. Science (2012).
[2]
Ognjen Arandjelović. 2014. Hallucinating optimal high-dimensional subspaces. Pattern Recognit (2014).
[3]
R. Arandjelović and A. Zisserman. 2012. Three things everyone should know to improve object retrieval. In CVPR.
[4]
V. Balntas et al. 2016. Learning local feature descriptors with triplets and shallow convolutional neural networks. In BMVC.
[5]
Y. Bao et al. 2014. Multi-step-ahead time series prediction using multiple-output support vector regression. Neurocomputing (2014).
[6]
V. O. Baron et al. 2017. Label-free optical vibrational spectroscopy to detect the metabolic state of M. tuberculosis cells at the site of disease. Sci Rep (2017).
[7]
A. Beykikhoshk et al. 2015. Overcoming data scarcity of Twitter: using tweets as bootstrap with application to autism-related topic content analysis. In ASONAM.
[8]
Navneet Dalal and Bill Triggs. 2005. Histograms of oriented gradients for human detection. In CVPR. IEEE.
[9]
C. Deb et al. 2009. A novel in vitro multiple-stress dormancy model for mycobacterium tuberculosis generates a lipid-loaded, drug-tolerant, dormant pathogen. PLoS ONE (2009).
[10]
J. L. Díaz-Huerta et al. 2019. Image processing for AFB segmentation in bacillo-scopies of pulmonary tuberculosis diagnosis. PLoS ONE (2019).
[11]
D. H. Douglas and T. K. Peucker. 1973. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica (1973).
[12]
J. Fan and O. Arandjelović. 2018. Employing domain specific discriminative information to address inherent limitations of the LBP descriptor in face recognition. In IJCNN. IEEE.
[13]
S. H. Gillespie et al. 2022. Implications of drug-induced phenotypical resistance: is isoniazid radicalising M. tuberculosis? Front Antibiot (2022).
[14]
B. Guindon and Y. Zhang. 2017. Application of the dice coefficient to accuracy assessment of object-based image classification. Can J Remote Sens (2017).
[15]
C. B. Holmes et al. 1998. A review of sex differences in the epidemiology of tuberculosis. Int J Tuberc Lung Dis (1998).
[16]
X. Li et al. 2019. Dice loss for data-imbalanced NLP tasks. arXiv:1911.02855 (2019).
[17]
I. Loshchilov and F. Hutter. 2016. SGDR: Stochastic gradient descent with warm restarts. arXiv:1608.03983 (2016).
[18]
P. K. Mehta et al. 2012. Diagnosis of extrapulmonary tuberculosis by PCR. FEMS Immunol Med Microbiol (2012).
[19]
A. Mishchuk et al. 2017. Working hard to know your neighbor's margins: Local descriptor learning loss. NIPS (2017).
[20]
K. S. Mithra and W. R. Sam Emmanuel. 2019. Automated identification of mycobacterium bacillus from sputum images for tuberculosis diagnosis. Signal Image Video Process (2019).
[21]
A. Mukundan et al. 2019. Understanding and improving kernel local descriptors. Int J Comput Vis (2019).
[22]
T. Ojala et al. 1994. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. In ICPR.
[23]
R. O. Panicker et al. 2018. Automatic detection of tuberculosis bacilli from microscopic sputum smear images using deep learning methods. Biocybern Biomed Eng (2018).
[24]
M. Pultar. 2020. Improving the HardNet Descriptor. arXiv:2007.09699 (2020).
[25]
O. Ronneberger et al. 2015. U-net: Convolutional networks for biomedical image segmentation. In MICCAI.
[26]
J. Rumin et al. 2015. The use of fluorescent Nile red and BODIPY for lipid measurement in microalgae. Biotechnol Biofuel (2015).
[27]
D. P.S. Spence et al. 1993. Tuberculosis and poverty. BMJ (1993).
[28]
K. R. Steingart et al. 2007. A systematic review of commercial serological antibody detection tests for the diagnosis of extrapulmonary tuberculosis. Postgrad Med J (2007).
[29]
Y. Tian et al. 2019. Sosnet: Second order similarity regularization for local descriptor learning. In CVPR.
[30]
K. Toman. 2004. Toman's tuberculosis: case detection, treatment and monitoring. Questions and answers. World Health Organization.
[31]
D. Vente et al. 2019. Using Machine Learning for Automatic Estimation of M. Smegmatis Cell Count from Fluorescence Microscopy Images. W3PHIAI (2019).
[32]
Y. Wakamoto et al. 2013. Dynamic persistence of antibiotic-stressed mycobacteria. Science (2013).
[33]
World Health Organization. 2022. Global Tuberculosis Report. Technical Report. https://www.who.int/teams/global-tuberculosis-programme/tb-reports/global-tuberculosis-report-2022
[34]
X. Yue et al. 2019. Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles. In BiCoB.
[35]
M. Zachariou et al. 2022. Extracting and Classifying Salient Fields of View From Microscopy Slides of Tuberculosis Bacteria. In ICPRAI.
[36]
M. Zachariou et al. 2022. Tuberculosis bacteria detection and counting in fluorescence microscopy images using a multi-stage deep learning pipeline. Information (2022).

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
SAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing
March 2023
1932 pages
ISBN:9781450395175
DOI:10.1145/3555776
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 June 2023

Check for updates

Author Tags

  1. ACM proceedings
  2. microscopy
  3. machine learning
  4. fluorescence
  5. shape descriptors
  6. MSVR
  7. regression
  8. deep learning
  9. treatment monitoring
  10. tuberculosis
  11. mycobacterium tuberculosis

Qualifiers

  • Poster

Conference

SAC '23
Sponsor:

Acceptance Rates

Overall Acceptance Rate 1,650 of 6,669 submissions, 25%

Upcoming Conference

SAC '25
The 40th ACM/SIGAPP Symposium on Applied Computing
March 31 - April 4, 2025
Catania , Italy

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 33
    Total Downloads
  • Downloads (Last 12 months)13
  • Downloads (Last 6 weeks)0
Reflects downloads up to 16 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media