Research on Biomedical Engineering
http://www.rbejournal.periodikos.com.br/article/doi/10.1590/2446-4740.0524
Research on Biomedical Engineering
Original Article

Automatic identifi cation of tuberculosis mycobacterium

Costa Filho, Cícero Ferreira Fernandes; Levy, Pamela Campos; Xavier, Clahildek de Matos; Fujimoto, Luciana Botinelly Mendonça; Costa, Marly Guimarães Fernandes

Downloads: 0
Views: 903

Abstract

Introduction: According to the Global TB control report of 2013, “Tuberculosis (TB) remains a major global health problem. In 2012, an estimated 8.6 million people developed TB and 1.3 million died from the disease. Two main sputum smear microscopy techniques are used for TB diagnosis: Fluorescence microscopy and conventional microscopy. Fluorescence microscopy is a more expensive diagnostic method because of the high costs of the microscopy unit and its maintenance. Therefore, conventional microscopy is more appropriate for use in developing countries. Methods: This paper presents a new method for detecting tuberculosis bacillus in conventional sputum smear microscopy. The method consists of two main steps, bacillus segmentation and post-processing. In the fi rst step, the scalar selection technique was used to select input variables for the segmentation classifi ers from four color spaces. Thirty features were used, including the subtractions of the color components of different color spaces. In the post-processing step, three fi lters were used to separate bacilli from artifact: a size fi lter, a geometric fi lter and a Rule-based fi lter that uses the components of the RGB color space. Results: In bacillus identifi cation, an overall sensitivity of 96.80% and an error rate of 3.38% were obtained. An image database with 120-sputum-smear microscopy slices of 12 patients with objects marked as bacillus, agglomerated bacillus and artifact was generated and is now available online. Conclusions: The best results were obtained with a support vector machine in bacillus segmentation associated with the application of the three post-processing fi lters.

Keywords

Tuberculosis, Automatic bacillus identifi cation, Neural network, Support vector machine.

References

Bennedsen J, Larsen SO. Examination for tubercle bacili by fluorescence microscopy. Scandinavian Journal of Respiratory Diseases 1966; 47(2):114-20. PMid:4161476.

Costa MGF, Costa Filho CFF, Sena JF, Salem J, Lima MO. Automatic identification of mycobacterium tuberculosis with conventional light microscopy. In: Proceedings of 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2008. p. 382-5.

Costa Filho CFF, Costa MGF, Kimura Junior A. Autofocus functions for tuberculosis diagnosis with conventional sputum smear microscopy. In: Méndez-Vilas, A. editor. Current Microscopy Contributions to Advances in Science and Technology. Badajoz: Formatex; 2012. p. 13-20.

Forero MG, Cristóbal G, Alvarez-Borrego J. Automatic identification techniques of tuberculosis bacteria. Proceedings of the Society for Photo-Instrumentation Engineers 2003; 5203:71-81. http://dx.doi.org/10.1117/12.506800.

Forero MG, Sroubek F, Cristóbal G. Identification of tuberculosis bacteria based on geometric and color. Real Time Imaging 2004; 10(4):251-62. http://dx.doi.org/10.1016/j.rti.2004.05.007.

Forero MG, Cristóbal G, Desco M. Automatic identification of Mycobacterium tuberculosis by Gaussian mixture models. Journal of Microscopy 2006; 223(Pt 2):120-32. http://dx.doi.org/10.1111/j.1365-2818.2006.01610.x. PMid:16911072

Haykin S. Neural networks and learning machines. 3rd. ed. New Jersey: Pearson Prentice Hall; 1999.

Khutlang R, Krishnan S, Dendere R, Whitelaw A, Veropoulos K, Learmonth G, Douglas TS. Classification of Mycobacterium tuberculosis in images of ZN-stained sputum smears. IEEE Transactions on Information Technology in Biomedicine 2010; 14(4):949-57. http://dx.doi.org/10.1109/TITB.2009.2028339. PMid:19726269

Kimura A, Costa MGF, Costa Filho CFF, Fujimoto LBM, Salem J. Evaluation of autofocus functions of conventional sputum smear microscopy for tuberculosis. In: Proceedings of 32th Annual International IEEE EMBS Conference; 2010. p. 3041-4. http://dx.doi.org/10.1109/IEMBS.2010.5626143.

Lenseigne B, Brodin P, Jeon H, Christophe T, Genovesio A. Support vector machines for automatic detection of tuberculosis bacteria in confocal microscopy images. In: Proceedings of 4th IEEE International Symposium on Biomedical Imaging; 2007. p. 85-8. http://dx.doi.org/10.1109/ISBI.2007.356794.

Makkapati V, Agrawal R, Acharya R. Segmentation and classification of tuberculosis bacilli from ZN-stained sputum smear images. In: Proceedings of 5th Annual IEEE Conference on Automation Science and Engineering; 2009. p. 217-20. http://dx.doi.org/10.1109/COASE.2009.5234173.

Osman MK, Mashor MY, Jaafar H. Performance comparison and thresholding algorithms for tuberculosis bacilli segmentation. In: Proceedings of International Conference of Computer, Information and Telecommunication Systems (CITS); 2012. p. 1-5. http://dx.doi.org/10.1109/CITS.2012.6220378.

Raof RAA, Salleh Z, Sahidan SI, Mashor MY, Noor SS, Idris FM, Hasan H. Color thresholding method for image segmentation algorithm of Ziehl-Neelsen sputum slide images. In: Proceedings of 5th International Conference on Electrical Engineering, Computing Science and Automatic Control; 2008. p. 212-7. http://dx.doi.org/10.1109/ICEEE.2008.4723398.

Sadaphal P, Rao J, Comstock GW, Beg MF. Image processing techniques for identifying Mycobacterium tuberculosis in Ziehl-Neelsen stains. The International Journal of Tuberculosis and Lung Disease 2008; 12(5):579-82. PMid:18419897.

Santos A, Ortiz de Solórzano C, Vaquero JJ, Peña JM, Malpica N, del Pozo F. Evaluation of autofocus functions in molecular cytogenetic analysis. Journal of Microscopy 1997; 188(Pt 3):264-72. http://dx.doi.org/10.1046/j.1365-2818.1997.2630819.x. PMid:9450330

Sotaquirá M, Rueda L, Narvaez R. Detection and quantification of bacilli and clusters present in sputum smear samples: a novel algorithm for pulmonary tuberculosis diagnosis. In: Proceedings of International Conference on Digital Image Processing; 2009. p. 117-21. http://dx.doi.org/10.1109/ICDIP.2009.59.

Steingart KR, Henry M, Ng V, Hopewell PC, Ramsay A, Cunningham J, Urbanczik R, Perkins M, Aziz MA, Pai M. Fluorescence versus conventional sputum smear microscopy for tuberculosis: a systematic review. The Lancet Infectious Diseases 2006; 6(9):570-81. http://dx.doi.org/10.1016/S1473-3099(06)70578-3. PMid:16931408

Theodoridis S, Koutroumbas K. Pattern recognition. 4th ed. Amsterdam: Academic Press; 2009.

Toman K. How reliable is smear microscopy? In: Frieden T, editor. Toman’s Tuberculosis: case detection, treatment, and monitoring. Questions and answers. WHO; 2004a. p. 14-23.

Toman K. What are the advantages and disadvantages of fluorescence microscopy? In: Frieden T, editor. Toman’s Tuberculosis: case detection, treatment, and monitoring. Questions and answers. WHO; 2004b. p. 31-5.

United Nations - UN. The millennium development goals report [internet]. 2010 [cited 2013 Dec 18]. Available from: http://www.un.org/millenniumgoals/reports.shtml.

Veropoulos K, Campbell C, Learmonth G, Knight B, Simpson J. The automated identification of tubercle bacilli using image processing and neural computing techniques. In: Proceedings of 8th International Conference on Artificial Neural Networks; 1998. p. 797-802. http://dx.doi.org/10.1007/978-1-4471-1599-1_123.

World Health Organization - WHO. Global TB Control report. [internet]. 2010 [cited 2013 Dec 18]. Available from:http://www.who.int/tb/publications/global_report/2010/en/index.html.

World Health Organization - WHO. Global TB control report. [internet]. 2013. [cited 2014 Jan 24]. Available from: http://www.who.int/tb/publications/global_report/en.
5889fbeb5d01231a018b485f rbejournal Articles
Links & Downloads

Res. Biomed. Eng.

Share this page
Page Sections