Advertisement

Classification of Tuberculosis Digital Images Using Hybrid Evolutionary Extreme Learning Machines

  • Ebenezer Priya
  • Subramanian Srinivasan
  • Swaminathan Ramakrishnan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7653)

Abstract

In this work, classification of Tuberculosis (TB) digital images has been attempted using active contour method and Differential Evolution based Extreme Learning Machines (DE-ELM). The sputum smear positive and negative images (N=100) recorded under standard image acquisition protocol are subjected to segmentation using level set formulation of active contour method. Moment features are extracted from the segmented images using Hu’s and Zernike method. Further, the most significant moment features derived using Principal Component Analysis and Kernel Principal Component Analysis (KPCA) are subjected to classification using DE-ELM. Results show that the segmentation method identifies the bacilli retaining their shape in-spite of artifacts present in the images. It is also observed that with the KPCA derived significant features, DE-ELM performed with higher accuracy and faster learning speed in classifying the images.

Keywords

Tuberculosis Sputum smear images Active contours Level sets Principal Component Analysis Kernel Principal Component Analysis Hu’s moments Zernike moments Extreme learning machines Differential evolution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Khutlang, R., Krishnan, S., Whitelaw, A., Douglas, T.S.: Automated detection of tuberculosis in Ziehl-Neelsen-stained sputum smears using two one-class classifiers. J. Microsc. 237(1), 96–102 (2010)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Forero, M.G., Cristobal, G., Desco, M.: Automatic identification of Mycobacterium tuberculosis by Gaussian mixture models. J. Microsc. 223(2), 120–132 (2006)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Sadaphal, P., Rao, J., Comstock, G.W., Beg, M.F.: Image processing techniques for identifying Mycobacterium tuberculosis in Ziehl-Neelsen stains. Int. J. Tuberc. Lung. Dis. 12(5), 579–582 (2008)Google Scholar
  4. 4.
    Veropoulos, K.: Machine learning approaches to medical decision making. Ph.D dissertation, University of Bristol (2001)Google Scholar
  5. 5.
    Chan, T., Moelich, M., Sandberg, B.: Some Recent Developments in Variational Image Segmentation. In: Tai, X.-C., Lie, K.-A., Chan, T.F., Osher, S. (eds.) Image Processing Based on Partial Differential Equations, Proceeding of the International Conference on PDE-Based Image Processing and Related Inverse Problems, CMA, Oslo, pp. 175–211. Springer, Heidelberg (2007)Google Scholar
  6. 6.
    Osman, M.K., Mashor, M.Y., Jaafar, H.: Detection of Mycobacterium Tuberculosis in Ziehl Neelsen Stained Tissue Images using Zernike Moments and Hybrid Multilayered Perceptron Network. In: IEEE International Conference on Systems Man and Cybernetics, Istanbul, Turkey, pp. 4049–4055 (2010)Google Scholar
  7. 7.
    Ruberto, C.D., Morgera, A.: Moment-based Techniques for Image Retrieval. In: 19th International Conference on Database and Expert Systems Application, Turin, Italy, pp. 155–159 (2008)Google Scholar
  8. 8.
    Chen, Q., Petriu, E., Yang, X.: A comparative study of Fourier Descriptors and Hu’s Seven Moment Invariants for Image Recognition. In: Canadian Conference on Electrical and Computer Engineering, Niagara Falls, vol. 1, pp. 103–106 (2004)Google Scholar
  9. 9.
    Arvacheh, E.M., Tizhoosh, H.R.: Pattern Analysis Using Zernike Moments. In: Instrumentation and Measurement Technology Conference, Ottawa, Canada, pp. 1574–1578 (2005)Google Scholar
  10. 10.
    Dastidar, S.G., Adeli, H., Dadmehr, N.: Principal component analysis – enhanced cosine radial basis function neural network for robust epilepsy and seizure detection. IEEE Trans. Biomed. Eng. 55(2), 512–518 (2008)CrossRefGoogle Scholar
  11. 11.
    Latifoglu, F., Polat, K., Kara, S., Gunes, S.: Medical diagnosis of atherosclerosis from Carotid Artery Doppler Signals using principal component analysis (PCA), k-NN based weighting pre-processing and Artificial Immune Recognition System (AIRS). J. Biomed. Inform. 41(1), 15–23 (2008)CrossRefGoogle Scholar
  12. 12.
    Polat, K., Gunes, S.: Computer aided medical diagnosis system based on principal component analysis and artificial immune recognition system classifier algorithm. Expert Syst. Appl. 34(1), 773–779 (2008)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Cui, P., Li, J., Wang, G.: Improved kernel principal component analysis for fault detection. Expert Syst. Appl. 34(2), 1210–1219 (2008)CrossRefGoogle Scholar
  14. 14.
    Iqbal, A., Valous, N.A., Sun, D.-W., Allen, P.: Parsimonious classification of binary lacunarity data computed from food surface images using kernel principal component analysis and artificial neural networks. Meat Sci. 87(2), 107–114 (2011)CrossRefGoogle Scholar
  15. 15.
    Kim, K.I., Franz, M.O., Schölkopf, B.: Iterative kernel principal component analysis for image modeling. IEEE Trans. Pattern Anal. Mach. Intell. 27(9), 1351–1366 (2005)CrossRefGoogle Scholar
  16. 16.
    Yusoff, I.A., Isa, N.A.M., Othman, N.H., Sulaiman, S.N., Jusman, Y.: Performance of Neural Network Architectures: Cascaded MLP versus Extreme Learning Machine on cervical cell image classification. In: 10th International Conference on Information Science, Signal Processing and their Applications, Kuala Lumpur, Malaysia, pp. 308–311 (2010)Google Scholar
  17. 17.
    Huynh, H.T., Won, Y.: Hematocrit Estimation from Compact Single Hidden Layer Feedforward Neural Networks Trained by Evolutionary Algorithm. In: IEEE Congress on Evolutionary Computation, Hong Kong, pp. 2962–2966 (2008)Google Scholar
  18. 18.
    Jiang, X., Nie, S.: Urine Sediment Image Segmentation based on Level Set and Mumford-Shah Model. In: The 1st International Conference on Bioinformatics and Biomedical Engineering, China, pp. 1028–1030 (2007)Google Scholar
  19. 19.
    Huang, Z., Leng, J.: Analysis of Hu’s Moment Invariants on Image Scaling and Rotation. In: 2nd International conference on Computer Engineering and Technology, Chengdu, China, vol. 7, pp. 476–480 (2010)Google Scholar
  20. 20.
    Fu, X., Li, Y., Harrison, R., Belkasim, S.: Content-based Image Retrieval Using Gabor-Zernike Features. In: 18th International Conference on Pattern Recognition, Hong Kong, vol. 2, pp. 417–420 (2006)Google Scholar
  21. 21.
    Aguado, D., Montoy, T., Borras, L., Seco, A., Ferrer, J.: Using SOM and PCA for analyzing and interpreting data from a P-removal SBR. Eng. Appl. Artif. Intel. 21(6), 919–930 (2008)CrossRefGoogle Scholar
  22. 22.
    Huynh, H.T., Won, Y.: Evolutionary algorithm for training compact single hidden layer feedforward neural networks. In: IEEE International Joint Conference on Neural Networks, Hong Kong, pp. 3028–3033 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Ebenezer Priya
    • 1
  • Subramanian Srinivasan
    • 1
  • Swaminathan Ramakrishnan
    • 2
  1. 1.Department of Instrumentation Engineering, MIT CampusAnna UniversityChennaiIndia
  2. 2.Biomedical Engineering Group, Department of Applied MechanicsIIT MadrasChennaiIndia

Personalised recommendations