Use of General Purpose GPU Programming to Enhance the Classification of Leukaemia Blast Cells in Blood Smear Images

  • Stefan Skrobanski
  • Stelios Pavlidis
  • Waidah Ismail
  • Rosline Hassan
  • Steve Counsell
  • Stephen Swift
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7619)

Abstract

Leukaemia is a life threatening form of cancer, which causes an uncontrollable increase in the production of malformed white blood cells, termed blasts, inhibiting the body’s ability to fight infection. Given the variety of leukaemia types and the disease’s nature, prompt diagnosis is essential for the choice of appropriate, timely patient treatment. Currently, however, the diagnostic process is time consuming and laborious. To target this issue we propose a methodology based on an existing system, for automated blast detection and diagnosis from a set of blood smear images, utilising a mixture of image processing, cellular automata, heuristic search and classification techniques. Our system builds upon this work, by employing General Purpose Graphical Processing Unit programming, to shorten execution times. Additionally, we utilise an enhanced ellipse-fitting algorithm for blast cell detection, yielding more information from captured cells. We show that the methodology is efficient, producing highly accurate classification results.

Keywords

General Purpose GPU Programming Image Processing Leukaemia Evolutionary Programming Classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hassan, R.: Molecular Diagnosis in Acute Leukaemia: Hospital University’s experience. In: International Joint Symposium Frontier In Biomedical Sciences: From Genes to Applications, Faculty of Medicine, Gadjah Mada University, Yogyakarta, Indonesia (2008) Google Scholar
  2. 2.
    Vardiman, J.W., Harris, N.L., Brunning, R.D.: The World Health Organization (WHO) classification of the myeloid neoplasms. Blood 100(7), 2292–2302 (2002)CrossRefGoogle Scholar
  3. 3.
    Nipon, T.U., Gader, P.: System-level training of neural networks for counting white blood cells. IEEE Trans. SMS-C 32(1), 48–53 (2002)Google Scholar
  4. 4.
    Yi, D.H., Rashid, S., Cibas, E.S., Arrigg, P.G., Dana, M.R.: Acute unilateral leukemic hypopyon in an adult with relapsing acute lymphoblastic leukemia. Am. J. Ophthalmol. 139, 719–721 (2005)CrossRefGoogle Scholar
  5. 5.
    Petrou, M., Petrou, C.: Image Processing, The Fundamentals, 2nd edn. John Wiley and Sons, Ltd, Chichester (2010)MATHCrossRefGoogle Scholar
  6. 6.
    Piuri, V., Scotti, F.: Morphological Classification of Blood Leucocytes by Microscope Images. In: IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, Boston, MA (2004)Google Scholar
  7. 7.
    Jiang, K., Liao, Q.M., Xiong, Y.: A novel white blood cell segmentation scheme based on feature space clustering. Soft Computing - A Fusion of Foundations, Methodologies and Applications 10(1), 12–19 (2006)Google Scholar
  8. 8.
    Zamini, F., Safabakhsh, R.: An unsupervised GVF Snake Approach for White Blood Cell Segmentation based on Nucleus. In: International Conference on Signal Processing Proceedings (ICSP), Beijing (2006)Google Scholar
  9. 9.
    Yampri, P., Pintavirooj, C., Daochai, S., Teartulakarn, S.: White Blood Cell Classification based on the Combination of Eigen Cell and Parametric Feature Detection. In: 1st IEEE Conference on Industrial Electronics and Applications, Singapore (2006)Google Scholar
  10. 10.
    Zerfass, T., Schlarb, T., Elter, M.: Segmentation of leukocyte cells in bone marrow smears. In: 23rd International Symposium on Computer-Based Medical Systems (CBMS), Perth, WA (2010)Google Scholar
  11. 11.
    Borovicka, J.: Circle Detection Using Hough Transform. University of Bristol, BristolGoogle Scholar
  12. 12.
    Mulchrone, K.F., Choudhury, K.R.: Fitting an Ellipse to an Arbitary Shape: Implications for Strain Analysis. Journal of Structural Geology 26, 143–153 (2004)CrossRefGoogle Scholar
  13. 13.
    Ismail, W., Hassan, R., Swift, S.: Detecting Leukaemia (AML) Blood Cells Using Cellular Automata and Heuristic Search. In: Cohen, P.R., Adams, N.M., Berthold, M.R. (eds.) IDA 2010. LNCS, vol. 6065, pp. 54–66. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  14. 14.
    Ismail, W., Swift, S.: Detecting Leukaemia (AML) blood cells using Genetic Algorithms. In: SCOR 2010. Brunel University, London (2010)Google Scholar
  15. 15.
    Microsoft, n.d., Standard Template Library, http://msdn.microsoft.com/en-us/library/c191tb28.aspx (accessed March 23, 2012)
  16. 16.
    LibTIFF - TIFF Library and Utilities, http://www.libtiff.org/libtiff.html (accessed March 23, 2012)
  17. 17.
    NVIDIA CUDA C Programming Guide. NVIDIA Corporation, Santa Clara (2011) Google Scholar
  18. 18.
    Wen-Mei, H.W.: GPU Computing Gems Emerald Edition, 1st edn. Morgan Kaufmann, San Francisco (2011)Google Scholar
  19. 19.
    NVidia, CURAND Library. 1st edn. NVidia Corporation (2010)Google Scholar
  20. 20.
    Microsoft, GDI+, http://msdn.microsoft.com/en-us/library/ms533798v=vs.85.aspx (accessed March 23, 2012)
  21. 21.
    Otsu, N.: A Threshold Selection Method from Gray-Level Historgrams. IEEE Transactions on Systems, Man, and Cybernetics SMC-9(1), 62–67 (1979)MathSciNetGoogle Scholar
  22. 22.
    Bandini, S.: Cellular Automata. Future Generation Computer Systems 18(7) (2002)Google Scholar
  23. 23.
    Fang, L.: The New Adaptive Evolutionary Programing. In: IEEE Proceedings of the Ninth International Conference on Machine Learning and Cybernetics, Qingdao (2010)Google Scholar
  24. 24.
    Ghozeil, A., Fogel, B.D.: Discovering Patterns in Sptial Data Using Evolutionary Programming. In: GECCO Genetic and Evolutionary Computation Conference. MIT Press, Cambridge (1996)Google Scholar
  25. 25.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA Data Mining Software: An Update. SIGKDD Explorations 11(1), 10–18 (2009)CrossRefGoogle Scholar
  26. 26.
    Zhu, N., Wang, G., Yang, G., Dai, W.: A fats 2D Otsu Thresholding Algorithm Based on Improved Histogram. In: CCPR Chinese Conference on Pattern Recognition, Nanjing (2009)Google Scholar
  27. 27.
    Ismail, W.: Automatic Detection and Classification of Leukaemia Cells. PhD Thesis, School of Information systems, Computing and mathematics, Brunel University, London, UK (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Stefan Skrobanski
    • 1
  • Stelios Pavlidis
    • 2
  • Waidah Ismail
    • 2
  • Rosline Hassan
    • 3
  • Steve Counsell
    • 2
  • Stephen Swift
    • 2
  1. 1.Arithmetica LtdLondonUK
  2. 2.Department of Information Systems and ComputingBrunel UniversityLondonUK
  3. 3.Department of Haematology, School of Medical SciencesUniversiti Sains MalaysiaMalaysia

Personalised recommendations