Rapid Prototyping of Image Analysis Applications

  • Cris L. Luengo Hendriks
  • Patrik Malm
  • Ewert Bengtsson
Chapter

Abstract

When developing a program to automate an image analysis task, one does not start with a blank slate. Far from it. Many useful algorithms have been described in the literature, and implemented countless times. When developing an image analysis program, experience points the programmer to one or several of these algorithms. The programmer then needs to try out various possible combinations of algorithms before finding a satisfactory solution. Having to implement these algorithms just to see if they work for this one particular application does not make much sense. This is the reason programmers and researches build up libraries of routines that they have implemented in the past, and draw on these libraries to be able to quickly string together a few algorithms and see how they work on the current application. Several image analysis packages exist, both commercial and free, and they can be used as a basis for building up such a library. None of these packages will contain all the necessary algorithms, but they should provide at least the most basic ones. This chapter introduces you to one such package, DIPimage, and demonstrates how one can proceed to quickly develop a solution to automate a routine medical task. As an illustrative example we use some of the approaches taken over the years to solve the long-standing classical medical image analysis problem of assessing a Pap smear. To make best use of this chapter, you should have MATLAB and DIPimage running on your computer, and try out the command sequences given.

References

  1. 1.
    Luengo Hendriks, C.L., van Vliet, L.J., Rieger, B., van Ginkel, M., Ligteringen, R.: DIPimage User Manual. Quantitative Imaging Group, Delft University of Technology, Delft, The Netherlands (1999–2010)Google Scholar
  2. 2.
    Traut, H.F., Papanicolaou, G.N.: Cancer of the uterus: the vaginal smear in its diagnosis. Cal. West. Med. 59(2), 121–122 (1943)Google Scholar
  3. 3.
    Christopherson, W.M., Parker, J.E., Mendez, W.M., Lundin Jr., F.E.: Cervix cancer death rates and mass cytologic screening. Cancer 26(4), 808–811 (1970)CrossRefGoogle Scholar
  4. 4.
    Bengtsson, E.: Fifty years of attempts to automate screening for cervical cancer. Med. Imaging Technol. 17(3), 203–210 (1999)Google Scholar
  5. 5.
    Tolles, W.E., Bostrom, R.C.: Automatic screening of cytological smears for cancer: the instrumentation. Ann. N. Y. Acad. Sci. 63, 1211–1218 (1956)CrossRefGoogle Scholar
  6. 6.
    Spencer, C.C., Bostrom, R.C.: Performance of the Cytoanalyzer in recent clinical trials. J. Natl. Cancer Inst. 29, 267–276 (1962)Google Scholar
  7. 7.
    Prewitt, J.M.S., Mendelsohn, M.L.: The analysis of cell images. Ann. N. Y. Acad. Sci. 128(3), 1035–1053 (1965)CrossRefGoogle Scholar
  8. 8.
    Watanabe, S., the CYBEST group: An automated apparatus for cancer prescreening: CYBEST. Comput. Graph. Image Process. 3(4), 350–358 (1974)CrossRefGoogle Scholar
  9. 9.
    Tanaka, N., Ikeda, H., Ueno, T., Watanabe, S., Imasato, Y.: Fundamental study of automatic cyto-screening for uterine cancer. II. Segmentation of cells and computer simulation. Acta Cytol. 21(1), 79–84 (1977)Google Scholar
  10. 10.
    Tanaka, N., Ikeda, H., Ueno, T., Takahashi, M., Imasato, Y.: Fundamental study of automatic cyto-screening for uterine cancer. I. Feature evaluation for the pattern recognition system. Acta Cytol. 21(1), 72–78 (1977)Google Scholar
  11. 11.
    Tanaka, N., Ueno, T., Ikeda, H., Ishikawa, A., Yamauchi, K., Okamoto, Y., Hosoi, S.: CYBEST model 4: automated cytologic screening system for uterine cancer utilizing image analysis processing. Anal. Quant. Cytol. Histol. 9(5), 449–453 (1987)Google Scholar
  12. 12.
    Burger, G., Jutting, U., Rodenacker, K.: Changes in benign cell populations in cases of cervical cancer and its precursors. Anal. Quant. Cytol. 3(4), 261–271 (1981)Google Scholar
  13. 13.
    MacAulay, C., Palcic, B.: An edge relocation segmentation algorithm. Anal. Quant. Cytol. Histol. 12(3), 165–171 (1990)Google Scholar
  14. 14.
    Serra, J.: Image Analysis and Mathematical Morphology. Academic, London (1982)MATHGoogle Scholar
  15. 15.
    Kuhl, F.P., Giardina, C.R.: Elliptic Fourier features of a closed contour. Comput. Graph. Image Process. 18(3), 236–258 (1982)CrossRefGoogle Scholar
  16. 16.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 3(6), 610–621 (1973)CrossRefGoogle Scholar
  17. 17.
    Galloway, M.M.: Texture analysis using gray level run lengths. Comput. Graph. Image Process. 4(2), 172–179 (1975)CrossRefGoogle Scholar
  18. 18.
    MacAulay, C., Palcic, B.: Fractal texture features based on optical density surface area. Use in image analysis of cervical cells. Anal. Quant. Cytol. Histol. 12(6), 394–398 (1990)Google Scholar
  19. 19.
    Lee, J., Nelson, A., Wilbur, D.C., Patten, S.F.: The development of an automated Papanicolaou smear screening system. Cancer 81, 332–336 (1998)CrossRefGoogle Scholar
  20. 20.
    DeCresce, R.P., Lifshitz, M.S.: PAPNET cytological screening system. Lab Med. 22, 276–280 (1991)Google Scholar
  21. 21.
    Luck, R.L., Scott, R.: Morphological classification system and method. US Patent 5,257,182, 1993Google Scholar
  22. 22.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)MATHGoogle Scholar
  23. 23.
    Mehnert, A.J.H.: Image Analysis for the Study of Chromatin Distribution in Cell Nuclei. Ph.D. Thesis, University of Queensland, Brisbane, Australia, 2003Google Scholar
  24. 24.
    Bamford, P., Lovell, B.: Unsupervised cell nucleus segmentation with active contours. Signal Process. 71(2), 203–213 (1998)MATHCrossRefGoogle Scholar
  25. 25.
    Li, B., Acton, S.T.: Active contour external force using vector field convolution for image segmentation. IEEE Trans. Image Process. 16(8), 2096–2106 (2007)MathSciNetCrossRefGoogle Scholar
  26. 26.
    Hutchinson, M.L., Cassin, C.M., Ball, H.G.: The efficacy of an automated preparation device for cervical cytology. Am. J. Clin. Pathol. 96(3), 300–305 (1991)Google Scholar
  27. 27.
    Howell, L.P., Davis, R.L., Belk, T.I., Agdigos, R., Lowe, J.: The AutoCyte preparation system for gynaecologic cytology. Acta Cytol. 42(1), 171–177 (1998)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Cris L. Luengo Hendriks
    • 1
  • Patrik Malm
    • 2
    • 3
  • Ewert Bengtsson
    • 2
    • 3
  1. 1.Centre for Image AnalysisSwedish University of Agricultural SciencesUppsalaSweden
  2. 2.Swedish University of Agricultural SciencesUppsalaSweden
  3. 3.Uppsala UniversityUppsalaSweden

Personalised recommendations