Using the low-pass monogenic signal framework for cell/background classification on multiple cell lines in bright-field microscope images

  • Firas Mualla
  • Simon Schöll
  • Björn Sommerfeldt
  • Andreas Maier
  • Stefan Steidl
  • Rainer Buchholz
  • Joachim Hornegger
Original Article

Abstract

Purpose

   Several cell detection approaches which deal with bright-field microscope images utilize defocusing to increase image contrast. The latter is related to the physical light phase through the transport of intensity equation (TIE). Recently, it was shown that it is possible to approximate the solution of the TIE using a low-pass monogenic signal framework. The purpose of this paper is to show that using the local phase of the aforementioned monogenic signal instead of the defocused image improves the cell/background classification accuracy.

Materials and methods

   The paper statement was tested on an image database composed of three cell lines: adherent CHO, adherent L929, and Sf21 in suspension. Local phase and local energy images were generated using the low-pass monogenic signal framework with axial derivative images as input. Machine learning was then employed to investigate the discriminative power of the local phase. Three classifier models were utilized: random forest (RF), support vector machine (SVM) with a linear kernel, and SVM with a radial basis function (RBF) kernel.

Results

   The improvement, averaged over cell lines, of classifying \(5 \times 5\) sized patches extracted from the local phase image instead of the defocused image was \(7.3\) % using the RF, \(11.6\) % using the linear SVM, and \(10.2\) % when a RBF kernel was employed instead of the linear one. Furthermore, the feature images can be sorted by increasing discriminative power as follows: at-focus signal, local energy, defocused signal, local phase. The only exception to this order was the superiority of local energy over defocused signal for suspended cells.

Conclusions

   Local phase computed using the low-pass monogenic signal framework considerably outperforms the defocused image for the purpose of pixel-patch cell/background classification in bright-field microscopy.

Keywords

Monogenic signal Cell detection  Bright-field microscopy Transport of intensity equation Local phase  Machine learning 

References

  1. 1.
    Agero U, Monken CH, Ropert C, Gazzinelli RT, Mesquita ON (2003) Cell surface fluctuations studied with defocusing microscopy. Phys Rev E 67(5):051904CrossRefGoogle Scholar
  2. 2.
    Ali R, Gooding M, Szilágyi T, Vojnovic B, Christlieb M, Brady M (2012) Automatic segmentation of adherent biological cell boundaries and nuclei from brightfield microscopy images. Mach Vis Appl 23(4):607–621CrossRefGoogle Scholar
  3. 3.
    Ali R, Szilagyi T, Gooding M, Christlieb M, Brady M (2010) On the use of low-pass filters for image processing with inverse Laplacian models. J Math Imaging Vis 43:1–10Google Scholar
  4. 4.
    Becattini G, Mattos L, Caldwell D (2011) A novel framework for automated targeting of unstained living cells in bright field microscopy. In: Proceedings of the IEEE international symposium on biomedical imaging: from nano to macro, pp 195–198Google Scholar
  5. 5.
    Boukerroui D, Noble JA, Brady M (2004) On the choice of band-pass quadrature filters. J Math Imaging Vis 21(1–2):53–80CrossRefGoogle Scholar
  6. 6.
    Breiman L (2011) Random forests. Mach Learn 45(1):5–32Google Scholar
  7. 7.
    Chang CC, Lin CJ (2001) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27:1–27:27. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
  8. 8.
    Felsberg M, Sommer G (2001) The monogenic signal. IEEE Trans Signal Process 49(12):3136–3144CrossRefGoogle Scholar
  9. 9.
    Hamilton WR (1844) II. On quaternions; or on a new system of imaginaries in algebra. Lond Edinb Dublin Philos Mag J Sci 25(163):10–13Google Scholar
  10. 10.
    Sjöström Jesper P, Frydel B, Wahlberg L (1999) Artificial neural network-aided image analysis system for cell counting. Cytometry 36(1):18–26CrossRefGoogle Scholar
  11. 11.
    Khoshgoftaar T, Golawala M, Van Hulse J (2007) An empirical study of learning from imbalanced data using random forest. In: Proceedings of the IEEE International Conference on Tools with, Artificial Intelligence, vol 2, pp 310–317 Google Scholar
  12. 12.
    Long X, Cleveland W, Yao Y (2005) A new preprocessing approach for cell recognition. IEEE Trans Inf Technol Biomed 9(3):407–412PubMedCrossRefGoogle Scholar
  13. 13.
    Long X, Cleveland W, Yao Y (2006) Automatic detection of unstained viable cells in bright field images using a support vector machine with an improved training procedure. Comput Biol Med 36(4):339–362PubMedCrossRefGoogle Scholar
  14. 14.
    Mellor M, Brady M (2005) Phase mutual information as a similarity measure for registration. Med Image Anal 9(4):330–343PubMedCrossRefGoogle Scholar
  15. 15.
    Morrone MC, Ross J, Burr DC, Owens R (1986) Mach bands are phase dependent. Nature 324(6094):250–253CrossRefGoogle Scholar
  16. 16.
    Mualla F, Schöll S, Sommerfeldt B, Maier A, Hornegger J (2013) Automatic cell detection in bright-field microscope images using SIFT, random forests, and hierarchical clustering. IEEE Trans Med Image 32(12):2274–2286. doi:10.1109/TMI.2013.2280380 Google Scholar
  17. 17.
    Nattkemper T, Ritter H, Schubert W (1999) Extracting patterns of lymphocyte fluorescence from digital microscope images. Intell Data Anal Med Pharmacol 99:79–88Google Scholar
  18. 18.
    Popescu G (2011) Quantitative phase imaging of cells and tissues. McGraw-Hill, New YorkGoogle Scholar
  19. 19.
    Poularikas AD (2010) Handbook of formulas and tables for signal processing, vol 13. CRC Press, Boca Raton, FLGoogle Scholar
  20. 20.
    Russell B, Torralba A, Murphy K, Freeman W (2008) Labelme: a database and web-based tool for image annotation. Int J Comput Vis 77(1):157–173CrossRefGoogle Scholar
  21. 21.
    Scholkopf B, Smola AJ (eds) (2001) Learning with kernels. MIT Press, Cambridge, MAGoogle Scholar
  22. 22.
    Stein EM (1970) Singular integrals and differentiability properties of functions Elias M. Stein, vol 2. Princeton University Press, Princeton, NJGoogle Scholar
  23. 23.
    Teague MR (1983) Deterministic phase retrieval: a green’s function solution. J Opt Soc Am 73(11):1434–1441CrossRefGoogle Scholar
  24. 24.
    Tscherepanow M, Zöllner F, Hillebrand M, Kummert F (2008) Automatic segmentation of unstained living cells in bright-field microscope images. In: Advances in mass data analysis of images and signals in medicine, biotechnology, chemistry and food industry (Lecture notes in computer science), vol 5108. Springer, Berlin, pp 158–172Google Scholar

Copyright information

© CARS 2013

Authors and Affiliations

  • Firas Mualla
    • 1
  • Simon Schöll
    • 1
    • 2
    • 3
  • Björn Sommerfeldt
    • 4
  • Andreas Maier
    • 1
    • 3
  • Stefan Steidl
    • 1
  • Rainer Buchholz
    • 4
  • Joachim Hornegger
    • 1
    • 3
  1. 1.Pattern Recognition LabFriedrich-Alexander University Erlangen-NurembergErlangenGermany
  2. 2.ASTRUM IT GmbHErlangenGermany
  3. 3.Graduate School in Advanced Optical Technologies, SAOTFriedrich-Alexander University Erlangen-NurembergErlangenGermany
  4. 4.Institute of Bioprocess EngineeringFriedrich-Alexander University Erlangen-NurembergErlangenGermany

Personalised recommendations