Texture-Based Multiscale Segmentation: Application to Stromal Compartment Characterization on Ovarian Carcinoma Virtual Slides

  • Nicolas Signolle
  • Benoît Plancoulaine
  • Paulette Herlin
  • Marinette Revenu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5099)

Abstract

A multiscale segmentation strategy using wavelet-domain hidden Markov tree model and pairwise classifiers selection is tested in the present paper for histopathology virtual slide analysis. The classifiers selection is based on a study of the influence of hyper-parameters of the method. Combination of outputs of selected classifiers is then done with majority vote. The results of the segmentation of various types of stroma of ovarian carcinomas are presented and discussed.

Keywords

Majority Vote Combination Rule Virtual Slide Loose Connective Tissue Stromal Compartment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Wang, Y., Turner, R., Crookes, D., et al.: Investigation of methodologies for the segmentation of squamous epithelium from cervical histological virtual slides. In: IMVIP 2007, Int. Machine Vision and Image Processing Conference, pp. 83–90 (2007)Google Scholar
  2. 2.
    Pan, T.C., Mosaliganti, K., Machiraju, R., Cowden, D., Saltz, J.H.: Large scale image analysis and nuclear segmentation for digital microscopy images. In: APIII, Frontiers in Oncology and Pathology Informatics, Pittsburgh (2004)Google Scholar
  3. 3.
    Dombre, J.: Systèmes de représentation multi-échelles pour l’indexation et la restauration d’archives médiévales couleur. PhD thesis, University of Poitiers, France (2003)Google Scholar
  4. 4.
    Crouse, M.S., Nowak, R., Baraniuk, R.: Wavelet-based statistical signal processing using hidden markov models. IEEE Trans. Signal Processing 46, 886–902 (1998)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Mallat, S.: A wavelet tour of signal processing. Academic Press, London (1999)MATHGoogle Scholar
  6. 6.
    Elie, N., Labiche, A., Michels, J.J., Herlin, P.: Control of low resolution scanning of ovarian tumor stromal compartment. Image Analysis and Stereology 24(2), 85–93 (2005)Google Scholar
  7. 7.
    Tran, T., Elie, N., Plancoulaine, B., et al.: An original approach for quantification of blood vessels on the whole tumour section. Analytical cellular pathology 25(2), 63–75 (2003)Google Scholar
  8. 8.
    Elie, N., Plancoulaine, B., Signolle, J.P., Herlin, P.: Simple way of quantifying immunostained cell nuclei on the whole histologic section. Cytometry 56A(1), 37–45 (2003)CrossRefGoogle Scholar
  9. 9.
    Choi, H., Baraniuk, R.: Multiscale image segmentation using wavelet-domain hidden markov models. IEEE Trans. on Image Processing 10(9), 1309–1321 (2001)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Fan, G., Xia, X.G.: A joint multicontext and multiscale approach to bayesian segmentation. IEEE transactions on geoscience and Remote Sensing 39(12), 2680–2688 (2001)CrossRefGoogle Scholar
  11. 11.
    Hastie, T., Tibshirani, R.: Classification by pairwise coupling. Annals of statistics 26(2), 451–471 (1998)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Friedman, J.H.: Another approach to polychotomous classification. Technical report, Department of Statistics, Stanford University (1996)Google Scholar
  13. 13.
    Dietterich, T.G., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. Journal of Artificial Intelligence Research 2, 263–286 (1995)MATHGoogle Scholar
  14. 14.
    Allwein, E.L., Schapire, R.E., Singer, Y.: Reducing multiclass to binary: A unifying approach for margin classifiers. Journal of Machine Learning Research 1, 113–141 (2000)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Scheunders, P.: An orthogonal wavelet representation of multivalued images. IEEE Transactions Image Processing 12(6), 718–725 (2003)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Nicolas Signolle
    • 1
    • 2
  • Benoît Plancoulaine
    • 2
  • Paulette Herlin
    • 2
  • Marinette Revenu
    • 1
  1. 1.GREYC ENSICAEN UMR 6072CAENFrance
  2. 2.GRECAN EA 1772, iFR 146 ICOREUniversité de Caen, CLCC François BaclesseCAEN cedex 5France

Personalised recommendations