Epithelial Area Detection in Cytokeratin Microscopic Images Using MSER Segmentation in an Anisotropic Pyramid

  • Cristian Smochina
  • Radu Rogojanu
  • Vasile Manta
  • Walter Kropatsch
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7036)


The objective of semantic segmentation in microscopic images is to extract the cellular, nuclear or tissue components. This problem is challenging due to the large variations of features of these components (size, shape, orientation or texture). In this paper we present an automatic technique to robustly delimit the epithelial area (crypts) in microscopic images taken from colon tissues sections marked with cytokeratin-8. The epithelial area is highlighted using the anisotropic diffusion pyramid and segmented using MSER+. The crypts separation and lumen detection is performed by imposing topological constraints about the epithelial layer distribution within the tissue and the round-like shape of the crypt. The evaluation of the proposed method is made by comparing the results with ground-truth segmentations.


Crypt segmentation Anisotropic diffusion pyramid MSER Biomedical imaging Pathology Microscopy Fluorescence microscopy Image analysis 


  1. 1.
    Wu, H.S., Xu, R., Harpaz, N., Burstein, D., Gil, J.: Segmentation of intestinal gland images with iterative region growing. Journal of Microscopy 220(3), 190–204 (2005)CrossRefGoogle Scholar
  2. 2.
    Farjam, R., Soltanian-Zadeh, H., Jafari-Khouzani, K., Zoroofi, R.A.: An image analysis approach for automatic malignancy determination of prostate pathological images. Clinical Cytometry 72B(4), 227–240 (2007)CrossRefGoogle Scholar
  3. 3.
    Gunduz-Demir, C., Kandemir, M., Tosun, A.B., Sokmensuer, C.: Automatic segmentation of colon glands using object-graphs. Medical Image Analysis 14(1), 1–12 (2010)CrossRefGoogle Scholar
  4. 4.
    Naik, S., Doyle, S., Feldman, M., Tomaszewski, J., Madabhushi, A.: Gland segmentation and computerized Gleason grading of prostate histology by integrating low-, high-level and domain specific information. In: 2nd MICCAI Workshop on Microscopic Image Analysis with Application in Biology, Piscataway, NJ, USA (2007)Google Scholar
  5. 5.
    Chen, C.H., Lee, G.G.: Image Segmentation Using Multiresolution Wavelet Analysis and Expectation-Maximization (EM) Algorithm for Digital Mammography. International Journal of Imaging Systems and Technology 8(5), 491–504 (1997)CrossRefGoogle Scholar
  6. 6.
    Roshni, V.S., Raju, G.: Image Segmentation using Multiresolution Texture Gradient and Watershed Algorithm. International Journal of Computer Applications 22(5), 21–28 (2011)Google Scholar
  7. 7.
    Tolba, M.F., Mostafa, M.G., Gharib, T.F., Salem, M.A.: MR-Brain Image Segmentation Using Gaussian Multiresolution Analysis and the EM Algorithm. In: Proc. ICEIS (2), pp. 165–170 (2003)Google Scholar
  8. 8.
    Kimmel, R., Zhang, C., Bronstein, A., Bronstein, M.: Are MSER features really interesting?. IEEE Trans. PAMI (2010) (in press) Google Scholar
  9. 9.
    Donoser, M., Bischof, H.: 3D Segmentation by Maximally Stable Volumes (MSVs). In: 18th International Conference on Pattern Recognition (ICPR 2006), vol. 1, pp. 63–66 (2006)Google Scholar
  10. 10.
    Humphries, A., Wright, N.A.: Colonic Crypt Organization and Tumorigenesis: Human Colonic Crypts. Nature Reviews Cancer 8(6), 415–424 (2008)CrossRefGoogle Scholar
  11. 11.
    Moll, R., Divo, M., Langbein, L.: The human keratins: biology and pathology. Histochemistry and Cell Biology 129(6), 705–733 (2008)CrossRefGoogle Scholar
  12. 12.
    de Kruijf, E.M., van Nes, J.G.H., van de Velde, C.J.H., Putter, H., Smit Vincent, T.H.B.M., Liefers Gerrit, J., Kuppen, P.J.K., Tollenaar, R.A.E.M., Mesker, W.E.: Tumor-stroma ratio in the primary tumor is a prognostic factor in early breast cancer patients, especially in triple-negative carcinoma patients. Breast Cancer Research and Treatment 125(3), 687–696 (2011)CrossRefGoogle Scholar
  13. 13.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Addison-Wesley, Reading (1992)Google Scholar
  14. 14.
    Otsu, N.: A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics 9(1), 62–66 (1979)CrossRefGoogle Scholar
  15. 15.
    Kropatsch, W.G., Haxhimusa, Y., Ion, A.: Multiresolution Image Segmentations in Graph Pyramids. Applied Graph Theory in Computer Vision and Pattern Recognition 52, 3–41 (2007)Google Scholar
  16. 16.
    Smochina, C., Manta, V., Kropatsch, W.G.: Semantic Segmentation of Microscopic Images using a Morphological Hierarchy. In: Real, P., Diaz-Pernil, D., Molina-Abril, H., Berciano, A., Kropatsch, W. (eds.) CAIP 2011, Part I. LNCS, vol. 6854, pp. 102–109. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  17. 17.
    Weickert, J.: Anisotropic Diffusion in Image Processing. Teubner, Stuttgart (1998)zbMATHGoogle Scholar
  18. 18.
    Scharr, H., Weickert, J.: An anisotropic diffusion algorithm with optimized rotation invariance. In: German Association for Pattern Recognition, Kiel, Germany, pp. 460–467 (September 2000)Google Scholar
  19. 19.
    Acton, S.T., Bovik, A.C., Crawford, M.M.: Anisotropic diffusion pyramids for image segmentation. In: Proceedings of 1st IEEE International Conference on Image Processing (ICIP 1994), vol. 3, pp. 478–482 (1994)Google Scholar
  20. 20.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. BMVC, pp. 384–393 (2002)Google Scholar
  21. 21.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. International Journal of Computer Vision 65, 43–72 (2005)CrossRefGoogle Scholar
  22. 22.
    Chalana, V., Kim, Y.: A methodology for evaluation of boundary detection algorithms on medical images. IEEE Trans. Med. Imag. 16(5), 642–652 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Cristian Smochina
    • 1
  • Radu Rogojanu
    • 2
  • Vasile Manta
    • 1
  • Walter Kropatsch
    • 3
  1. 1.Faculty of Automatic Control and Computer Engineering“Gheorghe Asachi” Technical University of IasiRomania
  2. 2.Institute of Pathophysiology and Allergy ResearchMedical UniversityViennaAustria
  3. 3.Pattern Recognition and Image Processing Group, Institute of Computer Graphics and AlgorithmsVienna University of TechnologyAustria

Personalised recommendations