Dynamic Radial Contour Extraction by Splitting Homogeneous Areas

  • Christopher Malon
  • Eric Cosatto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6854)

Abstract

We introduce a dynamic programming based algorithm to extract a radial contour around an input point. Unlike many approaches, it encloses a region using feature homogeneity, without relying on edge maps. The algorithm operates in linear time in the number of pixels to be analyzed. Multiple initializations are unnecessary, and no fixed smoothness/local–optimality tradeoff needs to be tuned. We show that this method is beneficial in extracting nuclei from color micrographs of hematoxylin and eosin stained biopsy slides.

Keywords

Contour extraction dynamic programming histological images segmentation digital pathology 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Montalto, M.C.: Pathology re-imagined: The history of digital radiology and the future of anatomic pathology. Arch. Path. and Lab. Medicine 132(5), 764–765 (2008)Google Scholar
  2. 2.
    Bloom, H.J., Richardson, W.W.: Histological grading and prognosis in breast cancer; a study of 1409 cases of which 359 have been followed for 15 years. Br. J. Cancer. 11, 359–377 (1957)CrossRefGoogle Scholar
  3. 3.
    Nedzved, A., Ablameyko, S., Pitas, I.: Morphological segmentation of histology cell images. In: ICPR, vol. 1, pp. 500–503 (2000)Google Scholar
  4. 4.
    Latson, L., Sebek, B., Powell, K.A.: Automated cell nuclear segmentation in color images of hematoxylin and eosin-stained breast biopsy. Analytical and quantitative cytology and histology / the International Academy of Cytology (and) American Society of Cytology 25(6), 321–331 (2003)Google Scholar
  5. 5.
    Plissiti, M.E., Charchanti, A., Krikoni, O., Fotiadis, D.I.: Automated segmentation of cell nuclei in pap smear images. In: Proc. IEEE International Special Topic Conference on Information Technology in Biomedicine, Greece (2006)Google Scholar
  6. 6.
    Bamford, P., Lovell, B.C.: A methodology for quality control in cell nucleus segmentation. In: Digital Image Computing: Techniques and Applications (1999)Google Scholar
  7. 7.
    Pope, D.L., Parker, D.L., Clayton, P.D., Gustafson, D.E.: Left ventricular border recognition using a dynamic search algorithm. Radiology 155(2), 513–518 (1985)CrossRefGoogle Scholar
  8. 8.
    Parker, D.L., Pryor, T.A.: Analysis of b-scan speckle reduction by resolution limited filtering. Ultrasonic Imaging 4(2), 108–125 (1982)CrossRefGoogle Scholar
  9. 9.
    Sun, C., Pallottino, S.: Circular shortest path in images. Pattern Recognition 36(3), 709–719 (2003)CrossRefGoogle Scholar
  10. 10.
    Appleton, B., Sun, C.: Circular shortest paths by branch and bound. Pattern Recognition 36(11), 2513–2520 (2003)CrossRefGoogle Scholar
  11. 11.
    Adams, R., Bischof, L.: Seeded region growing. IEEE Trans. Pattern Anal. Mach. Intell. 16, 641–647 (1994)CrossRefGoogle Scholar
  12. 12.
    Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)MATHGoogle Scholar
  13. 13.
    Cosatto, E., Miller, M., Graf, H., Meyer, J.: Grading nuclear pleomorphism on histological micrographs. In: 19th International Conference on Pattern Recognition (2008)Google Scholar
  14. 14.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Prentice Hall, Englewood Cliffs (2002)Google Scholar
  15. 15.
    Japanese Research Society for Gastric Cancer. Japanese Classification of Gastric Carcinoma. Kanehara & Co., Ltd. (1995)Google Scholar
  16. 16.
    Malon, C., Marugame, A., Cosatto, E.: Epithelial structure detector (in preparation)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Christopher Malon
    • 1
  • Eric Cosatto
    • 1
  1. 1.NEC Laboratories AmericaUSA

Personalised recommendations