Annals of Biomedical Engineering

, Volume 37, Issue 12, pp 2646–2655 | Cite as

Detecting Mitoses in Time-Lapse Images of Embryonic Epithelia Using Intensity Analysis

  • Parthipan Siva
  • G. Wayne BrodlandEmail author
  • David Clausi


Although the frequency and orientation of mitoses can significantly affect the mechanics of early embryo development, these data have not been available due to a shortage of suitable automated techniques. Fluorescence imaging, though popular, requires biochemical intervention and is not always possible or desirable. Here, a new technique that takes advantage of a localized intensity change that occurs in bright field images is used to identify mitoses. The algorithm involves mapping a deformable, sub-cellular triangular mesh from one time-lapse image to the next so that corresponding regions can be identified. Triangles in the mesh that undergo darkening of a sufficient degree over a period consistent with mitosis are flagged. Mitoses are assumed to occur along the short axis of elliptical areas fit to suitably sized clusters of flagged triangles. The algorithm is less complex than previous approaches and it has strong discrimination characteristics. When applied to 15 image sets from neurulation-stage axolotl (Ambystoma mexicanum) embryos, it was able to correctly detect 86% of the manually identified mitoses, had less than 5% false positives and produced average angular errors of only 15°. The new algorithm is simpler to implement than those previously available, is substantially more accurate, and provides data that is important for understanding the mechanics of morphogenetic movements.


Mitosis identification Mitosis orientation Embryonic epithelia Morphogenetic movements Axolotl 


  1. 1.
    Benko, R., and G. W. Brodland. Measurement of in vivo stress resultants in neurulation-stage amphibian embryos. Ann. Biomed. Eng. 35:672–681, 2007.CrossRefPubMedGoogle Scholar
  2. 2.
    Bewes, J. M., N. Suchowerska, and D. R. McKenzie. Automated cell colony counting and analysis using the circular Hough image transform algorithm (CHiTA). Phys. Med. Biol. 53:5991–6008, 2008.CrossRefPubMedGoogle Scholar
  3. 3.
    Bollea, A., M. Masseroli, A. Nicotra, P. Beccaglia, S. Sen, E. Erba, and G. Balconi. Automatic quantitation of cell colonies on Petri dishes by computerized image analysis. Cytotechnology 17:185–191, 1995.CrossRefGoogle Scholar
  4. 4.
    Bordzilovskaya, N. P., T. A. Dettlaff, S. T. Duhon, and G. M. Malacinski. Developmental-stage series of the axolotl. In: Developmental Biology of the Axolotl, edited by J. B. Armstrong and G. M. Malacinski. New York: Oxford University Press, 1989.Google Scholar
  5. 5.
    Bottigli, U., M. Carpinelli, P. L. Fiori, B. Golosio, A. Marras, G. L. Masala, and P. Oliva. A new automatic system of cell colony counting. World Acad. Sci. Eng. Tech. 15:159–163, 2006.Google Scholar
  6. 6.
    Brodland, G. W. Do lamellipodia have the mechanical capacity to drive convergent extension? Int. J. Dev. Biol. 50:151–155, 2006.CrossRefPubMedGoogle Scholar
  7. 7.
    Brodland, G. W., D. I. Chen, and J. H. Veldhuis. A cell-based constitutive model for embryonic epithelia and other planar aggregates of biological cells. Int. J. Plast. 22:965–995, 2006.CrossRefGoogle Scholar
  8. 8.
    Brodland, G. W., M. J. Scott, A. F. MacLean, M. Globus, S. Vethamany-Globus, R. Gordon, J. H. Veldhuis, and R. Del Maestro. Morphogenetic movements during axolotl neural tube formation tracked by digital imaging. Dev. Gen. Evol. 205:311–318, 1996.Google Scholar
  9. 9.
    Brodland, G. W., and J. H. Veldhuis. Lamellipodium-driven tissue reshaping: a parametric study. Comput. Methods Biomech. Biomed. Eng. 9:17–23, 2006.CrossRefGoogle Scholar
  10. 10.
    Brodland, G. W., and J. H. Veldhuis. Computer simulations of mitosis and interdependencies between mitosis orientation, cell shape and epithelia reshaping. J. Biomech. 35:673–681, 2002.CrossRefPubMedGoogle Scholar
  11. 11.
    Burnside, M. B., and A. G. Jacobson. Analysis of morphogenetic movements in the neural plate of the newt Taricha Torosa. Dev. Biol. 18:537–552, 1968.CrossRefPubMedGoogle Scholar
  12. 12.
    Chen, X., and G. W. Brodland. Mechanical determinants of epithelium thickness in early-stage embryos. J. Mech. Bhvr. BioMed. Mat. 2:494–501, 2009.CrossRefGoogle Scholar
  13. 13.
    Davis, J., and M. Goadrich. The relationship between precision-recall and ROC curves. In: Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA, pp. 233–240, 2006.Google Scholar
  14. 14.
    Dougherty, E. R., and R. A. Lotufo. Hands-on Morphological Image Processing. SPIE Press, 2003.Google Scholar
  15. 15.
    Fauvel, J., R. Flood, and R. Wilson. Mobius and his Band: Mathematics and Astronomy in Nineteenth-century, Germany. Oxford University Press, 1993.Google Scholar
  16. 16.
    Fua, P., and Y. G. Leclerc. Object-centered surface reconstruction: combining multi-image stereo and shading. Int. J. Comput. Vision 16:35–56, 1995.CrossRefGoogle Scholar
  17. 17.
    Iles, P. J. W., G. W. Brodland, D. A. Clausi, and S. M. Puddister. Estimation of cellular fabric in embryonic epithelia. Comput. Methods Biomech. Biomed. Eng. 10:75–84, 2007.CrossRefGoogle Scholar
  18. 18.
    Jacobson, C. O., and A. Jacobson. Studies on morphogenetic movements during neural tube closure in amphibia. Zoon 1:17–21, 1973.Google Scholar
  19. 19.
    Kate, T., J. A. M. Belien, A. W. M. Smeulders, and J. P. A. Baak. Method for counting mitoses by image processing in feulgen stained breast cancer sections. Cytometry 14:241–250, 1993.CrossRefPubMedGoogle Scholar
  20. 20.
    Mahadevan, S., and D. P. Casasent. Detection of triple junction parameters in microscope images. In: Proceedings of the Photo-Optical Instrumentation Engineers (SPIE) 2001.4387, pp. 204–214, 2001.Google Scholar
  21. 21.
    Manning, C. D., P. Raghavan, and H. Schütze. Introduction to Information Retrieval. Cambridge University Press, 2008.Google Scholar
  22. 22.
    Parida, L., D. Geiger, and R. Hummel. Junctions: detection, classification, and reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 20:687–698, 1998.CrossRefGoogle Scholar
  23. 23.
    Phukpattaranont, P., and P. Boonyaphiphat. Color based segmentation of nuclear stained breast cancer cell images. ECTI Trans. Elec. Eng. Electron. Comm. 5:158–164, 2007.Google Scholar
  24. 24.
    Pilet, J., V. Lepetit, and P. Fua. Fast non-rigid surface detection, registration and realistic augmentation. Int. J. Comput. Vision 76:109–122, 2008.CrossRefGoogle Scholar
  25. 25.
    Puddister, S. Estimating Bulk Geometrical Properties of Cellular Structures. Master’s Thesis, University of Waterloo, 2003.Google Scholar
  26. 26.
    Sclaroff, S., and J. Isidoro. Active blobs: region-based, deformable appearance models. Comput. Vis. Image Und. 89:197–225, 2003.CrossRefGoogle Scholar
  27. 27.
    Shimada, T., K. Kato, A. Kamikouchi, and K. Ito. Analysis of the distribution of the brain cells of the fruit fly by an automatic cell counting algorithm. Physica A 350:144–149, 2005.CrossRefGoogle Scholar
  28. 28.
    Singh, A. Optic Flow Computation: A Unified Perspective. IEEE Press, 1990.Google Scholar
  29. 29.
    Siva, P. Quantifying the Frequency and Orientation of Mitoses in Embryonic Epithelia. Master’s Thesis, University of Waterloo, 2007.Google Scholar
  30. 30.
    Siva, P., G. W. Brodland, and D. Clausi. Detection of mitoses in embryonic epithelia using motion field analysis. Comput. Methods Biomech. Biomed. Eng. 12:151–163, 2009.Google Scholar
  31. 31.
    Siva, P., G. W. Brodland, and D. Clausi. Automated detection of mitosis in embryonic tissues. In: Proceedings of the Fourth Canadian Conference on Computer and Robot Vision, Montreal, PQ, May 28–30, 2007, pp. 97–104, 2007.Google Scholar
  32. 32.
    Sluzek, A. A local algorithm for real-time junction detection in contour images. Lect. Notes Comput. Sci. 2124:465–472, 2001.CrossRefGoogle Scholar
  33. 33.
    Talukder, A., and D. Casasent. Multiscale Gabor wavelet fusion for edge detection in microscopy images. SPIE 3391:336–347, 1998.CrossRefGoogle Scholar
  34. 34.
    Tao, H., and T. S. Huang. Connected vibrations: a modal analysis approach for non-rigid motion tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 735–740, 1998.Google Scholar
  35. 35.
    Thrun, S., W. Burgard, and D. Fox. Probabilistic Robotics. The MIT Press, 2005.Google Scholar
  36. 36.
    Veldhuis, J. H., and G. W. Brodland. A deformable block-matching algorithm for tracking epithelial cells. Image Vis. Comp. 17:905–911, 1999.CrossRefGoogle Scholar
  37. 37.
    Veldhuis, J. H., G. W. Brodland, C. J. Wiebe, and G. J. Bootsma. Multiview robotic microscope reveals the in-plane kinematics of amphibian neurulation. Ann. Biomed. Eng. 33:821–828, 2005.CrossRefPubMedGoogle Scholar
  38. 38.
    Vincent, L. M., and B. R. Masters. Morphological image processing and network analysis of cornea endothelial cell images. Image Algebra Morphol. Image Process. III 1769:212–226, 1992.Google Scholar

Copyright information

© Biomedical Engineering Society 2009

Authors and Affiliations

  • Parthipan Siva
    • 1
  • G. Wayne Brodland
    • 2
    • 3
    Email author
  • David Clausi
    • 1
  1. 1.Department of Systems Design EngineeringUniversity of WaterlooWaterlooCanada
  2. 2.Department of Civil and Environmental EngineeringUniversity of WaterlooWaterlooCanada
  3. 3.Department of BiologyUniversity of WaterlooWaterlooCanada

Personalised recommendations