CSF Cell Images Segmentation Using a Hybrid Model Based on Watershed and Snake

Abstract:

In this paper, a new image segmentation approach is proposed based on the morphological watershed transform and an improved balloon snake algorithm for reducing the incorrect segmenting rate that caused by uneven dyeing of Cerebrospinal Fluid (CSF) cells. Firstly, a marker-controlled watershed pre-segmentation was applied to resolve the over-segmentation problem of the watershed and eliminate the approximate contour of CSF cells. Secondly, due to the weak boundary of some cytoplasm, we performed a coarse segmentation by using an improved balloon snake to dilate the watershed result. Finally, a fine segmentation was performed to obtain the ultimate cytoplasm contours. The results show that the new method is more accurate and robust to weak boundary.

• Periodical: Applied Mechanics and Materials (Volumes 321-324)
• Pages: 1051-1054
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.321-324.1051
• Online since: June 2013
• Authors: Yin Wei Li*, Wen Ming Huang, Wen Zheng Cai
• Keywords: Active Contour Model, Balloon Snake, Cerebrospinal Fluid, Segmentation, Watershed

References

[1] L.H. Nee, M.Y. Mashor and R. Hassan: J. Med. Im. Heal. Inf. Vol 2 (2012), pp.278-284.

[2] J. Park, J.M. Keller: Pat. Anal. Mach. Intelligence Vol 23 (2001), pp.1201-1205.

[3] M. Kass, W. Andrew and T.Demetri: Int. J. Comput.Vis Vol. 1 (1987), pp.321-331.

[4] S. Beucher, C. Lantuéjoul: Proc. Int. Worksh. Img. Proc, Rennes(1979).

[5] L. Vincent, P. Soille: IEEE Trans. Pat. Anal. Mach. Intelligence Vol 13 (1991), pp.583-598.

[6] S. Jean: Sig. Proc Vol 38 (1994), pp.3-11.

[7] Laurent D.Cohen: CVGIP: Image Understanding Vol 53 (1991), pp.211-218.

[8] Donna J. Williams, S. Mubarak: CVGIP: Image Understanding Vol 55 (1992), pp.14-26.