A HYBRID SEGMENTATION FRAMEWORK USING LEVEL SET METHOD FOR CONFOCAL MICROSCOPY IMAGES

Quan Xue, Severine Degrelle, Juhui Wang, Isabelle Hue, Michel Guillomot

Abstract

Based on variational and level set approaches, we present a hybrid framework with quality control for confocal microscopy image segmentation. First, nuclei are modelled as blobs with additive noise and a filter derived from the Laplacian of a Gaussian kernel is applied for blob detection. Second, nuclei segmentation is reformulated as a front propagation problem and the energy minimization is obtained near the boundaries of the nuclei with the Fast-Marching algorithm. For each blob, multiple locally optimized points are selected as the initial condition of the front propagation to avoid image under-segmentation. In order to achieve higher accuracy, a graphical interface is provided for users to manually correct the errors. Finally, the estimated nuclei centres are used to mesh the image with a Voronoi network. Each mesh is considered as a Geodesic Active Contour and evolves to fit the boundaries of the nuclei. Additional post-processing tools are provided to eliminate potential residual errors. The method is tested on confocal microscopy images obtained during trophoblast elongation in ruminants. Experimental results show that cell nuclei can be segmented with controlled accuracy and difficulties such as inhomogeneous background or cell coalescence can be overcome.

References

  1. Byun. J.Y., Verardo. M.R., Sumengen. B., Lewis. G.P., Manjunath. B.S., Fisher. S.K., 2006. Automated tool for the detection of cell nuclei in digital microscopic images: Application to retinal images. Molecular Vision, pp.949-960. August 2006.
  2. Chang. H., Park. C., Parvin. B., 2007. Quantitative representation of three-dimensinal cell culture models. In ISBI'07, IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp.536- 539. April 12-15, 2007. Washington DC, USA.
  3. Dirk. P., Jens. R, Nick. T., Badrinath. R., 2006. SpatioTemporal Cell Cycle Phase Analysis Using Level Sets and Fast Marching Methods. In MIAAB'06, 1st international workshop on Microscopic Image Analysis with Applications in Biology. On 5th of October 2006. Copenhagen, Denmark, USA.
  4. Long. F.L., Peng. H.C., Myers, E., 2007. Automatic segmentation of nuclei in 3D microscopy images of c.elegans. In ISBI'07, IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp.536-539. April 12-15, 2007. Washington DC, USA.
  5. Pitas. I., 2000. Digital image processing algorithms and applications. Wiley-Interscience publication. New York, 1st edition
  6. Sethian, J.A., 1996. Level set methods and fast marching methods. CAMBRIDE UNIVERSITY Press.
  7. Solorzano. C.O., Malladi. R., Lelievre.S.A., Lockett. S.J., 2001. Segmentation of nuclei and cells using membrane related protein markers. Journal of Microscopy, Vol.201, Pt 3, pp.404-415, March 2001.
  8. Thomas, J.G., Graham, W., 2007. WatershedCounting3D: A new method of segmenting and counting punctuate structures from confocal image data. Blackwell Synergy - Traffic, Volume 8 Issue 4 pp. 339-346, April 2007.
  9. Vicent. C., Ron. K, Guillermo. S., 1997. Geodesic Active Contours. International Journal of Computer Vision, Vol.22 (1), pp.61-79, 1997.
  10. Wahlby. C., Sintorn. I.M., Erlandsson. F., Borgefors. G., Bengtson. E., 2004. Combining intensity, edge, and shape information for 2D and 3D segmentation of cell nuclei in tissue sections. Journal of Microscopy, Vol.215, Pt 1, pp.67-76, July 2004.
  11. Wu. H.S., Xu. R., Harpaz. N., Burstein. D., Gil. J., 2005. Segmentation of intestinal gland images with iterative region growing. Journal of Microscopy, Vol.220, Pt 3, pp.190-204, December 2005.
Download


Paper Citation


in Harvard Style

Xue Q., Degrelle S., Wang J., Hue I. and Guillomot M. (2008). A HYBRID SEGMENTATION FRAMEWORK USING LEVEL SET METHOD FOR CONFOCAL MICROSCOPY IMAGES . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 277-282. DOI: 10.5220/0001065602770282


in Bibtex Style

@conference{biosignals08,
author={Quan Xue and Severine Degrelle and Juhui Wang and Isabelle Hue and Michel Guillomot},
title={A HYBRID SEGMENTATION FRAMEWORK USING LEVEL SET METHOD FOR CONFOCAL MICROSCOPY IMAGES},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={277-282},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001065602770282},
isbn={978-989-8111-18-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)
TI - A HYBRID SEGMENTATION FRAMEWORK USING LEVEL SET METHOD FOR CONFOCAL MICROSCOPY IMAGES
SN - 978-989-8111-18-0
AU - Xue Q.
AU - Degrelle S.
AU - Wang J.
AU - Hue I.
AU - Guillomot M.
PY - 2008
SP - 277
EP - 282
DO - 10.5220/0001065602770282