Automatic Segmentation of Cell Images by Improved Graph Cut-Based Approach

Abstract:

Cell segmentation provides an opportunity to reveal object of interest from the background of an image. In the traditional graph cut segmentation approach, the user initiates the segmentation process by selecting pixels for foreground and background. However, one of the problems of traditional graph cut is that it is time consuming, especially on a large dataset. Thus, we propose a fully automatic technique for cell segmentation on graph cut to automate the selection of sample foreground and background pixels. In order to achieve this, a combination of two methods namely Otsu thresholding and kmeans clustering algorithm is explored. The Otsu thresholding and the k-means provides an initial cell segmentation, creating a platform to automatically select sample foreground and background pixels initiating the graph cut segmentation. Experimental results on two public datasets suggest promising results.

• Periodical: Journal of Biomimetics, Biomaterials and Biomedical Engineering (Volume 29)
• Pages: 74-80
• DOI: https://doi.org/10.4028/www.scientific.net/JBBBE.29.74
• Online since: October 2016
• Authors: Kazeem Oyeyemi Oyebode*, Jules Raymond Tapamo
• Keywords: Automatic Graph Cut Segmentation, Cell Segmentation, Energy Function, Graph Cut, k-Mean Clustering

References

[1] Boykov, Y., Jolly, M.: Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images. In: 8th International Conference on Computer Vision, Vancouer, pp.105-112. Vancouer (2001).

DOI: 10.1109/iccv.2001.937505

[2] Zhang, L., Kong, H., Chin C.T., Wang, T., Chen, S.: Cytoplasm segmentation on cervical cell images using graph cut-based approach. Biomed Mater Eng. 24(1), 1125-1131 (2014).

DOI: 10.3233/bme-130912

[3] Lesko, M., Kato, Z., Nagy A., Gombos, I., Torok, Z., Vgh Jr L., Vgh, L.: Live Cell Segmentation in Fluorescence Microscopy via Graph Cut. In: International Conference on Pattern Recognition pp.1485-1488. (2010).

DOI: 10.1109/icpr.2010.367

[4] Veskler, O.: Star shape prior for graph-cut image segmentation. In: 08 Proceedings of the 10th European Conference on Computer Vision pp.454-467. Berlin(2008).

DOI: 10.1007/978-3-540-88690-7_34

[5] Freedman,D., Zhang, T.: Interactive Graph Cut Based Segmentation with shape priors. In: IEEE Conference on Computer Vision and Pattern Recognition. pp.755-762. (2005).

DOI: 10.1109/cvpr.2005.191

[6] Candemir S., Akgul Y. S,.: Adaptive Regularization Parameter for Graph Cut Segmentation. Lecture notes in computer science. 6111, 117-126 (2010).

DOI: 10.1007/978-3-642-13772-3_13

[7] Peng, B., Veksler, O.: Parameter Selection for Graph Cut Based Image Segmentation. In: British Machine Vision Conference. (2008).

DOI: 10.5244/c.22.16

[8] Lin, X., Adiga, U., Olson, K., Guzowski, JF., Barnes, CA., Roysam, B.: A hybrid 3d watershed algorithm incorporating gradient cues and object models for automatic segmentation of nuclei in confocal image stacks. Cytometry Part A. 56(1), 23-26(2003).

DOI: 10.1002/cyto.a.10079

[9] Nielsen, B., Albregtsen, F., Danielsen, H.: Automatic segmentation of cell nuclei in feulgen-stained histological sections of prostate cancer and quantitative evaluation of segmentation results. Cytometry. 81, 588{601 (2012).

DOI: 10.1002/cyto.a.22068

[10] Danek, O., Matula, P., Ortiz-de-Solorzano, C., Munoz-Barrutia A., Maska, M., Kozubek, M.,: Segmentation of Touching Cell Nuclei Using Two Stage Graph Cut Model. Springer-Verlag. 411-419 (2009).

DOI: 10.1007/978-3-642-02230-2_42

[11] Song, Y., Cai, W., Feng, DD., Chen, M.: Cell Nucei Segmentation in Fluorescence Microscopy Images Using Inter- and IntraRegion Discriminative Information. In: IEEE International Conference of EMBS. Japan. (2009).

[12] Coelho, LP, Shari, A., Murphy, RF.: Nuclear segmentationtation in microscope cell images: a hand-segmented dataset and comparison of algorithms. In: IEEE International Symposium on Biomedical Imaging. pp.518-521. Boston(2009).

DOI: 10.1109/isbi.2009.5193098

[13] Chen, C., Wang, W., Ozolek, JA., Rohde, GK.: A exible and robust approach for segmenting cell nuclei from 2D microscopy images using supervised learning and template matching,. Cytometry A. 83(5) pp.495-507 (2013).

DOI: 10.1002/cyto.a.22280

[14] Alilou, A., Kovalev, V., Taimouri, V.: Segmentation of cell nuclei in heterogeneous microscopy images: A reshapable templates approach. Computerized Medical Images and Graphics. 37(7) pp.488-499 (2013).

DOI: 10.1016/j.compmedimag.2013.07.004

[15] Boykov, Y., Jolly, M., Murphy, RF.: Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images,. In: International Conference on Computer Vision. Vancouer(2001).

DOI: 10.1109/iccv.2001.937505

[16] Boykov, Y., Kolmogorov, K.: An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. IEE Transactions on PAMI. pp.1124-1137 (2004).

DOI: 10.1109/tpami.2004.60

[17] Hartigan, J.A., Hartigan, M.A.: A k-means clustering algorithm. Appl Stat. 28 p.100{108 (1979).

[18] Otsu, N.: A threshold selection method from gray-level histograms. IEEE Transaction on systems, man, and cybernetics. 9(1) pp.62-66 (1979).

DOI: 10.1109/tsmc.1979.4310076

[19] Vebjorn L., Katherine L.S., Anne E.C.: Annotated high-throughput microscopy image sets for validation. Nature Methods. 9(637) (2012).

[20] Oyebode K., Tapamo J.: Adaptive Parameter Selection for Graph Cut-Based Seg-mentation on Cell Images. Image Analysis and Stereology. 30(1) (2016).

DOI: 10.5566/ias.1333