Splitting touching cells based on concave-point and improved watershed algorithms

Abstract

Splitting touching cells is important for medical image processing and analysis system. In this paper, a novel strategy is proposed to separate ellipse-like or circle-like touching cells in which different algorithms are used according to the concave-point cases of touching domains. In the strategy, a concave-point extraction and contour segmentation methods for cells in series and in parallel are used for the images with distinct concave points, and an improved watershed algorithm with multi-scale gradient and distance transformation is adopted for the images with un-distinct or complex concave points. In order to visualize each whole cell, ellipse fitting is used to process the segments. Experimental results show that, for the cell images with distinct concave points, both of the two algorithms can achieve good separating results, but the concave-point based algorithm is more efficient. However, for the cell images with unobvious or complex concave points, the improved watershed based algorithm can give satisfying segmenting results.

Keywords

touching cells splitting / concave points / watershed / ellipse fitting

References

[1] Shirin N I, Atefeh M, Ali M N. A new approach for touching cells segmentation. In: Proceedings of the 2008 International Conference on Biomedical Engineering and Informatics. 2008, 816-820

[2] Mussio P, Pietrogrande M, Bottoni P. Automatic cell counter in digital images of liver tissue sections. In: Proceedings of the 4th IEEE Symposium on Computer-Based Medical Systems. 1991, 153-160

[3] Ali S, Abdullah Z, Rosalina A. Combining boundary and skeleton information for convex and concave points detection. In: Proceedings of the 7th International Conference on Computer Graphics, Imaging and Visualization. 2010, 113-117

[4] Wang W, Song H. Cell cluster image segmentation on form analysis. In: Proceedings of the 3rd International Conference on Natural Computation. 2007, 833-836

[5] Bai X, Sun C, Zhou F. Touching cells splitting by using concave points and ellipse fitting. In: Proceedings of the 2008 Digital Image Computing: Techniques and Applications. 2008, 271-278

[6] Grau V, Mewes A, Alcaniz M, Kikinis R. Improved watershed transform for medical image segmentation using prior information. IEEE Transactions on Medical Imaging, 2004, 23(4): 447-458

[7] Zhang X J, Sun W R, Zhong Z H. A new algorithm for watershed segmentation of cells in marrow. In: Proceedings of the 27th Annual International Conference of the Engineering in Medicine and Biology Society. 2005, 6456-6459

[8] Liu Y, Zhao Q. An improved watershed algorithm based on multi-scale gradient and distance transformation. In: Proceedings of the 3rd International Congress on Image and Signal Processing. 2010, 8: 3750-3754

[9] Jumaat A K, Rahman W, Ibrahim A, Mahmud R. Comparison of balloon snakes and GVF snakes in segmenting masses from breast ultrasound images. In: Proceedings of the 2nd International Conference on Computer Research and Development. 2010, 505-509

[10] Du X, Bui T. A new model for image segmentation. IEEE Signal Process Letters, 2008, 15: 182-185

[11] Zhang Q, Min L, Zhang J, Zhang M. Automatic liver segmentation scheme forMRI images based on cellular neural networks. China Communications, 2012, 9(9): 89-95

[12] Wu H S, Barba J, Gil J. A parametric fitting algorithm for segmentation of cell images. IEEE Transations on Biomedical Engineering, 1998, 45(3): 400-407

[13] Kharma N, Moghnieh H, Yao J, Guo Y. Automatic segmentation of cells from microscopic imagery using ellipse detection. IET Image Processing, 2007, 1(1): 39-47

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg