Novel Method of MRI Medical Image Segmentation Combining Watershed Algorithm and WKFCM Algorithm

Abstract:

Aimed at the disadvantage of over-segmentation that traditional watershed algorithm segmented MRI images, a new method of MRI image segmentation was presented. First, through traditional watershed segmentation algorithm, the image was segmented into different areas, and then based on the improved kernel-clustering algorithm, we used Mercer-kernel to map average gray value of each area to high-dimensional feature space, making originally not displayed features manifested. In this way, we can achieve a more accurate clustering, and solve over-segmentation problem of watershed algorithm segmenting MRI images efficiently, thereby get better segmentation result. Experimental results show that the method of this paper can segment brain MRI images satisfactorily, and obtain clearer segmentation images.

• Periodical: Applied Mechanics and Materials (Volumes 121-126)
• Pages: 4518-4522
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.121-126.4518
• Online since: October 2011
• Authors: Jin Qing Liu, Kun Chen
• Keywords: High-Dimensional Feature Space, Mercer-Kernel, MRI Image Segmentation, Watershed Algorithm, WKFCM Algorithm

References

[1] Chen Zhi-bin, Qiu Tian-shuang, SU Ruan: Chinese Journal of Electronics, Vol. 36 (2008), pp.1733-1736, in Chinese.

[2] Konstantin L , Alexei S, Vitali Z: Computers in Biology and Medicine, Vol. 39 (2009), pp.153-160.

[3] Wang Na, Guo Min: Computer Engineering and Applications, Vol. 45 (2009), pp.212-214, in Chinese.

[4] Zhang Li, Zhou Wei-da et al.: Chinese Computers, Vol. 25 (2002), pp.587-590, in Chinese.

[5] Vincent L, Soille P: IEEE Trans on Pattern Anal and Mach intelligence, Vol. 13 (1991), pp.538-598.

[6] Feng Lin, Guan Hui-juan et al.: Journal of Dalian University of Technology, Vol. 46 (2006), pp.851-856, in Chinese.

[7] Xue Geng-jian, Wang Yi, Zhao Hai-tao et al.: Chinese Medical Imaging Technology, Vol. 21 (2005), pp.1609-1611, in Chinese.