Brain MRI segmentation using KFCM and Chan-Vese model

Abstract

To extract region of interests (ROI) in brain magnetic resonance imaging (MRI) with more than two objects and improve the segmentation accuracy, a hybrid model of a kernel-based fuzzy c-means(KFCM) clustering algorithm and Chan-Vese (CV) model for brain MRI segmentation is proposed. The approach consists of two successive stages. Firstly, the KFCM is used to make a coarse segmentation, which achieves the automatic selection of initial contour. Then an improved CV model is utilized to subdivide the image. Fuzzy membership degree from KFCM clustering is incorporated into the fidelity term of the 2-phase piecewise constant CV model to obtain accurate multi-object segmentation. Experimental results show that the proposed model has advantages both in accuracy and in robustness to noise in comparison with fuzzy c-means (FCM) clustering, KFCM, and the hybrid model of FCM and CV on brain MRI segmentation.

Keywords

brain magnetic resonance imaging / image segmentation / kernel-based fuzzy c-means clustering / Chan-Vese model

References

[1] Yu Jian. General c-means clustering model [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1197-1211.

[2] Xu R., Wunsch D. II Survey of clustering algorithms [J]. IEEE Trans on Neural Networks, 2005, 16(3): 645-678.

[3] Mumford D., Shah J. Optimal approximation by piecewise smooth functions and associated variational problems [J]. Communications on Pure and Applied Mathematics, 1989, 42(5): 577-685.

[4] Chan T. F., Vese L. A. Active contours without edges [J]. IEEE Trans on Image Processing, 2001, 10(2): 266-277.

[5] Tu S., Zhang S., Chen Y., et al. Automatic tracing and segmentation of rat mammary fat pads in MRI image sequences based on cartoon-texture model [J]. Transactions of Tianjin University, 2009, 15(3): 229-235.

[6] Junmo K., John F. W., Anthony Y., et al. A nonparametric statistical method for image segmentation using information theory and curve evolution [J]. IEEE Trans on Image Processing, 2005, 14(10): 1486-1502.

[7] Precioso F., Barlaud M., Blu T., et al. Robust real-time segmentation of images and videos using a smoothing-spline snake-based algorithm [J]. IEEE Trans on Image Processing, 2005, 14(7): 910-924.

[8] Clark M. C., Hall L. O., Goldgof D. B., et al. MRI segmentation using fuzzy clustering techniques [J]. IEEE Engineering in Medicine and Biology, 1994, 13(5): 730-742.

[9] Zhang D Q, Chen S C. Kernel-based fuzzy and possibilistic c-means clustering [C]. In: International Conference on Artificial Neural Network. Istanbul, Turkey, 2003. 122–125.

[10] Zhang D Q, Chen S C, Pan Z S et al. Kernel-based fuzzy clustering incorporating spatial constraints for image segmentation[C]. In: Proceedings of the Second International Conference on Machine Learning and Cybernetics. Xi’an, China, 2003. 2189–2192.

[11] Vese L. A., Chan T. F. A multiphase level set framework for image segmentation using the Mumford and Shah model [J]. International Journal of Computer Vision, 2002, 50(3): 271-293.

[12] Ray N, Acton S T. Image segmentation by curve evolution with clustering [C]. In: Proceedings of 34th Asilomar Conference on Signals, Systems, and Computers. Pacific Grove, CA, USA, 2000. 495–498.

[13] Yang Feng, Sun Xiaohuan, Chen Guoyue et al. An improved hybrid model for medical image segmentation [C]. In: Proceedings of 11th IEEE Singapore International Conference on Communication Systems. Singapore, 2008. 367–370.

[14] Center for Morphometric Analysis. Internet Brain Segmentation Repository [EB/OL]. http://www. cma. mgh. harvard.edu/ibsr/, 2010-08-04.