A New Medical Image Segmentation Method Based on Chan-Vese Model

Abstract:

The traditional segmentation method for medical image segmentation is difficult to achieve the accuracy requirement, and when the edges of the image are blurred, it will occurs incomplete segmentation problem, in order to solve this problem, we propose a medical image segmentation method which based on Chan-Vese model and mathematical morphology. The method integrates Chan-Vese model, mathematical morphology, composite multiphase level sets segmentation algorithm, first, through iterative etching operation to extract the outline of the medical image, and then the medical image is segmented by the Chan-Vese model based on the complex multiphase level sets, finally the medical image image is dilated iteratively by using morphological dilation to restore the image. The experimental results and analysis show that, this method improves the multi-region segmentation accuracy during the segmentation of medical image and solves the problem of incomplete segmentation.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 3750-3756
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.3750
• Online since: February 2014
• Authors: Yuan Zheng Ma*, Jia Xin Chen
• Keywords: Chan-Vese Model, Complex Multiphase Level Sets, Mathematical Morphology, Medical Image Segmentation

References

[1] Fu K S, Mu J S. A survey on segmentation [J]. Pattern Recognition, 1982, 13: 3-16.

[2] Zhang Y J. A survey on evaluation methods for image segmentation [J]. Pattern Recognition, 1996, 29: 1335-1346.

DOI: 10.1016/0031-3203(95)00169-7

[3] Gu Li-xu, Peters T. 3D segmentation of medical images using a fast multistage hybrid algorithm [J]. International Journal of Computer Assisted Radiology and Surgery, 2006, 1(1): 23-31.

DOI: 10.1007/s11548-006-0001-4

[4] Kass M, Witkin A, and Terzopoulos D. Snakes: Active contour models [J]. International Journal of Computer Vision, 1988, 1(4): 321-331.

DOI: 10.1007/bf00133570

[5] Osher S, Sethian J A. Fronts propagating with curvature dependent speed: Algorithms based on Hamilton-jacobi formulations [J]. Journal of Computational Physics, 1988, 79: 12-49.

DOI: 10.1016/0021-9991(88)90002-2

[6] CHAN T, VESE L. Active contours without edges [J]. IEEE Transaction on Image Processing, 2001, 10(2): 266-277.

DOI: 10.1109/83.902291

[7] Chan T, Vese L. A level set algorithm for minimizing the Mumford-Shah functional in image processing[C]/Proceedings of IEEE Workshop on VLSM, 2001: 161-168.

DOI: 10.1109/vlsm.2001.938895

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

[9] Weng Xiaoguang, Zheng Gang. Image segmentation based on Chan-Vese model using complex multiphase level set[J]. Journal of applied Sciences-Electronics and Information Engineering，2009, 27（4）：365-369.

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

DOI: 10.1002/cpa.3160420503

[11] Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(3): 266-280.

DOI: 10.1109/34.841758

[12] HEINEMANN E G. Simultaneous brightness induction as a function of inducing-and test-field luminances [J]. Journal of Experimental Psychology, 1955, 50(2): 89-96.

DOI: 10.1037/h0040919

[13] D Martin; C Fowlkes; D Tal. A Database of Human Segmented Natural and Its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics[A] IEEE 8th International Conference on Computer Vision[C]. Vancouver, Canada, 2001, 416-423.

DOI: 10.1109/iccv.2001.937655