Medical image segmentation based on the diffusion equation and MRF model

被引：0

作者：

Li, Yibing ^{[1
]}

Zhu, Yao ^{[1
]}

Ye, Fang ^{[1
]}

机构：

[1] College of Information and communication Engineering, Harbin Engineering University

来源：

Journal of Information and Computational Science | 2014年 / 11卷 / 05期

关键词：

Diffusion equation; Image segmentation; Medical image; MRF model;

D O I：

10.12733/jics20103005

中图分类号：

学科分类号：

摘要：

Due to the impact of noise and imaging equipment, medical image may appear the problems of spots, microgroove and grayscale inhomogeneity, which seriously affect the segmentation effect and bring difficulty to the analysis of pathological. This paper uses algorithm based on the diffusion equation and MRF model to overcome above problems. At first we use improved diffusion equation to smooth the image, the improved diffusion equation uses morphological operators instead of the Gauss convolution term of Lin Shi operator, it can not only preserve the contour but significantly reduce the amount of calculation. Then we use MRF model to segment the processed image. The experiment show that our algorithm has a good ability of anti-noise, and to solve the problems caused by grayscale inhomogeneity of medical image. © 2014 by Binary Information Press.

引用

页码：1471 / 1478

页数：7

共 11 条

[1]

Li A., Li Y., An improved iterative algorithm for cell image segmentation, Natural Science Journal of Heilongjiang University, 27, 6, pp. 811-817, (2010)

[2]

Shang G., Li J., Using the gray level transformation method to improve the quality of medical images, Applied Science, 32, 11, pp. 2005-2008, (2005)

[3]

Liu J., Zhang Y., Xu X., A gray distribution Markov model-based image segmentation, Computer Application, 28, 3, pp. 686-687, (2008)

[4]

Jodoin P.-M., Lalande A., Voisin Y., Bouchot O., Steinmetz E., Markovian method for 2D, 3D and 4D segmentation of MRI, In Proceedings of the 15th IEEE International Conference on Image Processing, pp. 3012-3015, (2008)

[5]

Catte F., Lions P., Morel J., Image selective smoothing and edge detection by nonlinear diffusion, SIAM Journal on Numerical Analysis, 29, pp. 182-193, (1992)

[6]

Lin Z., Shi Q., A de-noising and maintain a realistic anisotropic diffusion equation, Journal of Geographical Sciences, 22, 11, pp. 1133-1137, (1999)

[7]

Jiang S., Feng X., Song G., Anisotropic diffusion equation based on morphological operators, Journal of Xidian University, 33, 1, pp. 121-124, (2006)

[8]

Perona P., Malik J., Scale space and edge detection using anisotropic diffusion, IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 7, pp. 629-639, (1990)

[9]

Liu X., Langer D.L., Haider M.A., Yang Y., Wernick M.N., Prostate cancer segmentation with simultaneous estimation of Markov random field parameters and class, IEEE Transactions on Medical Imaging, 28, 6, pp. 906-915, (2009)

[10]

Luo J., Chen L., Luo G., Structural shape and topology optimization method based on the level set method for semi-implicit scheme Ze continued, Journal of Solid Mechanics, 29, 2, pp. 175-180, (2008)

← 1 2 →