-
针对现有磁共振（MR）图像分割算法大多直接在原图像上进行处理，分割效果受噪声影响较大的问题，本文引入二维集合经验模式分解（BEEMD）算法，提高距离正则化水平集（DRLSE）方法对MR图像的分割精度. 算法中首先使用 BEEMD将待分割MR图像分解为多个二维固有模式函数（BIMF），通过对各BIMF赋予不同加权系数重构待分割图像，从而增强分割目标；然后在DRLSE的边界指示函数中添加部分BIMF分量，恢复因高斯平滑被模糊的目标轮廓，并使用DRLSE方法对重构图像进行分割. 通过对仿真图像和临床MR图像分割验证，表明本文算法具有较高的分割精度和鲁棒性，能有效实现对临床MR图像的分割.
-
关键词:
- 磁共振图像 /
- 距离正则化水平集 /
- 二维集合经验模式分解 /
- 固有模式函数
Original image is directly processed by the existing image segmentation algorithms, which is easily affected by noise. A bi-dimensional ensemble empirical mode decomposition (BEEMD) method is introduced to improve the accuracy of MR image segmentation by distance regularized level set (DRLSE) method. The BEEMD method is the extension of one-dimensional noise assisted data analysis from ensemble empirical mode decomposition (EEMD). The key points of BEEMD are as follows. four-neighborhood optimization is used to find extermum; three-spline interpolation is used to obtain the envelope; amplitude standard of added white noise is restricted; a certain time of integration is used to avoid modality aliasing problem. The main steps of the proposed method are as follows. Firstly, the MR image is decomposed into a number of two-dimensional intrinsic mode functions (BIMF) by BEEMD method; different weighting coefficients are endued to BIMF for image reconstruction to enhance the segmentation target. Secondly, part of BIMF components are added into edge indicator function of DRLSE to recover the blurring boundary caused by Gauss smooth operation. Then DRLSE is used to segment the reconstructed MR image. High accuracy and robustness of proposed algorithm are obtained in both simulations and clinical MR images. However, compared with DRLSE, the proposed method is complex and time consuming because using BEEMD for preprocessing the segmentation image.-
Keywords:
- magnetic resonance image /
- distance regularized level set evolution /
- bi-dimensional ensemble empirical mode decomposition /
- intrinsic mode functions
[1] Seiko K S, Kuroki Y, Nasu K, Nawano S, Moriyama N, Okazaki M 2007 Magn. Reson. Ned. Sci. 6 21
[2] Tang X, Hong L M, Zu D L 2010 Chin. Phys. B 19 078702
[3] Xu Y, Wang W T, Wang W M 2012 Chin. Phys. B 21 118704
[4] Bao S L, Du J, Gao S 2013 Acta Phys. Sin. 62 088701 (in Chinese) [包尚联, 杜江, 高嵩 2013 62 088701]
[5] Fang S, Wu W C, Ying K, Guo H 2013 Acta Phys. Sin. 62 048702 (in Chinese) [方晟, 吴文川, 应葵, 郭华 2013 62 048702]
[6] Osher S, Sethian J 1988 J. Comput. Phys. 79 12
[7] Chan F T, Vese L 2001 IEEE T. Image Process. 10 266
[8] Munford D, Shah J 1989 Commun. Pure. Appl. Math. 42 577
[9] Li C M, Xu C Y, Gui C F, Fox M D 2010 IEEE T. Image Process. 19 3243
[10] Liu J Q, Liu W W 2011 Procedia Engineering 15 2634
[11] W Narkbuakaew, H Nagahashi, K Aoki, Y Kubota 2014 J. Biomed. Eng. 7 994
[12] Nunes J C, Bouaoune Y, Delechelle E, Niang O, Bunel P 2003 Image Vision Comput. 21 1019
[13] Huang N E, Shen Z, Long S R, Wu M C, Shih H H, Zheng Q, Yen NC, Tung C C, Liu H H 1998 Proc. of the Royal Society of London A 454 903
[14] Zheng Y Z, Qin Z 2009 J. Softw. 20 1096 (in Chinese) [郑有志, 覃征 2009 软件学报 20 1096]
[15] Zhang B H, Zhang C T, Wu J S, Liu H 2014 J. Light Electron Opt. 125 146
[16] Wu Z H, Huang N E 2009 Adv. Data Anal. 1 1
[17] Al-Baddai S, Al-Subari K, Tome A M, Volberg G, Hanslmayr S, Hammwohner R, Lang E W 2014 Biomed. Signal Proces. 13 218
[18] Neubauer A, Tome A M, Kodewitz A, Gorriz J M, Puntonet C G, Lang E W 2014 Adv. Data Anal. 06 1450004
[19] Zhou Y, Li H 2011 Opt. Express 19 18207
[20] Zhou Y, Li H 2013 Mech. Syst. Signal Pr. 35 369
[21] Ye X F, Wang L, Wang T 2012 Comput. Eng. Appl. 48 24 (in Chinese) [叶秀芬, 王雷, 王天 2012 计算机工程与应用 48 24]
[22] Shattuck D W, Sandor-Leahy S R, Schaper K A, Rottenberg D A, Leahy R M 2001 Neuroimage 13 856
[23] Laine A, Fan J, Yang W 1995 IEEE Eng. Med. Biol. IEEE Eng. Med. Biol. 14 536
[24] Qu J L, Wang X F, Gao F, Zhou Y P, Zhang X Y 2014 Acta Phys. Sin. 63 110201 (in Chinese) [曲建岭, 王小飞, 高峰, 周玉平, 张翔宇 2014 63 110201]
-
[1] Seiko K S, Kuroki Y, Nasu K, Nawano S, Moriyama N, Okazaki M 2007 Magn. Reson. Ned. Sci. 6 21
[2] Tang X, Hong L M, Zu D L 2010 Chin. Phys. B 19 078702
[3] Xu Y, Wang W T, Wang W M 2012 Chin. Phys. B 21 118704
[4] Bao S L, Du J, Gao S 2013 Acta Phys. Sin. 62 088701 (in Chinese) [包尚联, 杜江, 高嵩 2013 62 088701]
[5] Fang S, Wu W C, Ying K, Guo H 2013 Acta Phys. Sin. 62 048702 (in Chinese) [方晟, 吴文川, 应葵, 郭华 2013 62 048702]
[6] Osher S, Sethian J 1988 J. Comput. Phys. 79 12
[7] Chan F T, Vese L 2001 IEEE T. Image Process. 10 266
[8] Munford D, Shah J 1989 Commun. Pure. Appl. Math. 42 577
[9] Li C M, Xu C Y, Gui C F, Fox M D 2010 IEEE T. Image Process. 19 3243
[10] Liu J Q, Liu W W 2011 Procedia Engineering 15 2634
[11] W Narkbuakaew, H Nagahashi, K Aoki, Y Kubota 2014 J. Biomed. Eng. 7 994
[12] Nunes J C, Bouaoune Y, Delechelle E, Niang O, Bunel P 2003 Image Vision Comput. 21 1019
[13] Huang N E, Shen Z, Long S R, Wu M C, Shih H H, Zheng Q, Yen NC, Tung C C, Liu H H 1998 Proc. of the Royal Society of London A 454 903
[14] Zheng Y Z, Qin Z 2009 J. Softw. 20 1096 (in Chinese) [郑有志, 覃征 2009 软件学报 20 1096]
[15] Zhang B H, Zhang C T, Wu J S, Liu H 2014 J. Light Electron Opt. 125 146
[16] Wu Z H, Huang N E 2009 Adv. Data Anal. 1 1
[17] Al-Baddai S, Al-Subari K, Tome A M, Volberg G, Hanslmayr S, Hammwohner R, Lang E W 2014 Biomed. Signal Proces. 13 218
[18] Neubauer A, Tome A M, Kodewitz A, Gorriz J M, Puntonet C G, Lang E W 2014 Adv. Data Anal. 06 1450004
[19] Zhou Y, Li H 2011 Opt. Express 19 18207
[20] Zhou Y, Li H 2013 Mech. Syst. Signal Pr. 35 369
[21] Ye X F, Wang L, Wang T 2012 Comput. Eng. Appl. 48 24 (in Chinese) [叶秀芬, 王雷, 王天 2012 计算机工程与应用 48 24]
[22] Shattuck D W, Sandor-Leahy S R, Schaper K A, Rottenberg D A, Leahy R M 2001 Neuroimage 13 856
[23] Laine A, Fan J, Yang W 1995 IEEE Eng. Med. Biol. IEEE Eng. Med. Biol. 14 536
[24] Qu J L, Wang X F, Gao F, Zhou Y P, Zhang X Y 2014 Acta Phys. Sin. 63 110201 (in Chinese) [曲建岭, 王小飞, 高峰, 周玉平, 张翔宇 2014 63 110201]
计量
- 文章访问数: 6256
- PDF下载量: 535
- 被引次数: 0
下载:
