A New Method to Segment Multiple Sclerosis Lesions Using Multispectral Magnetic Resonance Images_Journal of Biomedical Engineering

Authors：

XIANGYan ,  HEJianfeng , MALei , XUJiaping

Department of Biomedical Engineering, Kunming University of Science and Technology, Kunming 650051, China;

Corresponding author：

HEJianfeng, Email: jfenghe@hotmail.com

Keywords：

multiple sclerosis; kernel fuzzy c-means clustering; magnetic resonance; segmentation

DOI：

10.7507/1001-5515.20150061

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Magnetic resonance (MR) images can be used to detect lesions in the brains of patients with multiple sclerosis (MS). An automatic method is presented for segmentation of MS lesions using multispectral MR images in this paper. Firstly, a Pd-w image is subtracted from its corresponding T1-w images to get an image in which the cerebral spinal fluid (CSF) is enhanced. Secondly, based on kernel fuzzy c-means clustering (KFCM) algorithm, the enhanced image and the corresponding T2-w image are segmented respectively to extract the CSF region and the CSF-MS lesions combinatoin region. A raw MS lesions image is obtained by subtracting the CSF region from CSF-MS region. Thirdly, based on applying median filter and thresholding to the raw image, the MS lesions were detected finally. Results were tested on BrainWeb images and evaluated with Dice similarity coefficient (DSC), sensitivity (Sens), specificity (Spec) and accuracy (Acc). The testing results were satisfactory.

Citation： XIANGYan, HEJianfeng, MALei, XUJiaping. A New Method to Segment Multiple Sclerosis Lesions Using Multispectral Magnetic Resonance Images. Journal of Biomedical Engineering, 2015, 32(2): 330-335. doi: 10.7507/1001-5515.20150061 Copy

1.	GARCÍA-LORENZO D, FRANCIS S, NARAYANAN S A, et al. Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging[J]. Med Image Anal, 2013, 17(1):1-18.
2.	LLADÓ X, OLIVER A, CABEZAS M, et al. Segmentation of multiple sclerosis lesions in brain MRI:A review of automated approaches[J]. Inf Sci (Ny), 2012, 186(1):164-185.
3.	ZHANG Daoqiang, CHEN Songcan. Clustering incomplete data using kernel-based fuzzy c-means algorithm[J]. Neural Processing Letters, 2003, 18(3):155-162.
4.	ZHANG Daoqiang, CHEN Songcan. A novel kernelized fuzzy C-means algorithm with application in medical image segmentation[J]. Artif Intell Med, 2004, 32(1):37-50.
5.	GRAVES D, PEDRYCZ W. Performance of kernel-based fuzzy clustering[J]. Electron Lett, 2007, 43(25):1445-1446.
6.	罗述谦, 周果宏.医学图像处理与分析[M].第2版.北京:科学出版社, 2010:214-215.
7.	BOUDRAA A O, DEHAK S M R, ZHU Yuemin, et al. Automated segmentation of multiple sclerosis lesions in multispectral MR imaging using fuzzy clustering[J]. Comput Biol Med, 2000, 30(1):23-40.
8.	HE R, DATTA S, SAJJA B R, et al. Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images[J]. Comput Med Imaging Graph, 2008, 32(5):353-366.
9.	DICE L R. Measures of the amount of ecologic association between species[J]. Ecology, 1945, 26(3):297-302.
10.	COLLINS D L, ZIJDENBOS A P, KOLLOKIAN V, et al. Design and construction of a realistic digital brain phantom[J]. IEEE Trans Med Imaging, 1998, 17(3):463-468.
11.	SHIEE N, BAZIN P L, OZTURK A, et al. A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions[J]. Neuroimage, 2010, 49(2):1524-1535.
12.	ACHIRON A, GICQUEL S, MIRON S, et al. Brain MRI lesion load quantification in multiple sclerosis:A comparison between automated multispectral and semi-automated thresholding computer-assisted techniques[J]. Magn Reson Imaging, 2002, 20(10):713-720.
13.	余学飞, 李彬, 陈武凡.多发性硬化症MR图像分割新算法研究[J].计算机工程与应用, 2009, 45(2):176-178.
14.	李彬, 陈武凡.基于马尔可夫场的多发性硬化症MR图像分割算法[J].生物医学工程学杂志, 2009, 26(4):861-865.
15.	相艳, 贺建峰, 马磊, 等.分割多发性硬化症白质病灶的新方法[J].计算机应用, 2013, 33(6):1737-1738, 1741.

1. GARCÍA-LORENZO D, FRANCIS S, NARAYANAN S A, et al. Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging[J]. Med Image Anal, 2013, 17(1):1-18.
2. LLADÓ X, OLIVER A, CABEZAS M, et al. Segmentation of multiple sclerosis lesions in brain MRI:A review of automated approaches[J]. Inf Sci (Ny), 2012, 186(1):164-185.
3. ZHANG Daoqiang, CHEN Songcan. Clustering incomplete data using kernel-based fuzzy c-means algorithm[J]. Neural Processing Letters, 2003, 18(3):155-162.
4. ZHANG Daoqiang, CHEN Songcan. A novel kernelized fuzzy C-means algorithm with application in medical image segmentation[J]. Artif Intell Med, 2004, 32(1):37-50.
5. GRAVES D, PEDRYCZ W. Performance of kernel-based fuzzy clustering[J]. Electron Lett, 2007, 43(25):1445-1446.
6. 罗述谦, 周果宏.医学图像处理与分析[M].第2版.北京:科学出版社, 2010:214-215.
7. BOUDRAA A O, DEHAK S M R, ZHU Yuemin, et al. Automated segmentation of multiple sclerosis lesions in multispectral MR imaging using fuzzy clustering[J]. Comput Biol Med, 2000, 30(1):23-40.
8. HE R, DATTA S, SAJJA B R, et al. Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images[J]. Comput Med Imaging Graph, 2008, 32(5):353-366.
9. DICE L R. Measures of the amount of ecologic association between species[J]. Ecology, 1945, 26(3):297-302.
10. COLLINS D L, ZIJDENBOS A P, KOLLOKIAN V, et al. Design and construction of a realistic digital brain phantom[J]. IEEE Trans Med Imaging, 1998, 17(3):463-468.
11. SHIEE N, BAZIN P L, OZTURK A, et al. A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions[J]. Neuroimage, 2010, 49(2):1524-1535.
12. ACHIRON A, GICQUEL S, MIRON S, et al. Brain MRI lesion load quantification in multiple sclerosis:A comparison between automated multispectral and semi-automated thresholding computer-assisted techniques[J]. Magn Reson Imaging, 2002, 20(10):713-720.
13. 余学飞, 李彬, 陈武凡.多发性硬化症MR图像分割新算法研究[J].计算机工程与应用, 2009, 45(2):176-178.
14. 李彬, 陈武凡.基于马尔可夫场的多发性硬化症MR图像分割算法[J].生物医学工程学杂志, 2009, 26(4):861-865.
15. 相艳, 贺建峰, 马磊, 等.分割多发性硬化症白质病灶的新方法[J].计算机应用, 2013, 33(6):1737-1738, 1741.

Journal of Biomedical Engineering

A New Method to Segment Multiple Sclerosis Lesions Using Multispectral Magnetic Resonance Images

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content