北京生物医学工程

MRI大脑图像灰质与白质的分割

Segmentation for brain grey matter and white matter of a MRI brain image

作者：陈亮亮

单位：陈亮亮。E-mail:puppymoon@163.com

分类号：

出版年·卷·期（页码）：2013·32·5（519-523）

摘要：

目的利用小波变换对MRI大脑图像进行多尺度下的自动阈值处理，实现大脑灰质与白质的分割。方法首先将MRI大脑图像去噪，接着进行预分割以去除非脑组织，余下的脑实质部分选择sym4小波函数对其一维直方图信号进行不同层次的小波系数的分解，实现多尺度下的自动阈值分割，从而提取脑实质中的灰质和白质。经过图像的后处理，以错误分割的百分比作为分割结果的评判标准。结果该方法能正确分离白质和灰质，对多幅MRI大脑图像重复实验，计算得到的像素差异百分比不超过3.7%，错误分割的百分比在允许范围内。结论该方法对于MRI大脑的灰白质分割具有一定的有效性，且操作简单、快速，分割效果理想。但由于小波阈值分割法的单一性，分割过程仍有人工干涉，分割结果也存在一定的过分割现象，应在此方法的基础上进一步研究和完善。

Objective To realize the segmentation of brain grey matter and white matter of a MRI brain image accurately by means of wavelet transformation which could automatically gain the threshold with multi-scale decomposition. Methods Firstly，The MRI brain image was denoised and pre-segmented to remove non-brain tissue. Then one-dimensional histogram signal of the rest brain tissue was decomposed by different levels of wavelet coefficients to realize automatically threshold segmentation under multi-scale，thus the brain grey matter and white matter were extracted. Finally，the results were evaluated by the percentage of error segmentation after the post-treatment. Results The expriment results showed that brain grey matter and white matter were correctly segmented，and the max percentage of error segmentation was 3.7%，which was within the allowable range. Conclusions The method is effective，easy and fast in segmentation for brain grey matter and white matter of a MRI image. However，due to the simplicity of the threshold segmentation with wavelet transformation，the whole process does not work without human intervention and there is some over-segmentation in the results. Further study and improvement should be made based on this method.

参考文献：

［1］余学飞.基于模糊理论的医学图像分割算法研究［D］.广州：南方医科大学，2009.
Yu Xuefei.Research about algorithm based on fuzzy theory for medical image segmentation［D］. Guangzhou:Southern Medical University,2009.
［2］Lipton Richard J. DNA Solution of Hard Computational Problems［J］. Science,1995， 268 (4):542-545.
［3］Pemmaraju S，Mitra S，Shieh Y，et al. Multiresolution waveletdecomposition and neur o-fuzzy clustering for segmentation of radiographic images［J］. Proceedings of the Eighth Annual IEEE Symposium on Computer-Based Med-I cal Systems (CBMS. 95). 1995:142-149.
［4］Olivo JC．Automatic threshold selection using the Wavelet transform． CVGIP-GMIP，1994，56(3)：205-218.
［5］邢凡，樊瑜瑾.基于小波变换多阈值彩色铁谱图像的分割方法［J］.润滑与密封，2008,33(7):69-72.
Xing Fan，Fan Yujin. Multi-threshould segmentation method based on wavelet transformation for color ferrography image［J］. Lubrication and Sealing，2008,33(7):69-72.
［6］何军宝.脑部核磁共振图像的模糊均值抗噪分割算法［D］.武汉：华中科技大学，2006.
He Junbao. Fuzzy c-means with entinoise segmentation algorithm for MRI brain image［D］. Wuhan:Huazhong University of Science and Technology,2006.
［7］Rajaqakse JC. Statistical approach to segmentation of single-channel cerebral M R images［J］. IEEE Trans Med Imaging，1997，16 (2):176-186.
［8］王建中.核磁共振脑图像分割方法的研究［D］.长春：东北师范大学,2007.
Wang Jianzhong. Research on methods for segmentation of MRI brain images［D］. Changchun:Northeast Normal University,2007.
［9］聂生东,章鲁,顾顺德,等. 磁共振图像的分割［J］. 国外医学生物医学工程分册,1999,22(6):23-25.
Nie Shengdong，Zhang Lu，Gu Shunde，et al. Segmentation of brain images［J］. Foreign Medical Sciences:Biomedical Engineering，1999，22(6):23-25.
［10］刘静. 基于小波变换的图像分割技术研究［D］. 济南：山东大学,2005.
Liu Jing. Reaseach on teconology for images segmentation based on wavelet transformation［D］. Jinan:Shandong University,2005.
［11］Reddick WE,Glass JO，Cook EN,et al.Automated segmentation and classification of multi spectral magnetic images using artificia neural networks［J］. IEEE Trans Med Imaging,1997,16(6):911-918.
［12］Li Bai， Yihui Liu， Dorothee Auer， Paul Morgan. Automatic Segmentation of Putamen from Brain MRI［J］. Technology & Automation,2001,19(8):679-698.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录