计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (2): 176-178.DOI: 10.3778/j.issn.1002-8331.2009.02.051

• 图形、图像、模式识别 • 上一篇    下一篇

多发性硬化症MR图像分割新算法研究

余学飞,李 彬,陈武凡   

  1. 南方医科大学 生物医学工程学院,广州 510515
  • 收稿日期:2008-07-03 修回日期:2008-08-21 出版日期:2009-01-11 发布日期:2009-01-11
  • 通讯作者: 余学飞

Novel segmentation algorithm for multiple sclerosis lesions in MR images

YU Xue-fei,LI Bin,CHEN Wu-fan   

  1. School of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China
  • Received:2008-07-03 Revised:2008-08-21 Online:2009-01-11 Published:2009-01-11
  • Contact: YU Xue-fei

摘要: 提出了一种针对多发性硬化症病灶T2加权脑部磁共振(MR)图像的分割算法。根据多发性硬化症病灶和脑脊液在T2加权像上同表现为高亮度信号的特点,把模糊C均值分割算法与形态学方法相结合,提出了基于核模糊C均值的多发性硬化症病灶分割算法。该算法首先用改进的核模糊C均值算法做基础分割,再用形态学方法提取出多发性硬化症病灶得到最终分割结果。通过对多发性硬化症模拟脑部MR图像的分割结果表明,算法能够比较准确地分割多发性硬化症病灶。

关键词: 图像分割, 核模糊C均值, 多发性硬化症

Abstract: A novel approach to the segmentation of Multiple Sclerosis(MS) lesions in T2-weighted Magnetic Resonance(MR) images is presented.According to the characteristic of MS lesions show the same high brightness with CerebroSpinal Fluid(CSF) in T2-weighted images,combining the strengths of the kernel fuzzy C-means algorithm and morphology characteristics of MS lesion tissues,the segmentation of MS lesions based on kernel fuzzy C-means algorithm is presented.The modified kernel fuzzy C-means algorithm is used to basic segmentation.Then the MS lesions are extracted by morphological method.The MS segmentation in simulated T2-weighted MR images show that the proposed algorithm can provide a powerful segmentation.

Key words: segmentation of image, kernel fuzzy C-means, multiple sclerosis lesions