计算机应用 ›› 2013, Vol. 33 ›› Issue (07): 2014-2017.DOI: 10.11772/j.issn.1001-9081.2013.07.2014

• 多媒体技术 • 上一篇    下一篇

基于混合水平集的脑组织自动提取方法

敖谦1,朱燕平2,江少锋2   

  1. 1. 上饶师范学院 计算机网络中心,江西 上饶 334001
    2. 南昌航空大学 测试与光电工程学院,南昌 330063
  • 收稿日期:2013-01-14 修回日期:2013-02-16 出版日期:2013-07-01 发布日期:2013-07-06
  • 通讯作者: 敖谦
  • 作者简介:敖谦(1975-),男,江西高安人,讲师,硕士,主要研究方向:图像处理、网络信息系统;朱燕平(1986-),男,江西吉安人,硕士,主要研究方向:医学图像处理;江少锋(1978-),男,江西贵溪人,副教授,博士,主要研究方向:医学图像处理。
  • 基金资助:

    国家自然科学基金资助项目(61162023);江西省自然科学基金资助项目(20114BAB211023)

Automatic brain extraction method based on hybrid level set model

AO Qian1,ZHU Yanping2,JIANG Shaofeng2   

  1. 1. Computer Network Center, Shangrao Normal University, Shangrao Jiangxi 334001, China
    2. School of Measuring and Optical Engineering, Nanchang Hangkong University, Nanchang Jiangxi 330063, China
  • Received:2013-01-14 Revised:2013-02-16 Online:2013-07-06 Published:2013-07-01
  • Contact: AO Qian
  • Supported by:

    ;Natural Science Foundation of Jiangxi Province of China

摘要: 脑组织自动提取是脑功能分析中一个重要的预处理步骤,为提高脑组织提取的精度,提出了一种新的提取方法。该方法首先对磁共振成像(MRI)图像使用改进脑组织提取工具(BET)算法快速提取初始轮廓;其次对此初始轮廓进行数学形态学膨胀处理,得到初始感兴趣区域;然后在初始感兴趣区域中使用改进混合轮廓模型进行处理,得到新的轮廓线再进行膨胀处理得到新的区域,如此不断迭代;最后,该混合模型收敛,获得较精确脑组织轮廓。实验采用了7组来自IBSR网站的MRI数据序列,所提算法得到的平均错误划分比例为7.89%。实验结果表明所提方法对于脑组织提取精度的提高是有效和可行的。

关键词: 脑组织提取, 混合水平集, 脑组织提取工具

Abstract: Automatic extraction of brain is an important step in the preprocessing of brain internal analysis. To improve the extraction result, a modified Brain Extraction Tool (BET) and hybrid level set model based method for automatic brain extraction was proposed. The first step of the proposed method was obtaining rough brain boundary with the improved BET algorithm. Then the morphological expansion was operated on the rough brain boundary to initialize the Region of Interest (ROI) where the hybrid active contour model was defined to obtain a new contour. The ROI and the new contour were iteratively replaced until the accurate brain boundary was achieved. Seven Magnetic Resonance Imaging (MRI) volumes from Internet Brain Segmentation Repository (IBSR) website were used in the experiment. The proposed method achieved low average total misclassification ratio of 7.89%. The experimental results show the proposed method is effective and feasible.

Key words: brain extraction, hybrid level set, Brain Extraction Tool (BET)

中图分类号: