| 利用感兴趣区域从脑部MRI中提取脑组织 |
| |
| 引用本文： | 江少锋,万红平,陈震,杨素华. 利用感兴趣区域从脑部MRI中提取脑组织[J]. 中国图象图形学报, 2013, 18(12): 1644-1650 |
| |
| 作者姓名： | 江少锋 万红平 陈震 杨素华 |
| |
| 作者单位： | 南昌航空大学测试与光电工程学院 |
| |
| 基金项目： | 国家自然科学基金项目（面上项目，重点项目，重大项目） |
| |
| 摘 要： | 从脑部MRI图像提取脑组织是影像学分析中的一项重要的预处理过程。本文提出了一种基于感兴趣区域和混合水平集方法的脑组织提取方法。该方法先采用BET方法得到脑组织的感兴趣区域，然后在该感兴趣区域内演化改进的混和水平集得到真实的脑组织边界。改进的混合水平集采用了一个非线性的速度函数，能够有效地防止边界泄露。该方法所用到的MRI数据均来自于互联网（IBSR, Internet Brain Segmentation Repository Web)。利用18组IBSR网站的MRI数据，本方法得到的结果接近于标准手动提取结果，并且在多个评价参数上都取得最好结果。实验表明该方法提取脑组织具有一定的准确性和稳定性。
|
| 关 键 词： | 脑组织提取 混合水平集 感兴趣区域；脑部MRI图像；活动轮廓 |
| 收稿时间： | 2013-04-02 |
| 修稿时间： | 2013-05-17 |
Automatic brain extraction from cerebral MRI volume using region of interest |
| |
| Jiang Shaofeng,Wan Hongping,Chen Zhen and Yang Suhua. Automatic brain extraction from cerebral MRI volume using region of interest[J]. Journal of Image and Graphics, 2013, 18(12): 1644-1650 |
| |
| Authors: | Jiang Shaofeng Wan Hongping Chen Zhen Yang Suhua |
| |
| Affiliation: | Key Laboratory of Nondestructive Testing, Nanchang Hangkong University, Ministry of Education, Nanchang Hangkong University, Nanchang 330063, China;Key Laboratory of Nondestructive Testing, Nanchang Hangkong University, Ministry of Education, Nanchang Hangkong University, Nanchang 330063, China;Key Laboratory of Nondestructive Testing, Nanchang Hangkong University, Ministry of Education, Nanchang Hangkong University, Nanchang 330063, China;Key Laboratory of Nondestructive Testing, Nanchang Hangkong University, Ministry of Education, Nanchang Hangkong University, Nanchang 330063, China |
| |
| Abstract: | Automatic extraction of brain tissue from MRI volume is an important step in the preprocessing of brain analysis. To improve the extraction result, a region of interest based method for automatic brain extraction was proposed. The first step of the proposed method was obtaining the brain region of interest with the BET algorithm. Then a modified hybrid level set model was defined to obtain the true brain boundary. The modified hybrid level set model used a nonlinear speed function which can eliminate the boundary leakage effectively. 18 MRI volumes from IBSR (Internet Brain Segmentation Repository) web were used in the experiment. The results obtained from our method were very similar with the results using manual extraction and almost achieved the best results on IBSR data compared with other method. Experiment shows the proposed method is effective and robust. |
| |
| Keywords: | brain extraction hybrid level set region of interest cerebral MRI active contour |
|
| 点击此处可从《中国图象图形学报》浏览原始摘要信息 |
|
点击此处可从《中国图象图形学报》下载免费的PDF全文 |
|
