一种半自动分割脑部MRI中胼胝体的方法  

A semi-automatic algorithm for callosum segmentation in head MRI

作　　者：杨金柱[1] 王艳飞[1] 栗伟[1] 耿欢[1] 赵大哲[1] 陈楠[2] 王星[2] 李坤成[2] 

机构地区：[1]东北大学医学影像计算教育部重点实验室,辽宁沈阳110004 [2]首都医科大学宣武医院放射科,北京100053

出　　处：《中国医学影像技术》2010年第9期1632-1635,共4页Chinese Journal of Medical Imaging Technology

基　　金：国家863计划项目(2006AA02z391);国家973计划项目(2005CB522800;2004CB318101);国家自然科学基金(30621004);中国科学院知识创新工程

摘　　要：针对胼胝体的图像特点以及实际应用要求,采用半自动方法对MRI中的胼胝体进行分割。首先采用基于Live-Wire的算法对胼胝体影像的起始层和终止层进行初始分割,然后利用基于距离变换的形状插值算法获取中间层的初始轮廓信息,对插值获得的初始轮廓采用Snake模型进行局部收缩,获得真实的胼胝体边界。对序列MRI脑影像中的胼胝体进行分割、重建、标定。实验结果与临床医师的使用反馈证明,本文提出的算法具有较高的灵活性与可信度,对胼胝体的分割精度与解剖统计信息相符,分割结果可满足临床需求。Based on the features of MR images of callosum and the requirements of practical application, a semi-automatic algorithm for callosum segmentation was proposed in this paper. Firstly, Live-Wire method was adopted to get the initial segment result for the first and last slices. Then the initial contour of middle slices was got using the method of shape interpolation based on distance transform. Using the initial contour as input of Snake model, the real callosum boundary could be found after some times of iteration. The experimental results and the feedbacks of clinical doctor showed that the algorithm has good flexibility and credibility, and the segment results match the Atlas of anatomy and meet the clinical needs.

关 键 词：磁共振成像 胼胝体 SNAKE模型 图像分割 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论] R445.2[自动化与计算机技术—计算机科学与技术]