一种基于最短路径思想的交互式MR图像壳核分割方法
Shortest Path Based Interactive Segmentation Method of Putamen
为了能够准确稳定的分割脑部磁共振(Magnetic Resonance, MR)图像内边缘模糊的壳核结构,提出了一种基于最短路径思想的交互式壳核分割方法。该方法结合壳核解剖学特点,使用分区域、分方向的代价函数和约束搜索路径等策略,有效地识别壳核外侧模糊边缘,克服了Live-Wire算法查找边缘时容易被屏状核边缘吸引的问题。大量实验表明该方法能够实现对脑磁共振图像中边缘模糊的壳核结构快速、准确且稳定的分割。
o accurately segment putamen with weak edge of basal ganglia region in brain MR images, a shortest path based interactive segmentation method is proposed in this paper. Considering anatomical features of putamen, the cost function of the method uses weight coefficients in sub regions and orientations, and the shortest path search region is restrained, so that the weak edge of putamen can be identified effectively which solved the problem of Live-wire in detecting edge of putamen. Great deals of experiments demonstrate that proposed method can realize fast segment with accuracy and robustness for putamen.
杨佩、仲伟冲、董恩清、孙文燕、李贞国
计算技术、计算机技术自动化技术、自动化技术设备射流技术
图像分割基底节区壳核分割Live-Wire算法
image segmentationbasal ganglia regionputamen segmentationLive-Wire algorithm
杨佩,仲伟冲,董恩清,孙文燕,李贞国.一种基于最短路径思想的交互式MR图像壳核分割方法[EB/OL].(2014-05-30)[2025-08-11].http://www.paper.edu.cn/releasepaper/content/201405-542.点此复制
评论