南方医科大学学报 ›› 2015, Vol. 35 ›› Issue (08): 1143-.

• • 上一篇    下一篇

基于多权重概率图谱的脑部图像分割

张雷,张明慧,卢振泰,冯前进,陈武凡   

  • 出版日期:2015-08-20 发布日期:2015-08-20

Brain image segmentation based on multi-weighted probabilistic atlas

  • Online:2015-08-20 Published:2015-08-20

摘要: 目的探讨有效地利用图谱的先验信息和待分割图像的灰度与结构信息,得到光滑、准确的分割结果的脑部图像分割方
法。方法利用配准的局部相似性测度、标号图像的距离场、待分割图像的自相似性计算多权重概率图谱,然后对多权重概率图
谱进行阈值处理得到最终的分割结果。通过配准的相似性测度加权,保证概率图谱计算的准确性;利用标号图像的距离场加
权,引入图谱标号图像提供的位置先验信息;经过待分割图像的自相似性加权,引入了待分割图像提供的灰度与结构信息。结
果对大量脑部MR图像中的海马进行分割实验,并与国际上主流的分割算法进行了比较,对左海马的分割精度提高到87%,对
右海马的分割精度提高到87.5%。结论基于多权重概率图谱的脑部图像分割能有效的提高分割精度。

Abstract: We propose a multi-weighted probabilistic atlas to obtain accurate, robust, and reliable segmentation. The local
similarity measure is used as the weight to compute the probabilistic atlas, and the distance field is used as the weight to
incorporate the locality information of the atlas; the self-similarity is used as the weight to incorporate the local information of
target image to refine the probabilistic atlas. Experimental results with brain MRI images showed that the proposed algorithm
outperforms the common brain image segmentation methods and achieved a median Dice coefficient of 87.1% on the left
hippocampus and 87.6% on the right.