基于差分搜索优化最大类间方差的脑组织分割方法

Brain tissue segmentation method based on maximum between-cluster variance optimized by the difference search algorithm

目的研究一种基于差分搜索的最大类间方差法,寻找多阈值对脑部磁共振图像进行有效分割。方法通过BET(brain extraction tool)算法去除原始磁共振图像的非脑组织部分,使用BFC(best-fit with coalescing)算法去除强度不均匀性,使用差分搜索算法对图像进行最大类间方差寻优,找出最优阈值,从而对磁共振图像进行多阈值分割。使用BrainWeb提供的仿真磁共振脑部图像数据对方法进行验证。结果对于不同噪声水平、强度不均匀性条件下的磁共振图像,所提出的基于差分搜索的最大类间方差法的分割效果均优于脑功能磁共振成像软件库(FSL)、统计参数图(SPM)和Brainsuite方法。结论基于差分搜索的最大类间方差法有较好的分割精度与强健性,尤其对脑脊液有很好的分割效果。

Objective To study a maximum between-cluster variance based on differential search algorithm,and to select the multi-threshold for effectively segmentation of brain magnetic resonance images.Methods The brain extraction tool(BET)algorithm was used to remove the non-brain tissue part of the original magnetic resonance image.The best-fit with coalescing(BFC)algorithm was used to remove the intensity non-uniformity.The differential search algorithm was used to optimize the maximum between-cluster variance of the image to find the optimal threshold for multi-threshold segmentation of the magnetic resonance image.The method was validated using simulated magnetic resonance(MR)brain image data provided by BrainWeb.Results For MR images with different noise levels and intensity inhomogeneities,the proposed method was better than FSL,SPM and Brainsuite methods.Conclusions The maximum between-cluster variance based on differential search algorithm has better segmentation accuracy and robustness,especially for cerebrospinal fluid.