Probabilistic segmentation of brain tissue in MR imaging
Probabilistic segmentation of brain tissue in MR imaging
复制标题
DOI：
10.1016/j.neuroimage.2005.05.046
复制
发表时间：
2005-10-01
期刊：
影响因子：
5.7
通讯作者：
van der Grond, J
中科院分区：
文献类型：
--
作者：
Anbeek, P;Vincken, KL;van der Grond, J
提出了一种新的脑磁共振成像中脑白质、灰质、无脑室脑脊液、脑室和脑白质病变五种不同类型脑结构的概率分割方法。该算法基于t1加权（T1-w）、反演恢复（IR）、质子密度加权（PD）、t2加权（T2-w）和流体衰减反演恢复（FLAIR）扫描的信息。它使用k近邻分类技术，从空间信息和体素强度构建特征空间。该技术为每种组织类型生成一个图像，表示每个体素是其一部分的概率。通过对这些概率图应用阈值，可以得到二值分割。计算了相似性指数（SI）和概率指数（PSI），对结果进行定量评价。通过交替剔除五种扫描类型中的一种，研究了每种图像类型对性能的影响。该程序表明，T1-w， PD或T2-w的合并并没有显著改善分割结果。进一步的研究表明，结合IR和FLAIR对5种脑组织类型的分割是最理想的。对金标准的评价表明，所有组织的si值都超过0.8，所有psi值都超过0.7，这意味着极好的一致性。(C) 2005爱思唯尔公司版权所有。
A new method has been developed for probabilistic segmentation of five different types of brain structures: white matter, gray matter, cerebro-spinal fluid without ventricles, ventricles and white matter lesion in cranial MR imaging. The algorithm is based on information from T1-weighted (T1-w), inversion recovery (IR), proton density-weighted (PD), T2-weighted (T2-w) and fluid attenuation inversion recovery (FLAIR) scans. it uses the K-Nearest Neighbor classification technique that builds a feature space from spatial information and voxel intensities. The technique generates for each tissue type an image representing the probability per voxel being part of it. By application of thresholds on these probability maps, binary segmentations can be obtained. A similarity index (SI) and a probabilistic SI (PSI) were calculated for quantitative evaluation of the results. The influence of each image type on the performance was investigated by alternately leaving out one of the five scan types. This procedure showed that the incorporation of the T1-w, PD or T2-w did not significantly improve the segmentation results. Further investigation indicated that the combination of IR and FLAIR was optimal for segmentation of the five brain tissue types. Evaluation with respect to the gold standard showed that the SI-values for all tissues exceeded 0.8 and all PSI-values exceeded 0.7, implying an excellent agreement. (C) 2005 Elsevier Inc. All rights reserved.