Fully automatic segmentation of white matter hyperintensities in MR images of the elderly
Fully automatic segmentation of white matter hyperintensities in MR images of the elderly
复制标题
DOI：
10.1016/j.neuroimage.2005.06.061
复制
发表时间：
2005-11-15
期刊：
影响因子：
5.7
通讯作者：
Relber, JHC
中科院分区：
文献类型：
--
作者：
Admiraal-Behloul, F;van den Heuvel, DMJ;Relber, JHC
定量图像分析在大型临床试验中的作用正在不断增加。有几种方法可用于执行白色高强度（WMH）体积定量。它们在所涉及的人类互动的数量上各不相同。在本文中，我们描述了一个全自动分割，用于量化WMH在一个大型的老年人临床试验。我们的分割方法结合了3种不同的MR图像的信息：质子密度（PD），T2加权和液体衰减反转恢复（FLAIR）图像：我们的方法使用了一种成熟的人工智能技术（模糊推理系统），不需要大量的计算。在9例接受重新定位扫描的患者中评价了分割的再现性;获得了0.91的类间相关系数（ICC）。在44例患者中测试了图像分辨率差异的影响，扫描6-和3-mm层厚FLAIR图像，我们得到的ICC值为0.99。100例患者的手动划定WMH的分割的准确性进行了评价，获得的ICC为0.98和相似性，指数为0.75。除了该方法显示出与专家描绘的非常高的体积和空间一致性之外，该软件在奔腾4处理器（512 MB拉尼）上对每位患者的要求不超过2分钟（前加载图像以保存结果）。(c)2005年爱思唯尔公司All rights reserved.
The role of quantitative image analysis in large clinical trials is continuously increasing. Several methods are available for performing white matter hyperintensity (WMH) volume quantification. They vary in the amount of the human interaction involved. In this paper, we describe a fully automatic segmentation that was used to quantify WMHs in a large clinical trial on elderly subjects. Our segmentation method combines information front 3 different MR images: proton density (PD), T2-weighted and fluid-attenuated inversion recovery (FLAIR) images: our method uses an established artificial intelligent technique (fuzz'v inference system) and does not require extensive computations. The reproducibility of the segmentation was evaluated in 9 patients who underwent scan-rescan with repositioning; an interclass correlation coefficient (ICC) of 0.91 was obtained. The effect of differences in image resolution was tested in 44 patients, scanned with 6- and 3-mm slice thickness FLAIR images; we obtained an ICC value of 0.99. The accuracy of the segmentation was evaluated on 100 patients for whom manual delineation of WMHs was available; the obtained ICC was 0.98 and the similarity, index was 0.75. Besides the fact that the approach demonstrated very high volumetric and spatial agreement with expert delineation, the software did not require more than 2 min per patient (front loading the images to saving the results) on a Pentium-4 processor (512 MB RANI). (c) 2005 Elsevier Inc. All rights reserved.