Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information
Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information
复制标题
DOI：
10.1118/1.2842076
复制
发表时间：
2008-04-01
期刊：
影响因子：
3.8
通讯作者：
Pluim, Josien P. W.
中科院分区：
文献类型：
--
作者：
Klein, Stefan;van der Heide, Uulke A.;Pluim, Josien P. W.
提出了一种在三维磁共振扫描中自动描绘前列腺（包括精囊）的方法。该方法是基于一组预标记的图集图像的非刚性配准。每个图谱图像与目标患者图像非刚性配准。随后，融合变形的图谱标签图像以产生患者图像的单个分割。所提出的方法进行了评估50临床扫描，这是手动分割由三位专家。Dice相似系数（DSC）用于量化自动和手动分割之间的重叠。我们调查的分割方法的性能的几个因素的影响。对于注册，两个相似性措施进行比较：互信息和本地化版本的互信息。后者被证明是上级的（中位Δ DSC约为0.02，p 0.05）。为了评估图谱组成的影响，比较了两个图谱集。第一组包括38名健康志愿者的扫描。第二组通过留一法使用用于评价的50个临床扫描构建。第二个图谱集给出了实质上更好的性能（Δ DSC= 0.04，p
An automatic method for delineating the prostate (including the seminal vesicles) in three-dimensional magnetic resonance scans is presented. The method is based on nonrigid registration of a set of prelabeled atlas images. Each atlas image is nonrigidly registered with the target patient image. Subsequently, the deformed atlas label images are fused to yield a single segmentation of the patient image. The proposed method is evaluated on 50 clinical scans, which were manually segmented by three experts. The Dice similarity coefficient (DSC) is used to quantify the overlap between the automatic and manual segmentations. We investigate the impact of several factors on the performance of the segmentation method. For the registration, two similarity measures are compared: Mutual information and a localized version of mutual information. The latter turns out to be superior (median Delta DSC approximate to 0.02, p0.05). To assess the influence of the atlas composition, two atlas sets are compared. The first set consists of 38 scans of healthy volunteers. The second set is constructed by a leave-one-out approach using the 50 clinical scans that are used for evaluation. The second atlas set gives substantially better performance (Delta DSC=0.04,p