Statistical validation of image segmentation quality based on a spatial overlap index - Scientific reports
Statistical validation of image segmentation quality based on a spatial overlap index - Scientific reports
复制标题
DOI：
10.1016/s1076-6332(03)00671-8
复制
发表时间：
2004-02-01
影响因子：
4.8
通讯作者：
Kikinis, R
中科院分区：
文献类型：
--
作者：
Zou, KH;Warfield, SK;Kikinis, R
理由和目标。为了检查基于相同解剖结构的两组分割之间的空间重叠的统计验证方法。Dice相似系数（DSC）被用作统计验证指标，以评估手动分割的再现性和MR图像自动概率分数分割的空间重叠准确性的性能，在两个临床实例中进行了说明。例1：10例前列腺近距离放射治疗患者接受了术前1.5T和术中0.5T MR成像。对于每种情况，分别在术前和术中图像上对前列腺外周区进行5次重复手动分割。实施例2：将半自动概率分数分割算法应用于具有3种类型的脑肿瘤的9个病例的MR成像。计算DSC值，并将对数转换值与方差分析（ANOVA）的平均值进行比较。例一：1.5T术前MRI的平均DSC为0.883（范围，0.876-0.893），0.5T术中MRI的平均DSC为0.838（范围，0.819-0.852）（P <0.001），分别在良好再现性范围内和边缘。例二：脑肿瘤的DSC范围较宽：脑膜瘤（0.519-0.893）、星形细胞瘤（0.487-0.972）和其他混合性胶质瘤（0.490-0.899）。DSC值是空间重叠的一种简单而有用的概括性度量，可应用于图像分割的再现性和准确性的研究。我们在两个临床应用中观察到总体令人满意但可变的验证结果。该度量可适用于类似的验证任务。
Rationale and Objectives. To examine a statistical validation method based on the spatial overlap between two sets of segmentations of the same anatomy.Materials and Methods. The Dice similarity coefficient (DSC) was used as a statistical validation metric to evaluate the performance of both the reproducibility of manual segmentations and the spatial overlap accuracy of automated probabilistic fractional segmentation of MR images, illustrated on two clinical examples. Example 1: 10 consecutive cases of prostate brachytherapy patients underwent both preoperative 1.5T and intraoperative 0.5T MR imaging. For each case, 5 repeated manual segmentations of the prostate peripheral zone were performed separately on preoperative and on intraoperative images. Example 2: A semi-automated probabilistic fractional segmentation algorithm was applied to MR imaging of 9 cases with 3 types of brain tumors. DSC values were computed and logit-transformed values were compared in the mean with the analysis of variance (ANOVA).Results. Example 1: The mean DSCs of 0.883 (range, 0.876-0.893) with 1.5T preoperative MRI and 0.838 (range, 0.819-0.852) with 0.5T intraoperative MRI (P < .001) were within and at the margin of the range of good reproducibility, respectively. Example 2: Wide ranges of DSC were observed in brain tumor segmentations: Meningiomas (0.519-0.893), astrocytomas (0.487-0.972), and other mixed gliomas (0.490-0.899).Conclusion. The DSC value is a simple and useful summary measure of spatial overlap, which can be applied to studies of reproducibility and accuracy in image segmentation. We observed generally satisfactory but variable validation results in two clinical applications. This metric may be adapted for similar validation tasks.