Towards accurate, automatic segmentation of the hippocampus and amygdala from MRI by augmenting ANIMAL with a template library and label fusion
Towards accurate, automatic segmentation of the hippocampus and amygdala from MRI by augmenting ANIMAL with a template library and label fusion
复制标题
DOI：
10.1016/j.neuroimage.2010.04.193
复制
发表时间：
2010-10-01
期刊：
影响因子：
5.7
通讯作者：
Pruessner, Jens C.
中科院分区：
文献类型：
--
作者：
Collins, D. Louis;Pruessner, Jens C.
我们描述了从MRI数据中对人类受试者的海马（HC）和杏仁核（AG）进行全自动分割的进展。三种方法进行了描述和测试与一组MRI从80名年轻的正常对照，使用手动标记的HC和AG作为金标准。这些方法包括：1）我们的基于动物图谱的方法，该方法使用非线性配准到预标记的非线性平均模板（ICBM 152）。在模板上定义的HC和AG标签通过逆变换映射以在受试者的MRI上分割这些结构。2)我们从80个标记数据集中选择最相似的MRI作为标准动物分割方案中的模板。3)我们使用标签融合技术来结合联合收割机分割从'n'最相似的模板。标签融合技术产生的最佳中位数Dice Kappa为0.886和相似性为0.795 HC，和0.826和0.703分别为AG。(C)2010年爱思唯尔公司All rights reserved.
We describe progress towards fully automatic segmentation of the hippocampus (HC) and amygdala (AG) in human subjects from MRI data. Three methods are described and tested with a set of MRIs from 80 young normal controls, using manual labeling of the HC and AG as a gold standard. The methods include: 1) our ANIMAL atlas-based method that uses non-linear registration to a pre-labeled non-linear average template (ICBM152). HC and AG labels, defined on the template are mapped through the inverse transformation to segment these structures on the subject's MRI. 2) We select the most similar MRI from the set of 80 labeled datasets to use as a template in the standard ANIMAL segmentation scheme. 3) We use label fusion techniques to combine segmentations from the 'n' most similar templates. The label fusion technique yields an optimal median Dice Kappa of 0.886 and similarity of 0.795 for HC, and 0.826 and 0.703 respectively for AG. (C) 2010 Elsevier Inc. All rights reserved.