Cury Claire, Glaunès Joan A, Toro Roberto, Chupin Marie, Schumann Gunter, Frouin Vincent, Poline Jean-Baptiste, Colliot Olivier
Institut du Cerveau et de la Moelle épinire, ICM, Paris, France.
Inserm, U 1127, Paris, France.
Front Neurosci. 2018 Nov 12;12:803. doi: 10.3389/fnins.2018.00803. eCollection 2018.
In this paper, we propose an approach for template-based shape analysis of large datasets, using diffeomorphic centroids as atlas shapes. Diffeomorphic centroid methods fit in the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework and use kernel metrics on currents to quantify surface dissimilarities. The statistical analysis is based on a Kernel Principal Component Analysis (Kernel PCA) performed on the set of initial momentum vectors which parametrize the deformations. We tested the approach on different datasets of hippocampal shapes extracted from brain magnetic resonance imaging (MRI), compared three different centroid methods and a variational template estimation. The largest dataset is composed of 1,000 surfaces, and we are able to analyse this dataset in 26 h using a diffeomorphic centroid. Our experiments demonstrate that computing diffeomorphic centroids in place of standard variational templates leads to similar shape analysis results and saves around 70% of computation time. Furthermore, the approach is able to adequately capture the variability of hippocampal shapes with a reasonable number of dimensions, and to predict anatomical features of the hippocampus, only present in 17% of the population, in healthy subjects.
在本文中，我们提出了一种基于模板的大型数据集形状分析方法，使用微分同胚质心作为图谱形状。微分同胚质心方法适用于大变形微分同胚度量映射（LDDMM）框架，并使用流上的核度量来量化表面差异。统计分析基于对参数化变形的初始动量向量集执行的核主成分分析（Kernel PCA）。我们在从脑磁共振成像（MRI）中提取的不同海马形状数据集上测试了该方法，比较了三种不同的质心方法和一种变分模板估计。最大的数据集由1000个表面组成，我们能够使用微分同胚质心在26小时内分析该数据集。我们的实验表明，计算微分同胚质心代替标准变分模板会产生相似的形状分析结果，并节省约70%的计算时间。此外，该方法能够用合理数量的维度充分捕捉海马形状的变异性，并预测健康受试者中仅17%的人群中存在的海马解剖特征。
