Statistical Shape Analysis of Large Datasets Based on Diffeomorphic Iterative Centroids - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Frontiers in Neuroscience Year : 2018

Statistical Shape Analysis of Large Datasets Based on Diffeomorphic Iterative Centroids

Abstract

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.
Fichier principal
Vignette du fichier
fnins-12-00803.pdf (2.03 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01920263 , version 2 (13-11-2018)
hal-01920263 , version 1 (12-02-2019)

Licence

Attribution

Identifiers

Cite

Claire Cury, Joan Glaunès, Roberto Toro, Marie Chupin, Gunter Schumann, et al.. Statistical Shape Analysis of Large Datasets Based on Diffeomorphic Iterative Centroids. Frontiers in Neuroscience, 2018, 12, pp.803. ⟨10.3389/fnins.2018.00803⟩. ⟨hal-01920263v2⟩
1298 View
551 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More