Learning Distributions of Shape Trajectories from Longitudinal Datasets: A Hierarchical Model on a Manifold of Diffeomorphisms

  title={Learning Distributions of Shape Trajectories from Longitudinal Datasets: A Hierarchical Model on a Manifold of Diffeomorphisms},
  author={Alexandre B{\^o}ne and Olivier Colliot and Stanley Durrleman},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
We propose a method to learn a distribution of shape trajectories from longitudinal data, i.e. the collection of individual objects repeatedly observed at multiple time-points. The method allows to compute an average spatiotemporal trajectory of shape changes at the group level, and the individual variations of this trajectory both in terms of geometry and time dynamics. First, we formulate a non-linear mixed-effects statistical model as the combination of a generic statistical model for… 

Figures and Tables from this paper

Clustering of Longitudinal Shape Data Sets Using Mixture of Separate or Branching Trajectories

It is shown how the tempered version of the stochastic EM algorithm can be used to test different scenarios of hippocampus atrophy in ageing by using an heteregenous population of normal ageing individuals and mild cognitive impaired subjects.

Learning the spatiotemporal variability in longitudinal shape data sets

A generative statistical model to learn the spatiotemporal variability in longitudinal shape data sets, which contain repeated observations of a set of objects or individuals over time, is proposed and applied to the modeling of the progressive atrophy of the hippocampus in Alzheimer’s disease patients.

A Nonlinear Hierarchical Model for Longitudinal Data on Manifolds

Large longitudinal studies provide information that is particularly valuable in medical studies. A problem that must be solved in order to realize the full potential is the correlation between

Riemannian Geometry Learning for Disease Progression Modelling

Riemannian manifold learning in association with the statistical task of longitudinal trajectory analysis is performed using a deep generative network, which maps trajectories in a low-dimensional Euclidean space to the observation space.

Computational and statistical methods for trajectory analysis in a Riemannian geometry setting. (Méthodes numériques et statistiques pour l'analyse de trajectoire dans un cadre de geométrie Riemannienne)

This PhD proposes new Riemannian geometry tools for the analysis of longitudinal observations of neuro-degenerative subjects by proposing a numerical scheme to compute the parallel transport along geodesics and tackling the issue of RiemANNian manifold learning.

A Geodesic Mixed Effects Model in Kendall's Shape Space

This work proposes the corresponding variational time discretization of geodesics and applies the approach for the estimation of group trends and statistical testing of 3D shapes derived from an open access longitudinal imaging study on osteoarthritis.

Hierarchical Geodesic Modeling on the Diffusion Orientation Distribution Function for Longitudinal DW-MRI Analysis

This work proposes a new framework to estimate a population trajectory of longitudinal diffusion orientation distribution functions (dODFs) along with subject-specific changes by using hierarchical geodesic modeling and validated on synthetic longitudinal dODF data.

Deformetrica 4: An Open-Source Software for Statistical Shape Analysis

Deformetrica is an open-source software for the statistical analysis of images and meshes. It relies on a specific instance of the large deformation diffeomorphic metric mapping (LDDMM) framework,

A new geodesic-based feature for characterization of 3D shapes: application to soft tissue organ temporal deformations

This study proposes a method for characterizing 3D shapes from point clouds and shows a direct application on a study of organ temporal deformations, showing that the proposed feature may be useful for several computer vision applications such as medical imaging, aerodynamics and robotics.



Learning spatiotemporal trajectories from manifold-valued longitudinal data

A Bayesian mixed-effects model is proposed to learn typical scenarios of changes from longitudinal manifold-valued data, namely repeated measurements of the same objects or individuals at several points in time, to estimate a group-average trajectory in the space of measurements.

Statistical Learning of Spatiotemporal Patterns from Longitudinal Manifold-Valued Networks

A mixed-effects model to learn spatiotempo-ral patterns on a network by considering longitudinal measures distributed on a fixed graph is introduced and it is shown that the personaliza-tion of this model yields accurate prediction of maps of cortical thickness in patients.

Statistical analysis of trajectories on Riemannian manifolds: Bird migration, hurricane tracking and video surveillance

We consider the statistical analysis of trajectories on Riemannian manifolds that are observed under arbitrary temporal evolutions. Past methods rely on cross-sectional analysis, with the given

Geodesic regression of image and shape data for improved modeling of 4D trajectories

This paper presents a framework for joint image and shape regression which incorporates images as well as anatomical shape information in a consistent manner and derives a gradient descent algorithm which simultaneously estimates baseline images and shapes, location of control points, and momenta.

Statistics on the space of trajectories for longitudinal data analysis

This paper presents a novel formulation of the longitudinal data analysis problem by identifying the structural changes over time to a product Riemannian manifold endowed with a Riemanni metric and a probability measure and presents theoretical results showing that the maximum likelihood estimate of the mean and median of a Gaussian and Laplace distribution respectively on the product manifold yield the Fréchet mean and Median respectively.

Sasaki metrics for analysis of longitudinal data on manifolds

The ability of these methods to distinguish differences in shape changes in a comparison of longitudinal corpus callosum data in subjects with dementia versus healthily aging controls is demonstrated.

Riemannian Nonlinear Mixed Effects Models: Analyzing Longitudinal Deformations in Neuroimaging

This paper generalizes non-linear mixed effects model to the regime where the response variable is manifold-valued, i.e., f: Rd → M: Rd; and demonstrates the immediate benefits such a model can provide and derive the underlying model and estimation schemes and demonstrate the direct consequence of the results.

Spatiotemporal Atlas Estimation for Developmental Delay Detection in Longitudinal Datasets

The method is used to analyze the morphological evolution of 2D profiles of hominids skulls and to analyze brain growth from amygdala of autistics, developmental delay and control children.

Bayesian Mixed Effect Atlas Estimation with a Diffeomorphic Deformation Model

A diffeomorphic constraint on the deformations considered in the deformable Bayesian mixed effect template model is introduced and an extension of the model including a sparsity constraint to select an optimal number of control points with relevant positions is proposed.

Multivariate General Linear Models (MGLM) on Riemannian Manifolds with Applications to Statistical Analysis of Diffusion Weighted Images

The variational algorithm efficiently solves for multiple geodesic bases on the manifold concurrently via gradient updates and allows us to answer questions such as: what is the relationship of the measurement at voxel y to disease when conditioned on age and gender.