Skip to Main content Skip to Navigation
Poster communications

Learning spatio-temporal trajectories from manifold-valued longitudinal data

Jean-Baptiste Schiratti 1, 2 Stéphanie Allassonniere 1 Olivier Colliot 2 Stanley Durrleman 2
2 ARAMIS - Algorithms, models and methods for images and signals of the human brain
Inria Paris-Rocquencourt, UPMC - Université Pierre et Marie Curie - Paris 6, ICM - Institut du Cerveau et de la Moëlle Epinière = Brain and Spine Institute
Abstract : We propose a Bayesian mixed-effects model 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. The model allows to estimate a group-average trajectory in the space of measurements. Random variations of this trajectory result from spatiotemporal transformations, which allow changes in the direction of the trajectory and in the pace at which trajectories are followed. The use of the tools of Riemannian geometry allows to derive a generic algorithm for any kind of data with smooth constraints, which lie therefore on a Riemannian manifold. Stochastic approximations of the Expectation-Maximization algorithm is used to estimate the model parameters in this highly non-linear setting. The method is used to estimate a data-driven model of the progressive impairments of cognitive functions during the onset of Alzheimer’s disease. Experimental results show that the model correctly put into correspondence the age at which each in- dividual was diagnosed with the disease, thus validating the fact that it effectively estimated a normative scenario of disease progression. Random effects provide unique insights into the variations in the ordering and timing of the succession of cognitive impairments across different individuals.
Document type :
Poster communications
Complete list of metadatas
Contributor : Jean-Baptiste Schiratti <>
Submitted on : Friday, December 18, 2015 - 4:35:05 PM
Last modification on : Monday, December 14, 2020 - 5:20:39 PM
Long-term archiving on: : Saturday, March 19, 2016 - 11:10:27 AM


Files produced by the author(s)


Public Domain


  • HAL Id : hal-01245909, version 1


Jean-Baptiste Schiratti, Stéphanie Allassonniere, Olivier Colliot, Stanley Durrleman. Learning spatio-temporal trajectories from manifold-valued longitudinal data. Neural Information Processing Systems, Dec 2015, Montréal, Canada. Advances in Neural Information Processing Systems. ⟨hal-01245909⟩



Record views


Files downloads