Description
Date depot: 1 janvier 1900
Titre: Learning methods for the spatiotemporal analysis of longitudinal image data
Directeur de thèse:
Olivier COLLIOT (ICM)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Non defini
Resumé:
Longitudinal data sets are often acquired in biological and medical sciences to capture variable temporal phenomena, which are due for instance to growth, ageing or disease progression. The statistical exploitation of such data sets is notably difficult since data of each individual follow a different trajectory of changes and at its own pace. This difficulty is further increased if observations take the form of structured data like images or measurements distributed at the nodes of a mesh, and if the measurements themselves are normalized data or positive definite matrices for which usual linear operations are not defined.
The Aramis team has contributed to the definition of a generic theoretical and algorithmic framework for learning typical trajectories from longitudinal data sets. (Durrleman et al. 2013) (Schiratti et al. 2015). This framework is built on tools from the Riemannian geometry to describe trajectories of changes for any kind of data and their variability within a group. The inference is based on a stochastic EM algorithm coupled with Markov Chain simulation methods.
The goal of my thesis is to extend this theoretical framework and develop techniques to estimate scenarios of Alzheimer’s disease progression, to identify pathological sub-types in a non-supervised manner, and to use these scenarios for diagnosis and prognosis purposes.
Doctorant.e: Bone Alexandre