Your browser doesn't support javascript.
loading
Monotonic Gaussian Process for spatio-temporal disease progression modeling in brain imaging data.
Abi Nader, Clément; Ayache, Nicholas; Robert, Philippe; Lorenzi, Marco.
Afiliação
  • Abi Nader C; Université Côte d'Azur, Inria Sophia Antipolis, Epione Research Project, France. Electronic address: clement.abi-nader@inria.fr.
  • Ayache N; Université Côte d'Azur, Inria Sophia Antipolis, Epione Research Project, France. Electronic address: nicholas.ayache@inria.fr.
  • Robert P; Université Côte d'Azur, CoBTeK lab, MNC3 Program, France. Electronic address: probert@unice.fr.
  • Lorenzi M; Université Côte d'Azur, Inria Sophia Antipolis, Epione Research Project, France. Electronic address: marco.lorenzi@inria.fr.
Neuroimage ; 205: 116266, 2020 01 15.
Article em En | MEDLINE | ID: mdl-31648001
ABSTRACT
We introduce a probabilistic generative model for disentangling spatio-temporal disease trajectories from collections of high-dimensional brain images. The model is based on spatio-temporal matrix factorization, where inference on the sources is constrained by anatomically plausible statistical priors. To model realistic trajectories, the temporal sources are defined as monotonic and time-reparameterized Gaussian Processes. To account for the non-stationarity of brain images, we model the spatial sources as sparse codes convolved at multiple scales. The method was tested on synthetic data favourably comparing with standard blind source separation approaches. The application on large-scale imaging data from a clinical study allows to disentangle differential temporal progression patterns mapping brain regions key to neurodegeneration, while revealing a disease-specific time scale associated to the clinical diagnosis.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Interpretação de Imagem Assistida por Computador / Modelos Estatísticos / Progressão da Doença / Doença de Alzheimer / Neuroimagem / Disfunção Cognitiva Tipo de estudo: Observational_studies / Prognostic_studies / Risk_factors_studies Limite: Aged / Aged80 / Female / Humans / Male Idioma: En Ano de publicação: 2020 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Interpretação de Imagem Assistida por Computador / Modelos Estatísticos / Progressão da Doença / Doença de Alzheimer / Neuroimagem / Disfunção Cognitiva Tipo de estudo: Observational_studies / Prognostic_studies / Risk_factors_studies Limite: Aged / Aged80 / Female / Humans / Male Idioma: En Ano de publicação: 2020 Tipo de documento: Article