Monotonic Gaussian Process for spatio-temporal disease progression modeling in brain imaging data

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 prio...

Full description

Saved in:
Bibliographic Details
Published in:NeuroImage (Orlando, Fla.) Fla.), 2020-01, Vol.205, p.116266-116266, Article 116266
Main Authors: Abi Nader, Clément, Ayache, Nicholas, Robert, Philippe, Lorenzi, Marco
Format: Article
Language:English
Subjects:
Aged
Aged, 80 and over
Alzheimer Disease - diagnostic imaging
Alzheimer Disease - pathology
Alzheimer’s disease
Bayesian modeling
Brain mapping
Clinical trials
Cognitive Dysfunction - diagnostic imaging
Cognitive Dysfunction - pathology
Data collection
Disease Progression
Disease progression modeling
Female
Gaussian process
Humans
Image Interpretation, Computer-Assisted - methods
Image Processing, Computer-Assisted - methods
Longitudinal Studies
Magnetic Resonance Imaging
Male
Mathematical models
Models, Statistical
Neurodegeneration
Neuroimaging
Neuroimaging - methods
Positron-Emission Tomography
Stochastic variational inference
Time Factors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1053-8119
1095-9572
1095-9572
DOI:10.1016/j.neuroimage.2019.116266