Open Access
June 2016 A spatiotemporal nonparametric Bayesian model of multi-subject fMRI data
Linlin Zhang, Michele Guindani, Francesco Versace, Jeffrey M. Engelmann, Marina Vannucci
Ann. Appl. Stat. 10(2): 638-666 (June 2016). DOI: 10.1214/16-AOAS926


In this paper we propose a unified, probabilistically coherent framework for the analysis of task-related brain activity in multi-subject fMRI experiments. This is distinct from two-stage “group analysis” approaches traditionally considered in the fMRI literature, which separate the inference on the individual fMRI time courses from the inference at the population level. In our modeling approach we consider a spatiotemporal linear regression model and specifically account for the between-subjects heterogeneity in neuronal activity via a spatially informed multi-subject nonparametric variable selection prior. For posterior inference, in addition to Markov chain Monte Carlo sampling algorithms, we develop suitable variational Bayes algorithms. We show on simulated data that variational Bayes inference achieves satisfactory results at more reduced computational costs than using MCMC, allowing scalability of our methods. In an application to data collected to assess brain responses to emotional stimuli our method correctly detects activation in visual areas when visual stimuli are presented.


Download Citation

Linlin Zhang. Michele Guindani. Francesco Versace. Jeffrey M. Engelmann. Marina Vannucci. "A spatiotemporal nonparametric Bayesian model of multi-subject fMRI data." Ann. Appl. Stat. 10 (2) 638 - 666, June 2016.


Received: 1 May 2015; Revised: 1 December 2015; Published: June 2016
First available in Project Euclid: 22 July 2016

zbMATH: 06625664
MathSciNet: MR3528355
Digital Object Identifier: 10.1214/16-AOAS926

Keywords: Multi-subject fMRI , spatiotemporal linear regression , variable selection priors , variational Bayes

Rights: Copyright © 2016 Institute of Mathematical Statistics

Vol.10 • No. 2 • June 2016
Back to Top