Abstract
In disease-association studies using neuroimaging data, evaluating the biological or clinical significance of individual associations requires not only detection of disease-associated areas of the brain but also estimation of the magnitudes of the associations or effect sizes for individual brain areas. In this paper, we propose a model-based framework for voxel-based inferences under spatial dependency in neuroimaging data. Specifically, we employ hierarchical mixture models with a hidden Markov random field structure to incorporate the spatial dependency between voxels. A nonparametric specification is proposed for the effect size distribution to flexibly estimate the underlying effect size distribution. Simulation experiments demonstrate that compared with a naive estimation method, the proposed methods can substantially reduce the selection bias in the effect size estimates of the selected voxels with the greatest observed associations. An application to neuroimaging data from an Alzheimer's disease study is provided.
Highlights
In disease-association studies using neuroimaging data, such as those related to brain magnetic resonance imaging (MRI), screening of disease-associated regions in the brain is a fundamental statistical task to understand the underlying mechanisms of disease and to develop disease diagnostics
Shu et al [4] proposed to use hidden Markov random field modelling and developed a multiple testing procedure based on the local index of significance (LIS) proposed by Sun and Cai [5] in multiple testing under dependency
We considered a simple situation where disease and normal control subjects were compared with no additional covariates
Summary
In disease-association studies using neuroimaging data, such as those related to brain magnetic resonance imaging (MRI), screening of disease-associated regions in the brain is a fundamental statistical task to understand the underlying mechanisms of disease and to develop disease diagnostics. In a cluster-level inference, groups of contiguous voxels whose association statistic values are above a certain threshold are defined and associated with disease status [1, 2] Another approach is to test every voxel individually, which takes into account the serious multiplicity problem of testing enormous numbers of voxels simultaneously. We use empirical Bayes estimation and hierarchical modelling of summary statistics from the whole set of features to derive shrinkage estimation for individual features [9, 10] and adapt this method to the analysis of disease-association studies using neuroimaging data with spatial dependence.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Computational and mathematical methods in medicine
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
