Bayesian Methods for Imaging Genetics

The analysis of combined neuroimaging and genetic data has tremendous potential for advancing our knowledge on how genetics relate to brain structure and brain function and how this relationship might modulate disease. This poses great challenges for data analytics as both neuroimaging and genetic data are highdimensional and the models that describe their relationship can involve millions of parameters. Bayesian approaches for imaging genetics have been developed to accommodate prior information on the relationship between neuroimaging endophenotypes and genetic variants while allowing for flexible statistical modelling structures. These include joint probabilistic frameworks for imaging, genetic and disease data and hierarchical models for relating neuroimaging and genetic data while accounting for spatial dependence in the data. The Bayesian framework allows naturally for the characterization of posterior uncertainty and inference which is an advantage over sparsity-based methods that emphasize point estimation. A substantial challenge associated with Bayesian methods within the context of imaging genetics however is the computation required for posterior approximation over a parameter space of high dimension. This article reviews recent work in this area of data analytics and outlines some challenges and future opportunities.

Author(s): Farouk Nathoo

Abstract | Full-Text | PDF

Share This Article