Bayesian Lesion Estimation with a Structured Spike-and-Slab Prior

TL;DR

This paper introduces BLESS, a scalable Bayesian spatial model for binary lesion detection in brain MRI scans, providing accurate uncertainty quantification and novel imaging statistics, validated on large-scale UK Biobank data.

Contribution

BLESS is a new hierarchical Bayesian model that handles binary spatial data with spike-and-slab priors and scalable variational inference, enabling large-scale lesion mapping with uncertainty quantification.

Findings

BLESS accurately estimates lesion locations and sizes.

The method provides credible intervals for cluster sizes.

Validated on 40,000 UK Biobank subjects.

Abstract

Neural demyelination and brain damage accumulated in white matter appear as hyperintense areas on T2-weighted MRI scans in the form of lesions. Modeling binary images at the population level, where each voxel represents the existence of a lesion, plays an important role in understanding aging and inflammatory diseases. We propose a scalable hierarchical Bayesian spatial model, called BLESS, capable of handling binary responses by placing continuous spike-and-slab mixture priors on spatially-varying parameters and enforcing spatial dependency on the parameter dictating the amount of sparsity within the probability of inclusion. The use of mean-field variational inference with dynamic posterior exploration, which is an annealing-like strategy that improves optimization, allows our method to scale to large sample sizes. Our method also accounts for underestimation of posterior variance due to variational inference by providing an approximate posterior sampling approach based on Bayesian bootstrap ideas and spike-and-slab priors with random shrinkage targets. Besides accurate uncertainty quantification, this approach is capable of producing novel cluster size based imaging statistics, such as credible intervals of cluster size, and measures of reliability of cluster occurrence. Lastly, we validate our results via simulation studies and an application to the UK Biobank, a large-scale lesion mapping study with a sample size of 40,000 subjects.