Improving accuracy and power with transfer learning using a meta-analytic database

TL;DR

This paper introduces a transfer learning approach using a brain imaging database to improve prediction accuracy and statistical power in small cohort studies, leveraging voxel selection for better biomarker identification.

Contribution

It proposes a novel transfer learning method with sparse discriminant models that utilize a database of images to enhance brain imaging analysis.

Findings

Good prediction accuracy on 18 fMRI condition pairs

Higher detection power in small cohorts with voxel selection

Effective transfer learning across different scanners

Abstract

Typical cohorts in brain imaging studies are not large enough for systematic testing of all the information contained in the images. To build testable working hypotheses, investigators thus rely on analysis of previous work, sometimes formalized in a so-called meta-analysis. In brain imaging, this approach underlies the specification of regions of interest (ROIs) that are usually selected on the basis of the coordinates of previously detected effects. In this paper, we propose to use a database of images, rather than coordinates, and frame the problem as transfer learning: learning a discriminant model on a reference task to apply it to a different but related new task. To facilitate statistical analysis of small cohorts, we use a sparse discriminant model that selects predictive voxels on the reference task and thus provides a principled procedure to define ROIs. The benefits of our approach are twofold. First it uses the reference database for prediction, i.e. to provide potential biomarkers in a clinical setting. Second it increases statistical power on the new task. We demonstrate on a set of 18 pairs of functional MRI experimental conditions that our approach gives good prediction. In addition, on a specific transfer situation involving different scanners at different locations, we show that voxel selection based on transfer learning leads to higher detection power on small cohorts.