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

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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00734911
Contributor : Yannick Schwartz <>
Submitted on : Friday, September 28, 2012 - 1:28:19 PM
Last modification on : Thursday, March 7, 2019 - 3:34:14 PM
Document(s) archivé(s) le : Friday, December 16, 2016 - 6:48:16 PM

Files

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00734911, version 2
  • ARXIV : 1209.5375

Collections

Citation

Yannick Schwartz, Gaël Varoquaux, Christophe Pallier, Philippe Pinel, Jean-Baptiste Poline, et al.. Improving accuracy and power with transfer learning using a meta-analytic database. MICCAI, Oct 2012, Nice, France. pp.1-8. ⟨hal-00734911v2⟩

Share

Metrics

Record views

602

Files downloads

340