Section: New Results

Transfer learning for met-analyses of functional neuroimaging datasets

Participants : Bertrand Thirion, Jean-Baptiste Poline, Gaël Varoquaux, Yannick Schwartz [Correspondant] .

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 work, 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.

Figure 7. The brain regions that reliably predict that the subject is listening to Korean versus native (french) language (left) are similar to those that can be used to predict that the subject is listening an unintelligible language (jabberwoky) as opposed to their native (french) language (right).

More details can be found in [29] and [30] .