Section: New Results

Principal Component Regression predicts functional responses across individuals

Participants : Bertrand Thirion [Correspondant] , Gaël Varoquaux, Olivier Grisel.

Inter-subject variability is a major hurdle for neuroimaging group-level inference, as it creates complex image patterns that are not captured by standard analysis models and jeopardizes the sensitivity of statistical procedures. A solution to this problem is to model random subjects effects by using the redundant information conveyed by multiple imaging contrasts. In this paper, we introduce a novel analysis framework, where we estimate the amount of variance that is fit by a random effects subspace learned on other images; we show that a principal component regression estimator outperforms other regression models and that it fits a significant proportion (10% to 25%) of the between-subject variability. This proves for the first time that the accumulation of contrasts in each individual can provide the basis for more sensitive neuroimaging group analyzes.

Figure 4. In most brain regions, knowing the amount of activation related to a set of reference contrasts yields an accurate prediction of the activation for a target contrast.

More details can be found in [36] .