Improved brain pattern recovery through ranking approaches

Fabian Pedregosa (1, 2) , Elodie Cauvet (3) , Gaël Varoquaux (2, 4) , Christophe Pallier (3) , Bertrand Thirion (2) , Alexandre Gramfort (2, 4)

1 SIERRA - Statistical Machine Learning and Parsimony
2 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data
3 NEUROSPIN - Service NEUROSPIN
4 LNAO - Laboratoire de Neuroimagerie Assistée par Ordinateur

Inferring the functional specificity of brain regions from functional Magnetic Resonance Images (fMRI) data is a challenging statistical problem. While the General Linear Model (GLM) remains the standard approach for brain mapping, supervised learning techniques (a.k.a.} decoding) have proven to be useful to capture multivariate statistical effects distributed across voxels and brain regions. Up to now, much effort has been made to improve decoding by incorporating prior knowledge in the form of a particular regularization term. In this paper we demonstrate that further improvement can be made by accounting for non-linearities using a ranking approach rather than the commonly used least-square regression. Through simulation, we compare the recovery properties of our approach to linear models commonly used in fMRI based decoding. We demonstrate the superiority of ranking with a real fMRI dataset.

Mots clés: fMRI; supervised learning; decoding; ranking

Domaines: Apprentissage [cs.LG]

Fabian Pedregosa, Elodie Cauvet, Gaël Varoquaux, Christophe Pallier, Bertrand Thirion, et al.. Improved brain pattern recovery through ranking approaches. PRNI 2012 : 2nd International Workshop on Pattern Recognition in NeuroImaging, Jul 2012, London, United Kingdom. ⟨hal-00717954⟩