Social-sparsity brain decoders: faster spatial sparsity

Gaël Varoquaux (1, 2) , Matthieu Kowalski (1, 3) , Bertrand Thirion (2, 1)

1 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data
2 NEUROSPIN - Service NEUROSPIN
3 L2S - Laboratoire des signaux et systèmes

—Spatially-sparse predictors are good models for brain decoding: they give accurate predictions and their weight maps are interpretable as they focus on a small number of regions. However, the state of the art, based on total variation or graph-net, is computationally costly. Here we introduce sparsity in the local neighborhood of each voxel with social-sparsity, a structured shrinkage operator. We find that, on brain imaging classification problems, social-sparsity performs almost as well as total-variation models and better than graph-net, for a fraction of the computational cost. It also very clearly outlines predictive regions. We give details of the model and the algorithm.

Mots clés: brain decoding; sparsity; spatial regularization

Domaines: Traitement du signal et de l'image [eess.SP]; Statistiques [math.ST]; Machine Learning [stat.ML]; Imagerie; Sciences cognitives

Gaël Varoquaux, Matthieu Kowalski, Bertrand Thirion. Social-sparsity brain decoders: faster spatial sparsity. Pattern Recognition in NeuroImaging, Jun 2016, Trento, Italy. ⟨hal-01334551⟩