Connectivity-informed Sparse Classifiers for fMRI Brain Decoding - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Connectivity-informed Sparse Classifiers for fMRI Brain Decoding


In recent years, sparse regularization has become a dominant means for handling the curse of dimensionality in functional magnetic resonance imaging (fMRI) based brain decoding problems. Enforcing sparsity alone, however, neglects the interactions between connected brain areas. Methods that additionally impose spatial smoothness would account for local but not long-range interactions. In this paper, we propose incorporating connectivity into sparse classifier learning so that both local and long-range connections can be jointly modeled. On real data, we demonstrate that integrating connectivity information inferred from diffusion tensor imaging (DTI) data provides higher classification accuracy and more interpretable classifier weight patterns than standard classifiers. Our results thus illustrate the benefits of adding neurologically-relevant priors in fMRI brain decoding.


Medical Imaging
Fichier principal
Vignette du fichier
connClassifierPRNI2012.pdf (726.35 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00726656 , version 1 (31-08-2012)


  • HAL Id : hal-00726656 , version 1


Bernard Ng, Viviana Siless, Gaël Varoquaux, Jean-Baptiste Poline, Bertrand Thirion, et al.. Connectivity-informed Sparse Classifiers for fMRI Brain Decoding. Pattern Recognition in Neuroimaging, Christos Davatzikos, Moritz Grosse-Wentrup, Janaina Mourao-Miranda, Dimitri Van De Ville, Jul 2012, London, United Kingdom. ⟨hal-00726656⟩
312 View
385 Download


Gmail Facebook X LinkedIn More