Small-sample brain mapping: sparse recovery on spatially correlated designs with randomization and clustering

Abstract : Functional neuroimaging can measure the brain's response to an external stimulus. It is used to perform brain mapping: identifying from these observations the brain regions involved. This problem can be cast into a linear supervised learning task where the neuroimaging data are used as predictors for the stimulus. Brain mapping is then seen as a support recovery problem. On functional MRI (fMRI) data, this problem is particularly challenging as i) the number of samples is small due to lim- ited acquisition time and ii) the variables are strongly correlated. We propose to overcome these difficulties using sparse regression models over new variables obtained by clustering of the original variables. The use of randomization techniques, e.g. bootstrap samples, and clustering of the variables improves the recovery properties of sparse methods. We demonstrate the benefit of our approach on an extensive simulation study as well as two fMRI datasets.
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download

https://hal.inria.fr/hal-00705192
Contributor : Gaël Varoquaux <>
Submitted on : Thursday, June 7, 2012 - 9:51:10 AM
Last modification on : Thursday, March 7, 2019 - 3:34:14 PM
Long-term archiving on : Saturday, September 8, 2012 - 4:05:08 AM

Files

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00705192, version 1

Collections

Citation

Gaël Varoquaux, Alexandre Gramfort, Bertrand Thirion. Small-sample brain mapping: sparse recovery on spatially correlated designs with randomization and clustering. International Conference on Machine Learning, Andrew McCallum, Jun 2012, Edimbourg, United Kingdom. ⟨hal-00705192⟩

Share

Metrics

Record views

2041

Files downloads

666