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 limited 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.

Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

References in corpus (5)

• Scikit-learn: Machine Learning in Python
• Modern hierarchical, agglomerative clustering algorithms
• The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures
• A supervised clustering approach for fMRI-based inference of brain states
• Trace Lasso: a trace norm regularization for correlated designs

Cited by in corpus (11)

• Assessing and tuning brain decoders: cross-validation, caveats, and guidelines
• Learning and comparing functional connectomes across subjects
• Mind the duality gap: safer rules for the Lasso
• Recursive nearest agglomeration (ReNA): fast clustering for approximation of structured signals
• A Novel Approach for Stable Selection of Informative Redundant Features from High Dimensional fMRI Data
• Swapping Variables for High-Dimensional Sparse Regression with Correlated Measurements
• Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso
• A Max-Product EM Algorithm for Reconstructing Markov-tree Sparse Signals from Compressive Samples
• Path Thresholding: Asymptotically Tuning-Free High-Dimensional Sparse Regression
• Disease Prediction based on Functional Connectomes using a Scalable and Spatially-Informed Support Vector Machine
• Fast clustering for scalable statistical analysis on structured images