Multiscale Mining of fMRI Data with Hierarchical Structured Sparsity

DOI10.1137/110832380MaRDI QIDQ4902145zbMATHOpenAlexDBLPWikidataFDO

Authors Rodolphe Jenatton, Alexandre Gramfort, Vincent Michel, Guillaume Obozinski, Evelyn Eger, Francis Bach, Bertrand Thirion

Publication date 25 January 2013

Published in SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1105.0363

zbMATH Keywords

proximal methodsstructured sparsitybrain readingintersubject validationsparse hierarchical models

Mathematics Subject Classification ID

Multivariate analysis (62H99) Applications of statistics to biology and medical sciences; meta analysis (62P10) Convex programming (90C25) Ridge regression; shrinkage estimators (Lasso) (62J07) Ill-posedness and regularization problems in numerical linear algebra (65F22)

Abstract: Inverse inference, or "brain reading", is a recent paradigm for analyzing functional magnetic resonance imaging (fMRI) data, based on pattern recognition and statistical learning. By predicting some cognitive variables related to brain activation maps, this approach aims at decoding brain activity. Inverse inference takes into account the multivariate information between voxels and is currently the only way to assess how precisely some cognitive information is encoded by the activity of neural populations within the whole brain. However, it relies on a prediction function that is plagued by the curse of dimensionality, since there are far more features than samples, i.e., more voxels than fMRI volumes. To address this problem, different methods have been proposed, such as, among others, univariate feature selection, feature agglomeration and regularization techniques. In this paper, we consider a sparse hierarchical structured regularization. Specifically, the penalization we use is constructed from a tree that is obtained by spatially-constrained agglomerative clustering. This approach encodes the spatial structure of the data at different scales into the regularization, which makes the overall prediction procedure more robust to inter-subject variability. The regularization used induces the selection of spatially coherent predictive brain regions simultaneously at different scales. We test our algorithm on real data acquired to study the mental representation of objects, and we show that the proposed algorithm not only delineates meaningful brain regions but yields as well better prediction accuracy than reference methods.

Recommendations

• Hierarchical spatio-temporal modeling of resting state fMRI data
• A hierarchical model for probabilistic independent component analysis of multi-subject fMRI studies

Cited in

(9)

• An Interactive Greedy Approach to Group Sparsity in High Dimensions
• Minimum distance Lasso for robust high-dimensional regression
• A supervised clustering approach for fMRI-based inference of brain states
• Structured learning in time-dependent Cox models
• Linearized alternating direction method of multipliers for sparse group and fused Lasso models
• A hierarchical modeling approach to data analysis and study design in a multi-site experimental fMRI study
• Structured sparsity through convex optimization
• Structured sparsity: discrete and convex approaches
• Regularized brain reading with shrinkage and smoothing

Describes a project that uses

Uses Software

• MayaVi
• Mayavi
• UNLocBoX

This page was built for publication: Multiscale Mining of fMRI Data with Hierarchical Structured Sparsity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4902145)