Total variation regularization for fMRI-based prediction of behaviour

Abstract

While medical imaging typically provides massive amounts of data, the extraction of relevant information for predictive diagnosis remains a difficult challenge. Functional MRI (fMRI) data, that provide an indirect measure of task-related or spontaneous neuronal activity, are classically analyzed in a mass-univariate procedure yielding statistical parametric maps. This analysis framework disregards some important principles of brain organization: population coding, distributed and overlapping representations. Multivariate pattern analysis, i.e., the prediction of behavioural variables from brain activation patterns better captures this structure. To cope with the high dimensionality of the data, the learning method has to be regularized. However, the spatial structure of the image is not taken into account in standard regularization methods, so that the extracted features are often hard to interpret. More informative and interpretable results can be obtained with the l_1 norm of the image gradient, a.k.a. its Total Variation (TV), as regularization. We apply for the first time this method to fMRI data, and show that TV regularization is well suited to the purpose of brain mapping while being a powerful tool for brain decoding. Moreover, this article presents the first use of TV regularization for classification.

Cited by in corpus (13)

• Assessing and tuning brain decoders: cross-validation, caveats, and guidelines
• Traction force microscopy with optimized regularization and automated Bayesian parameter selection for comparing cells
• Ring artifacts correction in compressed sensing tomographic reconstruction
• Incorporating structured assumptions with probabilistic graphical models in fMRI data analysis
• Predictive support recovery with TV-Elastic Net penalty and logistic regression: an application to structural MRI
• Bayesian Nonlinear Tensor Regression with Functional Fused Elastic Net Prior
• Graph-based regularization for regression problems with alignment and highly-correlated designs
• Measuring the functional connectome "on-the-fly": towards a new control signal for fMRI-based brain-computer interfaces
• Multi-scale Mining of fMRI data with Hierarchical Structured Sparsity
• Disease Prediction based on Functional Connectomes using a Scalable and Spatially-Informed Support Vector Machine
• Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space
• An Algorithmic Theory of Dependent Regularizers, Part 1: Submodular Structure
• Alternating Linearization for Structured Regularization Problems