Christine Keribin

A supervised clustering approach for fMRI-based inference of brain states

We propose a method that combines signals from many brain regions observed in functional Magnetic Resonance Imaging (fMRI) to predict the subjects behavior during a scanning session. Such predictions suffer from the huge number of brain regions sampled on the voxel grid of standard fMRI data sets: the curse of dimensionality. Dimensionality reduction is thus needed, but it is often performed using a univariate feature selection procedure, that handles neither the spatial structure of the images, nor the multivariate nature of the signal. By introducing a hierarchical clustering of the brain volume that incorporates connectivity constraints, we reduce the span of the possible spatial configurations to a single tree of nested regions tailored to the signal. We then prune the tree in a supervised setting, hence the name supervised clustering, in order to extract a parcellation (division of the volume) such that parcel-based signal averages best predict the target information. Dimensionality reduction is thus achieved by feature agglomeration, and the constructed features now provide a multi-scale representation of the signal. Comparisons with reference methods on both simulated and real data show that our approach yields higher prediction accuracy than standard voxel-based approaches. Moreover, the method infers an explicit weighting of the regions involved in the regression or classification task.

Estimation and selection for the latent block model on categorical data

This paper deals with estimation and model selection in the Latent Block Model (LBM) for categorical data. First, after providing sufficient conditions ensuring the identifiability of this model, we generalise estimation procedures and model selection criteria derived for binary data. Secondly, we develop Bayesian inference through Gibbs sampling and with a well calibrated non informative prior distribution, in order to get the MAP estimator: this is proved to avoid the traps encountered by the LBM with the maximum likelihood methodology. Then model selection criteria are presented. In particular an exact expression of the integrated completed likelihood criterion requiring no asymptotic approximation is derived. Finally numerical experiments on both simulated and real data sets highlight the appeal of the proposed estimation and model selection procedures.

Multiclass sparse Bayesian regression for fMRI-based prediction

Inverse inference has recently become a popular approach for analyzing neuroimaging data, by quantifying the amount of information contained in brain images on perceptual, cognitive, and behavioral parameters. As it outlines brain regions that convey information for an accurate prediction of the parameter of interest, it allows to understand how the corresponding information is encoded in the brain. However, it relies on a prediction function that is plagued by the curse of dimensionality, as there are far more features (voxels) than samples (images), and dimension reduction is thus a mandatory step. We introduce in this paper a new model, called Multiclass Sparse Bayesian Regression (MCBR), that, unlike classical alternatives, automatically adapts the amount of regularization to the available data. MCBR consists in grouping features into several classes and then regularizing each class differently in order to apply an adaptive and efficient regularization. We detail these framework and validate our algorithm on simulated and real neuroimaging data sets, showing that it performs better than reference methods while yielding interpretable clusters of features.

A supervised clustering approach for extracting predictive information from brain activation images

It is a standard approach to consider that images encode some information such as face expression or biomarkers in medical images; decoding this information is particularly challenging in the case of medical imaging, because the whole image domain has to be considered a priori to avoid biasing image-based prediction and image interpretation. Feature selection is thus needed, but is often performed using mass-univariate procedures, that handle neither the spatial structure of the images, nor the multivariate nature of the signal. Here we propose a solution that computes a reduced set of high-level features which compress the image information while retaining its informative parts: first, we introduce a hierarchical clustering of the research domain that incorporates spatial connectivity constraints and reduces the complexity of the possible spatial configurations to a single tree of nested regions. Then we prune the tree in order to produce a parcellation (division of the image domain) such that parcel-based signal averages optimally predict the target information. We show the power of this approach with respect to reference techniques on simulated data and apply it to enhance the prediction of the subjects behaviour during functional Magnetic Resonance Imaging (fMRI) scanning sessions. Besides its superior performance, the method provides an interpretable weighting of the regions involved in the regression or classification task.

Multi-class sparse Bayesian regression for neuroimaging data analysis

The use of machine learning tools is gaining popularity in neuroimaging, as it provides a sensitive assessment of the information conveyed by brain images. In particular, finding regions of the brain whose functional signal reliably predicts some behavioral information makes it possible to better understand how this information is encoded or processed in the brain. However, such a prediction is performed through regression or classification algorithms that suffer from the curse of dimensionality, because a huge number of features (i.e. voxels) are available to fit some target, with very few samples (i.e. scans) to learn the informative regions. A commonly used solution is to regularize the weights of the parametric prediction function. However, model specification needs a careful design to balance adaptiveness and sparsity. In this paper, we introduce a novel method, Multi-Class Sparse Bayesian Regression (MCBR), that generalizes classical approaches such as Ridge regression and Automatic Relevance Determination. Our approach is based on a grouping of the features into several classes, where each class is regularized with specific parameters. We apply our algorithm to the prediction of a behavioral variable from brain activation images. The method presented here achieves similar prediction accuracies than reference methods, and yields more interpretable feature loadings.