Section:
New Results
Total variation regularization for fMRI-based prediction of behaviour
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 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.
See also [15] and Fig. 3 .
Figure
3. Regression - Sizes prediction experiment -
Inter-subject analysis. Maps of weights found by TV regression
for various values of the regularization parameter . When
decreases, the TV regression algorithm creates different
clusters of weights with constant values. These clusters are easily
interpretable, compared to voxel-based map (see below). The TV
regression algorithm is very stable for different values of
. |