Localizing and Comparing Weight Maps Generated from Linear Kernel Machine Learning Models

Recently, machine learning models have been applied to neuroimaging data, allowing to make predictions about a variable of interest based on the pattern of activation or anatomy over a set of voxels. These pattern recognition based methods present undeniable assets over classical (univariate) techni...

Full description

Saved in:
Bibliographic Details
Published in2013 International Workshop on Pattern Recognition in Neuroimaging pp. 124 - 127
Main Authors Schrouff, J., Cremers, J., Garraux, G., Baldassarre, L., Mourao-Miranda, J., Phillips, C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2013
Subjects
Accuracy
Biological system modeling
Computational modeling
Data models
fMRI
machine learning
Neuroimaging
pattern comparison
pattern localization
Predictive models
ranking
Support vector machines
Online AccessGet full text
DOI10.1109/PRNI.2013.40

Cover

More Information
Summary:Recently, machine learning models have been applied to neuroimaging data, allowing to make predictions about a variable of interest based on the pattern of activation or anatomy over a set of voxels. These pattern recognition based methods present undeniable assets over classical (univariate) techniques, by providing predictions for unseen data, as well as the weights of each voxel in the model. However, the obtained weight map cannot be thresholded to perform regionally specific inference, leading to a difficult localization of the variable of interest. In this work, we provide local averages of the weights according to regions defined by anatomical or functional atlases (e.g. Brodmann atlas). These averages can then be ranked, thereby providing a sorted list of regions that can be (to a certain extent) compared with univariate results. Furthermore, we defined a "ranking distance", allowing for the quantitative comparison between localized patterns. These concepts are illustrated with two datasets.
DOI:10.1109/PRNI.2013.40