Classification of autistic individuals and controls using cross-task characterization of fMRI activity
NeuroImage: Clinical. 2016-01-01; 10: 78-88
DOI: 10.1016/j.nicl.2015.11.010
Read on PubMed
1. Neuroimage Clin. 2015 Nov 17;10:78-88. doi: 10.1016/j.nicl.2015.11.010.
eCollection 2016.
Classification of autistic individuals and controls using cross-task
characterization of fMRI activity.
Chanel G(1), Pichon S(2), Conty L(3), Berthoz S(4), Chevallier C(5), Grèzes
J(6).
Author information:
(1)Swiss Center for Affective Sciences, Campus Biotech, University of Geneva,
Geneva, Switzerland; Computer Vision and Multimedia Laboratory, University of
Geneva, Geneva, Switzerland.
(2)Swiss Center for Affective Sciences, Campus Biotech, University of Geneva,
Geneva, Switzerland; Faculty of Psychology and Educational Sciences, University
of Geneva, Geneva, Switzerland.
(3)Laboratoire de Psychopathologie et Neuropsychologie EA 2027, Université Paris
8, France.
(4)CESP, INSERM, Univ. Paris-Sud, Univ. Paris Descartes, UVSQ, Université
Paris-Saclay, Paris, France; Departement de Psychiatrie de l’Institut Mutualiste
Montsouris, Paris, France.
(5)Laboratoire de Neuroscience Cognitive, INSERM U960, Ecole Normale Supérieure,
Paris, France.
(6)Laboratoire de Neuroscience Cognitive, INSERM U960, Ecole Normale Supérieure,
Paris, France; Centre de Neuroimagerie de Recherche (CENIR), Centre de Recherche
de l’Institut du Cerveau et de la Moelle épinière (CRICM), Université Pierre et
Marie Curie-Paris 6 UMRS 975, Inserm U975, CNRS UMR 7225, Institut du cerveau et
de la moëlle épinière (ICM), Paris 75013, France.
Multivariate pattern analysis (MVPA) has been applied successfully to task-based
and resting-based fMRI recordings to investigate which neural markers
distinguish individuals with autistic spectrum disorders (ASD) from controls.
While most studies have focused on brain connectivity during resting state
episodes and regions of interest approaches (ROI), a wealth of task-based fMRI
datasets have been acquired in these populations in the last decade. This calls
for techniques that can leverage information not only from a single dataset, but
from several existing datasets that might share some common features and
biomarkers. We propose a fully data-driven (voxel-based) approach that we apply
to two different fMRI experiments with social stimuli (faces and bodies). The
method, based on Support Vector Machines (SVMs) and Recursive Feature
Elimination (RFE), is first trained for each experiment independently and each
output is then combined to obtain a final classification output. Second, this
RFE output is used to determine which voxels are most often selected for
classification to generate maps of significant discriminative activity. Finally,
to further explore the clinical validity of the approach, we correlate
phenotypic information with obtained classifier scores. The results reveal good
classification accuracy (range between 69% and 92.3%). Moreover, we were able to
identify discriminative activity patterns pertaining to the social brain without
relying on a priori ROI definitions. Finally, social motivation was the only
dimension which correlated with classifier scores, suggesting that it is the
main dimension captured by the classifiers. Altogether, we believe that the
present RFE method proves to be efficient and may help identifying relevant
biomarkers by taking advantage of acquired task-based fMRI datasets in
psychiatric populations.
DOI: 10.1016/j.nicl.2015.11.010
PMCID: PMC4683429
PMID: 26793434 [Indexed for MEDLINE]