Graph-based inter-subject pattern analysis of FMRI data.

In brain imaging, solving learning problems in multi-subjects settings is difficult because of the differences that exist across individuals. Here we introduce a novel classification framework based on group-invariant graphical representations, allowing to overcome the inter-subject variability pres...

Full description

Bibliographic Details
Main Authors: Sylvain Takerkart, Guillaume Auzias, Bertrand Thirion, Liva Ralaivola
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2014-01-01
Series:PLoS ONE
Online Access:http://europepmc.org/articles/PMC4134217?pdf=render
_version_ 1818333827273064448
author Sylvain Takerkart
Guillaume Auzias
Bertrand Thirion
Liva Ralaivola
author_facet Sylvain Takerkart
Guillaume Auzias
Bertrand Thirion
Liva Ralaivola
author_sort Sylvain Takerkart
collection DOAJ
description In brain imaging, solving learning problems in multi-subjects settings is difficult because of the differences that exist across individuals. Here we introduce a novel classification framework based on group-invariant graphical representations, allowing to overcome the inter-subject variability present in functional magnetic resonance imaging (fMRI) data and to perform multivariate pattern analysis across subjects. Our contribution is twofold: first, we propose an unsupervised representation learning scheme that encodes all relevant characteristics of distributed fMRI patterns into attributed graphs; second, we introduce a custom-designed graph kernel that exploits all these characteristics and makes it possible to perform supervised learning (here, classification) directly in graph space. The well-foundedness of our technique and the robustness of the performance to the parameter setting are demonstrated through inter-subject classification experiments conducted on both artificial data and a real fMRI experiment aimed at characterizing local cortical representations. Our results show that our framework produces accurate inter-subject predictions and that it outperforms a wide range of state-of-the-art vector- and parcel-based classification methods. Moreover, the genericity of our method makes it is easily adaptable to a wide range of potential applications. The dataset used in this study and an implementation of our framework are available at http://dx.doi.org/10.6084/m9.figshare.1086317.
first_indexed 2024-12-13T13:57:49Z
format Article
id doaj.art-2bec3e643d3e4fb1bd701b94f9021f70
institution Directory Open Access Journal
issn 1932-6203
language English
last_indexed 2024-12-13T13:57:49Z
publishDate 2014-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj.art-2bec3e643d3e4fb1bd701b94f9021f702022-12-21T23:42:50ZengPublic Library of Science (PLoS)PLoS ONE1932-62032014-01-0198e10458610.1371/journal.pone.0104586Graph-based inter-subject pattern analysis of FMRI data.Sylvain TakerkartGuillaume AuziasBertrand ThirionLiva RalaivolaIn brain imaging, solving learning problems in multi-subjects settings is difficult because of the differences that exist across individuals. Here we introduce a novel classification framework based on group-invariant graphical representations, allowing to overcome the inter-subject variability present in functional magnetic resonance imaging (fMRI) data and to perform multivariate pattern analysis across subjects. Our contribution is twofold: first, we propose an unsupervised representation learning scheme that encodes all relevant characteristics of distributed fMRI patterns into attributed graphs; second, we introduce a custom-designed graph kernel that exploits all these characteristics and makes it possible to perform supervised learning (here, classification) directly in graph space. The well-foundedness of our technique and the robustness of the performance to the parameter setting are demonstrated through inter-subject classification experiments conducted on both artificial data and a real fMRI experiment aimed at characterizing local cortical representations. Our results show that our framework produces accurate inter-subject predictions and that it outperforms a wide range of state-of-the-art vector- and parcel-based classification methods. Moreover, the genericity of our method makes it is easily adaptable to a wide range of potential applications. The dataset used in this study and an implementation of our framework are available at http://dx.doi.org/10.6084/m9.figshare.1086317.http://europepmc.org/articles/PMC4134217?pdf=render
spellingShingle Sylvain Takerkart
Guillaume Auzias
Bertrand Thirion
Liva Ralaivola
Graph-based inter-subject pattern analysis of FMRI data.
PLoS ONE
title Graph-based inter-subject pattern analysis of FMRI data.
title_full Graph-based inter-subject pattern analysis of FMRI data.
title_fullStr Graph-based inter-subject pattern analysis of FMRI data.
title_full_unstemmed Graph-based inter-subject pattern analysis of FMRI data.
title_short Graph-based inter-subject pattern analysis of FMRI data.
title_sort graph based inter subject pattern analysis of fmri data
url http://europepmc.org/articles/PMC4134217?pdf=render
work_keys_str_mv AT sylvaintakerkart graphbasedintersubjectpatternanalysisoffmridata
AT guillaumeauzias graphbasedintersubjectpatternanalysisoffmridata
AT bertrandthirion graphbasedintersubjectpatternanalysisoffmridata
AT livaralaivola graphbasedintersubjectpatternanalysisoffmridata