Graph-based inter-subject classification of local fMRI patterns

Abstract : Classification of medical images in multi-subjects settings is a difficult challenge due to the variability that exists between individuals. Here we introduce a new graph-based framework designed to deal with inter-subject functional variability present in fMRI data. A graphical model is constructed to encode the functional, geometric and structural properties of local activation patterns. We then design a specific graph kernel, allowing to conduct SVM classification in graph space. Experiments conducted in an inter-subject classification task of patterns recorded in the auditory cortex show that it is the only approach to perform above chance level, among a wide range of tested methods.
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00818815
Contributor : Sylvain Takerkart <>
Submitted on : Monday, April 29, 2013 - 11:45:57 AM
Last modification on : Thursday, March 7, 2019 - 3:34:14 PM
Document(s) archivé(s) le : Monday, August 19, 2013 - 9:47:20 AM

File

mlmi2012_takerkart_camera_read...
Files produced by the author(s)

Identifiers

Citation

Sylvain Takerkart, Guillaume Auzias, Bertrand Thirion, Daniele Schön, Liva Ralaivola. Graph-based inter-subject classification of local fMRI patterns. Third International Workshop Machine Learning in Medical Imaging - MLMI 2012 (Held in Conjunction with MICCAI 2012), Oct 2012, Nice, France. pp 184-192, ⟨10.1007/978-3-642-35428-1_23⟩. ⟨hal-00818815⟩

Share

Metrics

Record views

881

Files downloads

380