Extracting orthogonal subject- and condition-specific signatures from fMRI data using whole-brain effective connectivity

TY - JOUR

T1 - Extracting orthogonal subject- and condition-specific signatures from fMRI data using whole-brain effective connectivity

AU - Pallarés, Vicente

AU - Insabato, Andrea

AU - Sanjuán, Ana

AU - Kühn, Simone

AU - Mantini, Dante

AU - Deco, Gustavo

AU - Gilson, Matthieu

N1 - Copyright © 2018 The Authors. Published by Elsevier Inc. All rights reserved.

PY - 2018/9

Y1 - 2018/9

N2 - The study of brain communication based on fMRI data is often limited because such measurements are a mixture of session-to-session variability with subject- and condition-related information. Disentangling these contributions is crucial for real-life applications, in particular when only a few recording sessions are available. The present study aims to define a reliable standard for the extraction of multiple signatures from fMRI data, while verifying that they do not mix information about the different modalities (e.g., subjects and conditions such as tasks performed by them). In particular, condition-specific signatures should not be contaminated by subject-related information, since they aim to generalize over subjects. Practically, signatures correspond to subnetworks of directed interactions between brain regions (typically 100 covering the whole brain) supporting the subject and condition identification for single fMRI sessions. The key for robust prediction is using effective connectivity instead of functional connectivity. Our method demonstrates excellent generalization capabilities for subject identification in two datasets, using only a few sessions per subject as reference. Using another dataset with resting state and movie viewing, we show that the two signatures related to subjects and tasks correspond to distinct subnetworks, which are thus topologically orthogonal. Our results set solid foundations for applications tailored to individual subjects, such as clinical diagnostic.

AB - The study of brain communication based on fMRI data is often limited because such measurements are a mixture of session-to-session variability with subject- and condition-related information. Disentangling these contributions is crucial for real-life applications, in particular when only a few recording sessions are available. The present study aims to define a reliable standard for the extraction of multiple signatures from fMRI data, while verifying that they do not mix information about the different modalities (e.g., subjects and conditions such as tasks performed by them). In particular, condition-specific signatures should not be contaminated by subject-related information, since they aim to generalize over subjects. Practically, signatures correspond to subnetworks of directed interactions between brain regions (typically 100 covering the whole brain) supporting the subject and condition identification for single fMRI sessions. The key for robust prediction is using effective connectivity instead of functional connectivity. Our method demonstrates excellent generalization capabilities for subject identification in two datasets, using only a few sessions per subject as reference. Using another dataset with resting state and movie viewing, we show that the two signatures related to subjects and tasks correspond to distinct subnetworks, which are thus topologically orthogonal. Our results set solid foundations for applications tailored to individual subjects, such as clinical diagnostic.

KW - Journal Article

U2 - 10.1016/j.neuroimage.2018.04.070

DO - 10.1016/j.neuroimage.2018.04.070

M3 - SCORING: Journal article

C2 - 29753842

VL - 178

SP - 238

EP - 254

JO - NEUROIMAGE

JF - NEUROIMAGE

SN - 1053-8119

ER -