Header

UZH-Logo

Maintenance Infos

A New Representation of fMRI Signal by a Set of Local Meshes for Brain Decoding


Onal, Itir; Ozay, Mete; Mizrak, Eda; Öztekin, Ilke; Vural, Fatos T Yarman (2017). A New Representation of fMRI Signal by a Set of Local Meshes for Brain Decoding. IEEE Transactions on Signal and Information Processing over Networks, 3(4):683-694.

Abstract

How neurons influence each other's firing depends on the strength of synaptic connections among them. Motivated by the highly interconnected structure of the brain, in this study, we propose a computational model to estimate the relationships among voxels and employ them as features for cognitive state classification. We represent the sequence of functional Magnetic Resonance Imaging (fMRI) measurements recorded during a cognitive stimulus by a set of local meshes. Then, we represent the corresponding cognitive state by the edge weights of these meshes each of which is estimated assuming a regularized linear relationship among voxel time series in a predefined locality. The estimated mesh edge weights provide a better representation of information in the brain for cognitive state or task classification. We examine the representative power of our mesh edge weights on visual recognition and emotional memory retrieval experiments by training a support vector machine classifier. Also, we use mesh edge weights as feature vectors of inter-subject classification on Human Connectome Project task fMRI dataset, and test their performance. We observe that mesh edge weights perform better than the popular fMRI features, such as, raw voxel intensity values, pairwise correlations, features extracted using PCA and ICA, for classifying the cognitive states.

Abstract

How neurons influence each other's firing depends on the strength of synaptic connections among them. Motivated by the highly interconnected structure of the brain, in this study, we propose a computational model to estimate the relationships among voxels and employ them as features for cognitive state classification. We represent the sequence of functional Magnetic Resonance Imaging (fMRI) measurements recorded during a cognitive stimulus by a set of local meshes. Then, we represent the corresponding cognitive state by the edge weights of these meshes each of which is estimated assuming a regularized linear relationship among voxel time series in a predefined locality. The estimated mesh edge weights provide a better representation of information in the brain for cognitive state or task classification. We examine the representative power of our mesh edge weights on visual recognition and emotional memory retrieval experiments by training a support vector machine classifier. Also, we use mesh edge weights as feature vectors of inter-subject classification on Human Connectome Project task fMRI dataset, and test their performance. We observe that mesh edge weights perform better than the popular fMRI features, such as, raw voxel intensity values, pairwise correlations, features extracted using PCA and ICA, for classifying the cognitive states.

Statistics

Citations

Dimensions.ai Metrics
2 citations in Web of Science®
7 citations in Scopus®
Google Scholar™

Altmetrics

Additional indexing

Item Type:Journal Article, not_refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Psychology
Dewey Decimal Classification:150 Psychology
Scopus Subject Areas:Physical Sciences > Signal Processing
Physical Sciences > Information Systems
Physical Sciences > Computer Networks and Communications
Language:English
Date:1 December 2017
Deposited On:11 Nov 2019 14:08
Last Modified:28 Jul 2020 14:15
Publisher:Institute of Electrical and Electronics Engineers
ISSN:2373-776X
OA Status:Closed
Publisher DOI:https://doi.org/10.1109/tsipn.2017.2679491

Download

Full text not available from this repository.
View at publisher

Get full-text in a library