Nonlinear neural network for hemodynamic model state and input estimation using fMRI data

Handle URI:
http://hdl.handle.net/10754/563823
Title:
Nonlinear neural network for hemodynamic model state and input estimation using fMRI data
Authors:
Karam, Ayman M. ( 0000-0003-4130-330X ) ; Laleg-Kirati, Taous-Meriem ( 0000-0001-5944-0121 ) ; Zayane, Chadia ( 0000-0002-3035-3048 ) ; Kashou, Nasser H.
Abstract:
Originally inspired by biological neural networks, artificial neural networks (ANNs) are powerful mathematical tools that can solve complex nonlinear problems such as filtering, classification, prediction and more. This paper demonstrates the first successful implementation of ANN, specifically nonlinear autoregressive with exogenous input (NARX) networks, to estimate the hemodynamic states and neural activity from simulated and measured real blood oxygenation level dependent (BOLD) signals. Blocked and event-related BOLD data are used to test the algorithm on real experiments. The proposed method is accurate and robust even in the presence of signal noise and it does not depend on sampling interval. Moreover, the structure of the NARX networks is optimized to yield the best estimate with minimal network architecture. The results of the estimated neural activity are also discussed in terms of their potential use.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Applied Mathematics and Computational Science Program
Publisher:
Elsevier BV
Journal:
Biomedical Signal Processing and Control
Issue Date:
Nov-2014
DOI:
10.1016/j.bspc.2014.07.004
Type:
Article
ISSN:
17468094
Sponsors:
Research reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST). The authors would like to thank anonymous reviewers for valuables comments on the manuscript.
Appears in Collections:
Articles; Applied Mathematics and Computational Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorKaram, Ayman M.en
dc.contributor.authorLaleg-Kirati, Taous-Meriemen
dc.contributor.authorZayane, Chadiaen
dc.contributor.authorKashou, Nasser H.en
dc.date.accessioned2015-08-03T12:15:39Zen
dc.date.available2015-08-03T12:15:39Zen
dc.date.issued2014-11en
dc.identifier.issn17468094en
dc.identifier.doi10.1016/j.bspc.2014.07.004en
dc.identifier.urihttp://hdl.handle.net/10754/563823en
dc.description.abstractOriginally inspired by biological neural networks, artificial neural networks (ANNs) are powerful mathematical tools that can solve complex nonlinear problems such as filtering, classification, prediction and more. This paper demonstrates the first successful implementation of ANN, specifically nonlinear autoregressive with exogenous input (NARX) networks, to estimate the hemodynamic states and neural activity from simulated and measured real blood oxygenation level dependent (BOLD) signals. Blocked and event-related BOLD data are used to test the algorithm on real experiments. The proposed method is accurate and robust even in the presence of signal noise and it does not depend on sampling interval. Moreover, the structure of the NARX networks is optimized to yield the best estimate with minimal network architecture. The results of the estimated neural activity are also discussed in terms of their potential use.en
dc.description.sponsorshipResearch reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST). The authors would like to thank anonymous reviewers for valuables comments on the manuscript.en
dc.publisherElsevier BVen
dc.subjectBlock designen
dc.subjectBOLDen
dc.subjectEvent-relateden
dc.subjectfMRIen
dc.subjectHemodynamic modelen
dc.subjectNeural activityen
dc.subjectNeural networksen
dc.subjectNonlinear autoregressive with exogenous input (NARX)en
dc.subjectState estimationen
dc.titleNonlinear neural network for hemodynamic model state and input estimation using fMRI dataen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentApplied Mathematics and Computational Science Programen
dc.identifier.journalBiomedical Signal Processing and Controlen
dc.contributor.institutionDepartment of Biomedical, Industrial, and Human Factors Engineering, Wright State UniversityOH, United Statesen
kaust.authorLaleg-Kirati, Taous-Meriemen
kaust.authorZayane, Chadiaen
kaust.authorKaram, Ayman M.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.