Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers

Yang, Scott; Sanchez, Jose Miguel; Fernandez, Ricardo Bruña; Deravi, Farzin; Hoque, Sanaul; Wong-Lin, KongFatt; Prasad, Girijesh

doi:10.3390/s21186210

Journal article 501 views 71 downloads

Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers

Scott Yang

, Jose Miguel Sanchez Bornot, Ricardo Bruña Fernandez, Farzin Deravi, Sanaul Hoque, KongFatt Wong-Lin, Girijesh Prasad

Sensors, Volume: 21, Issue: 18, Start page: 6210

Swansea University Author: Scott Yang

PDF | Version of Record

© 2021 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license
Download (2.24MB)

Check full text

DOI (Published version): 10.3390/s21186210

Abstract

Studies on developing effective neuromarkers based on magnetoencephalographic (MEG) signals have been drawing increasing attention in the neuroscience community. This study explores the idea of using source-based magnitude-squared spectral coherence as a spatial indicator for effective regions of in...

Full description

Published in:	Sensors
ISSN:	1424-8220
Published:	MDPI AG 2021
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa58109
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2021-09-27T15:19:07Z
last_indexed	2023-01-11T14:38:28Z
id	cronfa58109
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2022-10-31T13:44:36.3421405</datestamp><bib-version>v2</bib-version><id>58109</id><entry>2021-09-27</entry><title>Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers</title><swanseaauthors><author><sid>81dc663ca0e68c60908d35b1d2ec3a9b</sid><ORCID>0000-0002-6618-7483</ORCID><firstname>Scott</firstname><surname>Yang</surname><name>Scott Yang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-09-27</date><deptcode>SCS</deptcode><abstract>Studies on developing effective neuromarkers based on magnetoencephalographic (MEG) signals have been drawing increasing attention in the neuroscience community. This study explores the idea of using source-based magnitude-squared spectral coherence as a spatial indicator for effective regions of interest (ROIs) localization, subsequently discriminating the participants with mild cognitive impairment (MCI) from a group of age-matched healthy control (HC) elderly participants. We found that the cortical regions could be divided into two distinctive groups based on their coherence indices. Compared to HC, some ROIs showed increased connectivity (hyper-connected ROIs) for MCI participants, whereas the remaining ROIs demonstrated reduced connectivity (hypo-connected ROIs). Based on these findings, a series of wavelet-based source-level neuromarkers for MCI detection are proposed and explored, with respect to the two distinctive ROI groups. It was found that the neuromarkers extracted from the hyper-connected ROIs performed significantly better for MCI detection than those from the hypo-connected ROIs. The neuromarkers were classified using support vector machine (SVM) and k-NN classifiers and evaluated through Monte Carlo cross-validation. An average recognition rate of 93.83% was obtained using source-reconstructed signals from the hyper-connected ROI group. To better conform to clinical practice settings, a leave-one-out cross-validation (LOOCV) approach was also employed to ensure that the data for testing was from a participant that the classifier has never seen. Using LOOCV, we found the best average classification accuracy was reduced to 83.80% using the same set of neuromarkers obtained from the ROI group with functional hyper-connections. This performance surpassed the results reported using wavelet-based features by approximately 15%. Overall, our work suggests that (1) certain ROIs are particularly effective for MCI detection, especially when multi-resolution wavelet biomarkers are employed for such diagnosis; (2) there exists a significant performance difference in system evaluation between research-based experimental design and clinically accepted evaluation standards.</abstract><type>Journal Article</type><journal>Sensors</journal><volume>21</volume><journalNumber>18</journalNumber><paginationStart>6210</paginationStart><paginationEnd/><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1424-8220</issnElectronic><keywords>MEG; connectivity coherence; wavelet-based neuromarker; hyperconnectivity; hypoconnectivity; MCI detection</keywords><publishedDay>16</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-09-16</publishedDate><doi>10.3390/s21186210</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This work was supported by the Northern Ireland Functional Brain Mapping Project Facility (1303/101154803), funded by Invest Northern Ireland and the University of Ulster, Alzheimer’s Research UK (ARUK) NI Pump Priming, EU’s INTERREG VA Programme, managed by the Special EU Programs Body (SEUPB), Ulster University Research Challenge Fund, and the COST Action Open Multiscale Systems Medicine (OpenMultiMed) supported by COST (European Cooperation in Science and Technology)</funders><projectreference/><lastEdited>2022-10-31T13:44:36.3421405</lastEdited><Created>2021-09-27T16:17:31.8154999</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Scott</firstname><surname>Yang</surname><orcid>0000-0002-6618-7483</orcid><order>1</order></author><author><firstname>Jose Miguel Sanchez</firstname><surname>Bornot</surname><order>2</order></author><author><firstname>Ricardo Bruña</firstname><surname>Fernandez</surname><order>3</order></author><author><firstname>Farzin</firstname><surname>Deravi</surname><order>4</order></author><author><firstname>Sanaul</firstname><surname>Hoque</surname><order>5</order></author><author><firstname>KongFatt</firstname><surname>Wong-Lin</surname><order>6</order></author><author><firstname>Girijesh</firstname><surname>Prasad</surname><order>7</order></author></authors><documents><document><filename>58109__21017__365e8f20b65943a19692d8a8743ecb16.pdf</filename><originalFilename>58109.pdf</originalFilename><uploaded>2021-09-27T16:18:58.8370948</uploaded><type>Output</type><contentLength>2349406</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2021 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2022-10-31T13:44:36.3421405 v2 58109 2021-09-27 Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers 81dc663ca0e68c60908d35b1d2ec3a9b 0000-0002-6618-7483 Scott Yang Scott Yang true false 2021-09-27 SCS Studies on developing effective neuromarkers based on magnetoencephalographic (MEG) signals have been drawing increasing attention in the neuroscience community. This study explores the idea of using source-based magnitude-squared spectral coherence as a spatial indicator for effective regions of interest (ROIs) localization, subsequently discriminating the participants with mild cognitive impairment (MCI) from a group of age-matched healthy control (HC) elderly participants. We found that the cortical regions could be divided into two distinctive groups based on their coherence indices. Compared to HC, some ROIs showed increased connectivity (hyper-connected ROIs) for MCI participants, whereas the remaining ROIs demonstrated reduced connectivity (hypo-connected ROIs). Based on these findings, a series of wavelet-based source-level neuromarkers for MCI detection are proposed and explored, with respect to the two distinctive ROI groups. It was found that the neuromarkers extracted from the hyper-connected ROIs performed significantly better for MCI detection than those from the hypo-connected ROIs. The neuromarkers were classified using support vector machine (SVM) and k-NN classifiers and evaluated through Monte Carlo cross-validation. An average recognition rate of 93.83% was obtained using source-reconstructed signals from the hyper-connected ROI group. To better conform to clinical practice settings, a leave-one-out cross-validation (LOOCV) approach was also employed to ensure that the data for testing was from a participant that the classifier has never seen. Using LOOCV, we found the best average classification accuracy was reduced to 83.80% using the same set of neuromarkers obtained from the ROI group with functional hyper-connections. This performance surpassed the results reported using wavelet-based features by approximately 15%. Overall, our work suggests that (1) certain ROIs are particularly effective for MCI detection, especially when multi-resolution wavelet biomarkers are employed for such diagnosis; (2) there exists a significant performance difference in system evaluation between research-based experimental design and clinically accepted evaluation standards. Journal Article Sensors 21 18 6210 MDPI AG 1424-8220 MEG; connectivity coherence; wavelet-based neuromarker; hyperconnectivity; hypoconnectivity; MCI detection 16 9 2021 2021-09-16 10.3390/s21186210 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University This work was supported by the Northern Ireland Functional Brain Mapping Project Facility (1303/101154803), funded by Invest Northern Ireland and the University of Ulster, Alzheimer’s Research UK (ARUK) NI Pump Priming, EU’s INTERREG VA Programme, managed by the Special EU Programs Body (SEUPB), Ulster University Research Challenge Fund, and the COST Action Open Multiscale Systems Medicine (OpenMultiMed) supported by COST (European Cooperation in Science and Technology) 2022-10-31T13:44:36.3421405 2021-09-27T16:17:31.8154999 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Scott Yang 0000-0002-6618-7483 1 Jose Miguel Sanchez Bornot 2 Ricardo Bruña Fernandez 3 Farzin Deravi 4 Sanaul Hoque 5 KongFatt Wong-Lin 6 Girijesh Prasad 7 58109__21017__365e8f20b65943a19692d8a8743ecb16.pdf 58109.pdf 2021-09-27T16:18:58.8370948 Output 2349406 application/pdf Version of Record true © 2021 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license true eng https://creativecommons.org/licenses/by/4.0/
title	Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers
spellingShingle	Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers Scott Yang
title_short	Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers
title_full	Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers
title_fullStr	Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers
title_full_unstemmed	Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers
title_sort	Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers
author_id_str_mv	81dc663ca0e68c60908d35b1d2ec3a9b
author_id_fullname_str_mv	81dc663ca0e68c60908d35b1d2ec3a9b_***_Scott Yang
author	Scott Yang
author2	Scott Yang Jose Miguel Sanchez Bornot Ricardo Bruña Fernandez Farzin Deravi Sanaul Hoque KongFatt Wong-Lin Girijesh Prasad
format	Journal article
container_title	Sensors
container_volume	21
container_issue	18
container_start_page	6210
publishDate	2021
institution	Swansea University
issn	1424-8220
doi_str_mv	10.3390/s21186210
publisher	MDPI AG
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str	1
active_str	0
description	Studies on developing effective neuromarkers based on magnetoencephalographic (MEG) signals have been drawing increasing attention in the neuroscience community. This study explores the idea of using source-based magnitude-squared spectral coherence as a spatial indicator for effective regions of interest (ROIs) localization, subsequently discriminating the participants with mild cognitive impairment (MCI) from a group of age-matched healthy control (HC) elderly participants. We found that the cortical regions could be divided into two distinctive groups based on their coherence indices. Compared to HC, some ROIs showed increased connectivity (hyper-connected ROIs) for MCI participants, whereas the remaining ROIs demonstrated reduced connectivity (hypo-connected ROIs). Based on these findings, a series of wavelet-based source-level neuromarkers for MCI detection are proposed and explored, with respect to the two distinctive ROI groups. It was found that the neuromarkers extracted from the hyper-connected ROIs performed significantly better for MCI detection than those from the hypo-connected ROIs. The neuromarkers were classified using support vector machine (SVM) and k-NN classifiers and evaluated through Monte Carlo cross-validation. An average recognition rate of 93.83% was obtained using source-reconstructed signals from the hyper-connected ROI group. To better conform to clinical practice settings, a leave-one-out cross-validation (LOOCV) approach was also employed to ensure that the data for testing was from a participant that the classifier has never seen. Using LOOCV, we found the best average classification accuracy was reduced to 83.80% using the same set of neuromarkers obtained from the ROI group with functional hyper-connections. This performance surpassed the results reported using wavelet-based features by approximately 15%. Overall, our work suggests that (1) certain ROIs are particularly effective for MCI detection, especially when multi-resolution wavelet biomarkers are employed for such diagnosis; (2) there exists a significant performance difference in system evaluation between research-based experimental design and clinically accepted evaluation standards.
published_date	2021-09-16T04:14:22Z
_version_	1763753970912722944
score	11.012678

Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers

Similar Items