Diagnosis of Alzheimer’s Disease with Extreme Learning Machine on Whole-Brain Functional Connectivity

The analysis of human brain fMRI subjects can research neuro-related diseases and explore the related rules of human brain activity. In this paper, we proposed an algorithm framework to analyze the functional connectivity network of the whole brain and to distinguish Alzheimer’s disease (AD), mild c...

Full description

Saved in:
Bibliographic Details
Published in:Concepts in magnetic resonance. Part B, Magnetic resonance engineering Vol. 2022; pp. 1 - 14
Main Authors: Lu, Jia, Zeng, Weiming, Zhang, Lu, Shi, Yuhu
Format: Journal Article
Language:English
Published: Hindawi 19.05.2022
John Wiley & Sons, Inc
Subjects:
ISSN:1552-5031, 1552-504X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The analysis of human brain fMRI subjects can research neuro-related diseases and explore the related rules of human brain activity. In this paper, we proposed an algorithm framework to analyze the functional connectivity network of the whole brain and to distinguish Alzheimer’s disease (AD), mild cognitive impairment (MCI), and cognitively normal (CN). In other studies, they use algorithms to select features or extract abstract features, or even manually select features based on prior information. Then, a classifier is constructed to classify the selected features. We designed a concise algorithm framework that uses whole-brain functional connectivity for classification without feature selection. The algorithm framework is a two-hidden-layer neural network based on extreme learning machine (ELM), which overcomes the instability of classical ELM in high-dimensional data scenarios. We use this method to conduct experiments for AD, MCI, and CN data and perform 10-fold cross-validation. We found that it has several advantages: (1) the proposed method has excellent classification accuracy with high speed. The classification accuracy of AD vs. CN is 96.85%, and the accuracy of MCI vs. CN is 95.05%. Their AUC (area under curve) of ROC (receiver operating characteristic curve) reached 0.9891 and 0.9888, respectively. Their sensitivities are 97.1% and 94.7%, and specificities are 96.3% and 95.3%, respectively. (2) Compared with other studies, the proposed method is concise. Construction of a two-hidden-layer neural network is to learn features of the whole brain for the diagnosis of AD and MCI, without the feature screening. It avoids the negative effects of feature screening by algorithm or prior information. (3) The proposed method is suitable for small sample and high-dimensional data. It meets the requirements of medical image analysis. In other studies, its classifiers usually deal with several to dozens of feature dimensions. The proposed method deals with 4005 feature dimensions.
AbstractList The analysis of human brain fMRI subjects can research neuro-related diseases and explore the related rules of human brain activity. In this paper, we proposed an algorithm framework to analyze the functional connectivity network of the whole brain and to distinguish Alzheimer’s disease (AD), mild cognitive impairment (MCI), and cognitively normal (CN). In other studies, they use algorithms to select features or extract abstract features, or even manually select features based on prior information. Then, a classifier is constructed to classify the selected features. We designed a concise algorithm framework that uses whole-brain functional connectivity for classification without feature selection. The algorithm framework is a two-hidden-layer neural network based on extreme learning machine (ELM), which overcomes the instability of classical ELM in high-dimensional data scenarios. We use this method to conduct experiments for AD, MCI, and CN data and perform 10-fold cross-validation. We found that it has several advantages: (1) the proposed method has excellent classification accuracy with high speed. The classification accuracy of AD vs. CN is 96.85%, and the accuracy of MCI vs. CN is 95.05%. Their AUC (area under curve) of ROC (receiver operating characteristic curve) reached 0.9891 and 0.9888, respectively. Their sensitivities are 97.1% and 94.7%, and specificities are 96.3% and 95.3%, respectively. (2) Compared with other studies, the proposed method is concise. Construction of a two-hidden-layer neural network is to learn features of the whole brain for the diagnosis of AD and MCI, without the feature screening. It avoids the negative effects of feature screening by algorithm or prior information. (3) The proposed method is suitable for small sample and high-dimensional data. It meets the requirements of medical image analysis. In other studies, its classifiers usually deal with several to dozens of feature dimensions. The proposed method deals with 4005 feature dimensions.
Audience Academic
Author Lu, Jia
Zeng, Weiming
Zhang, Lu
Shi, Yuhu
Author_xml – sequence: 1
  givenname: Jia
  orcidid: 0000-0002-2461-8935
  surname: Lu
  fullname: Lu, Jia
  organization: Laboratory of Digital Image and Intelligent ComputationShanghai Maritime University1550 Harbor AvenuePudongShanghai 201306Chinashmtu.edu.cn
– sequence: 2
  givenname: Weiming
  orcidid: 0000-0002-9035-8078
  surname: Zeng
  fullname: Zeng, Weiming
  organization: Laboratory of Digital Image and Intelligent ComputationShanghai Maritime University1550 Harbor AvenuePudongShanghai 201306Chinashmtu.edu.cn
– sequence: 3
  givenname: Lu
  orcidid: 0000-0003-4573-9530
  surname: Zhang
  fullname: Zhang, Lu
  organization: Basic Experiment and Training CenterShanghai Maritime University1550 Harbor AvenuePudongShanghai 201306Chinashmtu.edu.cn
– sequence: 4
  givenname: Yuhu
  orcidid: 0000-0002-4009-2849
  surname: Shi
  fullname: Shi, Yuhu
  organization: College of Information EngineeringShanghai Maritime University1550 Harbor AvenuePudongShanghai 201306Chinashmtu.edu.cn
BookMark eNp9kctKxDAUhoMoeN35AAGXWk3StJ0uxxlvMOJG0V1J05OZI20iSb2ufA1fzycxw4igqGSR5PB9B87518mydRYI2eZsn_MsOxBMiAPOZJHzfImsxZJIMiZvlr_eKV8l6yHcMiYGZc7WyHSMampdwECdocP2ZQbYgX9_fQt0jAFUAPqI_YwePfUeOqATUN6indJzpWdogTpLr2euheTQK7T0-N7qHp1VLR05ayF-HrB_3iQrRrUBtj7vDXJ1fHQ5Ok0mFydno-Ek0WmR90mTCaibWqdpmQ4yNmBSgWhMUee15lLUAy5NmQrTgFIpK1ijpQHBRS0ZF5I36QbZWfSdqhYqtMb1XukOg66GBZdc8FKWkdr_hYqngQ51XKrBWP8miIWgvQvBg6k09mo-ZxSxrTir5glU8wSqzwSitPdDuvPYKf_8F767wONaG_WI_9MfEnOV5A
CitedBy_id crossref_primary_10_1016_j_ijleo_2022_170212
crossref_primary_10_3389_fmed_2024_1412592
crossref_primary_10_7717_peerj_cs_2302
crossref_primary_10_1016_j_eswa_2024_124780
Cites_doi 10.1002/hbm.22156
10.1002/hbm.22353
10.1109/IJCNN.2004.1380068
10.1109/TCYB.2015.2512852
10.1006/nimg.2001.0978
10.1016/j.neucom.2007.10.008
10.1007/s13042-011-0019-y
10.1155/2020/8813738
10.1109/tsmcb.2011.2168604
10.1371/journal.pone.0212582
10.1016/j.neucom.2007.02.009
10.1016/j.neuroimage.2009.10.003
10.1109/tgrs.2014.2335751
10.1159/000354370
10.1016/j.neunet.2012.04.002
10.1016/j.clinph.2015.02.060
10.1109/72.655045
10.1016/j.neucom.2005.12.126
10.3389/fninf.2018.00060
10.1016/j.jalz.2018.02.001
10.1109/TCYB.2016.2533424
10.1001/archneur.58.3.397
10.3389/fnins.2021.605115
10.1007/s12559-019-09688-2
10.1016/j.neunet.2016.12.002
10.1016/j.neunet.2015.04.002
10.1001/archneurol.2009.266
ContentType Journal Article
Copyright Copyright © 2022 Jia Lu et al.
COPYRIGHT 2022 John Wiley & Sons, Inc.
Copyright_xml – notice: Copyright © 2022 Jia Lu et al.
– notice: COPYRIGHT 2022 John Wiley & Sons, Inc.
DBID RHU
RHW
RHX
AAYXX
CITATION
DOI 10.1155/2022/1047616
DatabaseName Hindawi Publishing Complete
Hindawi Publishing Subscription Journals
Hindawi Publishing Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef


Database_xml – sequence: 1
  dbid: RHX
  name: Hindawi Publishing Open Access
  url: http://www.hindawi.com/journals/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 1552-504X
Editor Leupold, Jochen
Editor_xml – sequence: 1
  givenname: Jochen
  surname: Leupold
  fullname: Leupold, Jochen
EndPage 14
ExternalDocumentID A714121949
10_1155_2022_1047616
GrantInformation_xml – fundername: Shanghai Sailing Program
  grantid: 19YF1419000
– fundername: National Natural Science Foundation of China
  grantid: 31870979; 61906117
GroupedDBID .3N
.GA
05W
0R~
10A
1L6
1OC
33P
4.4
50Z
51W
51X
52M
52N
52O
52P
52R
52S
52T
52W
52X
5GY
5VS
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A01
A03
AAESR
AAEVG
AAJEY
AAONW
AAZKR
ABCQN
ABEML
ABIJN
ACGFS
ACIWK
ACMXC
ACSCC
ADBBV
ADEOM
ADIZJ
AEIMD
AEUQT
AFBPY
AFPWT
AFZJQ
ALMA_UNASSIGNED_HOLDINGS
AMBMR
ATUGU
AZBYB
AZVAB
BAFTC
BHBCM
BRXPI
BY8
CS3
D-6
D-7
D-E
D-F
DCZOG
DPXWK
DR2
EBS
F00
F01
F04
F5P
G-S
GNP
GODZA
GROUPED_DOAJ
H.X
HBH
HHZ
HZ~
IAO
ICD
IX1
J0M
KQQ
LAW
LC2
LC3
LITHE
LOXES
LP6
LP7
LUTES
MK4
MSFUL
MSMAN
MSSTM
N04
N05
NF~
O66
O9-
OK1
P2P
P2W
P2X
P2Z
P4B
P4D
Q.N
Q11
QB0
RHU
RHW
RHX
RWI
RYL
SUPJJ
UB1
W8V
W99
WBKPD
WHWMO
WIH
WIJ
WJL
WOHZO
WQJ
WRC
WVDHM
WXI
XG1
XHW
XV2
~WT
24P
AAYXX
ACCMX
CITATION
ITC
O8X
ID FETCH-LOGICAL-c376t-d52ebdbc3393850804ae2df7b6bc142b814f932fdeaa3070dc4fe212b401241d3
IEDL.DBID RHX
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000805121800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1552-5031
IngestDate Sat Nov 29 13:53:24 EST 2025
Sat Nov 29 10:32:52 EST 2025
Sat Nov 29 03:43:46 EST 2025
Tue Nov 18 21:51:55 EST 2025
Sun Jun 02 19:21:13 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
https://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c376t-d52ebdbc3393850804ae2df7b6bc142b814f932fdeaa3070dc4fe212b401241d3
ORCID 0000-0002-4009-2849
0000-0002-2461-8935
0000-0002-9035-8078
0000-0003-4573-9530
OpenAccessLink https://dx.doi.org/10.1155/2022/1047616
PageCount 14
ParticipantIDs gale_infotracmisc_A714121949
gale_infotracacademiconefile_A714121949
crossref_citationtrail_10_1155_2022_1047616
crossref_primary_10_1155_2022_1047616
hindawi_primary_10_1155_2022_1047616
PublicationCentury 2000
PublicationDate 2022-05-19
PublicationDateYYYYMMDD 2022-05-19
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-05-19
  day: 19
PublicationDecade 2020
PublicationTitle Concepts in magnetic resonance. Part B, Magnetic resonance engineering
PublicationYear 2022
Publisher Hindawi
John Wiley & Sons, Inc
Publisher_xml – name: Hindawi
– name: John Wiley & Sons, Inc
References 22
23
24
25
26
27
10
11
12
13
14
15
16
17
18
19
1
2
3
4
5
6
7
8
9
20
21
References_xml – ident: 14
  doi: 10.1002/hbm.22156
– ident: 15
  doi: 10.1002/hbm.22353
– ident: 5
  doi: 10.1109/IJCNN.2004.1380068
– ident: 8
  doi: 10.1109/TCYB.2015.2512852
– ident: 22
  doi: 10.1006/nimg.2001.0978
– ident: 25
  doi: 10.1016/j.neucom.2007.10.008
– ident: 24
  doi: 10.1007/s13042-011-0019-y
– ident: 19
  doi: 10.1155/2020/8813738
– ident: 10
  doi: 10.1109/tsmcb.2011.2168604
– ident: 17
  doi: 10.1371/journal.pone.0212582
– ident: 9
  doi: 10.1016/j.neucom.2007.02.009
– ident: 21
  doi: 10.1016/j.neuroimage.2009.10.003
– ident: 13
  doi: 10.1109/tgrs.2014.2335751
– ident: 4
  doi: 10.1159/000354370
– ident: 11
  doi: 10.1016/j.neunet.2012.04.002
– ident: 16
  doi: 10.1016/j.clinph.2015.02.060
– ident: 23
  doi: 10.1109/72.655045
– ident: 26
  doi: 10.1016/j.neucom.2005.12.126
– ident: 27
  doi: 10.3389/fninf.2018.00060
– ident: 1
  doi: 10.1016/j.jalz.2018.02.001
– ident: 7
  doi: 10.1109/TCYB.2016.2533424
– ident: 2
  doi: 10.1001/archneur.58.3.397
– ident: 20
  doi: 10.3389/fnins.2021.605115
– ident: 18
  doi: 10.1007/s12559-019-09688-2
– ident: 12
  doi: 10.1016/j.neunet.2016.12.002
– ident: 6
  doi: 10.1016/j.neunet.2015.04.002
– ident: 3
  doi: 10.1001/archneurol.2009.266
SSID ssj0028960
Score 2.2807055
Snippet The analysis of human brain fMRI subjects can research neuro-related diseases and explore the related rules of human brain activity. In this paper, we proposed...
SourceID gale
crossref
hindawi
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Advertising executives
Algorithms
Alzheimer's disease
Brain
Medical imaging equipment
Medical research
Medicine, Experimental
Neural networks
Title Diagnosis of Alzheimer’s Disease with Extreme Learning Machine on Whole-Brain Functional Connectivity
URI https://dx.doi.org/10.1155/2022/1047616
Volume 2022
WOSCitedRecordID wos000805121800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1552-504X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0028960
  issn: 1552-5031
  databaseCode: 24P
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LSwMxEB5sUfAiPrFaSw4VD7LYbJPt7rHall6UIoq9Ldk8tFBb6dYHnvwb_j1_iZndtFhF8bjs7IPJJF--ZPINQFVwJB2Ke8rCnccaCfNCwYVXC4zh2q8jJGfFJhoXF2G_H_WcSFL6cwvfoh3Sc_8EFQUCGhSgEHIM3stuf86rwig_DMy55VU2SGf57d-eXUAeN_6u3CHzfR58wZTOOqy5ySBp5q23AUt6tAkrWVKmTLfgtpXnwQ1SMjakOXy904N7Pfl4e09JK99YIbiOStovU1zmI04s9ZacZymSmoxH5AYL4HqnWAmCdCyI5Wt_JEtwkXnpiG247rSvzrqeK4zgSTseTD3FfZ2oRFpP1kM7w6oxoX1lGkmQSMr8JKTM2HmZUVoI7NNKMqMtRiWWTFnEVvUdKI7GI70LpMYVKgIGkTKKyYAKKrRJQiGpZFSoWgmOZ06LpVMNx-IVwzhjD5zH6OLYubgEh3Prh1wt4xe7I_R_jJ3Ivk0KdxbA_hPKUcXNBmXUjqUsKkF5wdIGv1y4XXUt-Of39v5ntg-reInJATQqQ3E6edQHsCyfpoN0UoGCz3qVLPQ-Adf3z7A
linkProvider Hindawi Publishing
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Diagnosis+of+Alzheimer%E2%80%99s+Disease+with+Extreme+Learning+Machine+on+Whole-Brain+Functional+Connectivity&rft.jtitle=Concepts+in+magnetic+resonance.+Part+B%2C+Magnetic+resonance+engineering&rft.au=Lu%2C+Jia&rft.au=Zeng%2C+Weiming&rft.au=Zhang%2C+Lu&rft.au=Shi%2C+Yuhu&rft.date=2022-05-19&rft.pub=Hindawi&rft.issn=1552-5031&rft.eissn=1552-504X&rft.volume=2022&rft_id=info:doi/10.1155%2F2022%2F1047616&rft.externalDocID=10_1155_2022_1047616
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1552-5031&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1552-5031&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1552-5031&client=summon