Using graph convolutional network to characterize individuals with major depressive disorder across multiple imaging sites

Establishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive disorder (MDD). However, most previous studies using machine learning to identify MDD were based on small sample size and did not account for the brain c...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:EBioMedicine Ročník 78; s. 103977
Hlavní autori: Qin, Kun, Lei, Du, Pinaya, Walter H.L., Pan, Nanfang, Li, Wenbin, Zhu, Ziyu, Sweeney, John A., Mechelli, Andrea, Gong, Qiyong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Netherlands Elsevier B.V 01.04.2022
Elsevier
Predmet:
ISSN:2352-3964, 2352-3964
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Establishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive disorder (MDD). However, most previous studies using machine learning to identify MDD were based on small sample size and did not account for the brain connectome that is associated with the pathophysiology of MDD. Here, we addressed these limitations by applying graph convolutional network (GCN) in a large multi-site MDD dataset. Resting-state functional MRI scans of 1586 participants (821 MDD vs. 765 controls) across 16 sites of Rest-meta-MDD consortium were collected. GCN model was trained with individual whole-brain functional network to identify MDD patients from controls, characterize the most salient regions contributing to classification, and explore the relationship between topological characteristics of salient regions and clinical measures. GCN achieved an accuracy of 81·5% (95%CI: 80·5–82·5%, AUC: 0·865), which was higher than other common machine learning classifiers. The most salient regions contributing to classification were primarily identified within the default mode, fronto-parietal, and cingulo-opercular networks. Nodal topologies of the left inferior parietal lobule and left dorsolateral prefrontal cortex were associated with depressive severity and illness duration, respectively. These findings based on a large, multi-site dataset support the feasibility and effectiveness of GCN in characterizing MDD, and also illustrate the potential utility of GCN for enhancing understanding of the neurobiology of MDD by detecting clinically-relevant disruption in functional network topology. This study was supported by the National Natural Science Foundation of China (Grant Nos. 81621003, 82027808, 81820108018).
AbstractList Establishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive disorder (MDD). However, most previous studies using machine learning to identify MDD were based on small sample size and did not account for the brain connectome that is associated with the pathophysiology of MDD. Here, we addressed these limitations by applying graph convolutional network (GCN) in a large multi-site MDD dataset.BACKGROUNDEstablishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive disorder (MDD). However, most previous studies using machine learning to identify MDD were based on small sample size and did not account for the brain connectome that is associated with the pathophysiology of MDD. Here, we addressed these limitations by applying graph convolutional network (GCN) in a large multi-site MDD dataset.Resting-state functional MRI scans of 1586 participants (821 MDD vs. 765 controls) across 16 sites of Rest-meta-MDD consortium were collected. GCN model was trained with individual whole-brain functional network to identify MDD patients from controls, characterize the most salient regions contributing to classification, and explore the relationship between topological characteristics of salient regions and clinical measures.METHODSResting-state functional MRI scans of 1586 participants (821 MDD vs. 765 controls) across 16 sites of Rest-meta-MDD consortium were collected. GCN model was trained with individual whole-brain functional network to identify MDD patients from controls, characterize the most salient regions contributing to classification, and explore the relationship between topological characteristics of salient regions and clinical measures.GCN achieved an accuracy of 81·5% (95%CI: 80·5-82·5%, AUC: 0·865), which was higher than other common machine learning classifiers. The most salient regions contributing to classification were primarily identified within the default mode, fronto-parietal, and cingulo-opercular networks. Nodal topologies of the left inferior parietal lobule and left dorsolateral prefrontal cortex were associated with depressive severity and illness duration, respectively.FINDINGSGCN achieved an accuracy of 81·5% (95%CI: 80·5-82·5%, AUC: 0·865), which was higher than other common machine learning classifiers. The most salient regions contributing to classification were primarily identified within the default mode, fronto-parietal, and cingulo-opercular networks. Nodal topologies of the left inferior parietal lobule and left dorsolateral prefrontal cortex were associated with depressive severity and illness duration, respectively.These findings based on a large, multi-site dataset support the feasibility and effectiveness of GCN in characterizing MDD, and also illustrate the potential utility of GCN for enhancing understanding of the neurobiology of MDD by detecting clinically-relevant disruption in functional network topology.INTERPRETATIONThese findings based on a large, multi-site dataset support the feasibility and effectiveness of GCN in characterizing MDD, and also illustrate the potential utility of GCN for enhancing understanding of the neurobiology of MDD by detecting clinically-relevant disruption in functional network topology.This study was supported by the National Natural Science Foundation of China (Grant Nos. 81621003, 82027808, 81820108018).FUNDINGThis study was supported by the National Natural Science Foundation of China (Grant Nos. 81621003, 82027808, 81820108018).
SummaryBackgroundEstablishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive disorder (MDD). However, most previous studies using machine learning to identify MDD were based on small sample size and did not account for the brain connectome that is associated with the pathophysiology of MDD. Here, we addressed these limitations by applying graph convolutional network (GCN) in a large multi-site MDD dataset. MethodsResting-state functional MRI scans of 1586 participants (821 MDD vs. 765 controls) across 16 sites of Rest-meta-MDD consortium were collected. GCN model was trained with individual whole-brain functional network to identify MDD patients from controls, characterize the most salient regions contributing to classification, and explore the relationship between topological characteristics of salient regions and clinical measures. FindingsGCN achieved an accuracy of 81·5% (95%CI: 80·5–82·5%, AUC: 0·865), which was higher than other common machine learning classifiers. The most salient regions contributing to classification were primarily identified within the default mode, fronto-parietal, and cingulo-opercular networks. Nodal topologies of the left inferior parietal lobule and left dorsolateral prefrontal cortex were associated with depressive severity and illness duration, respectively. InterpretationThese findings based on a large, multi-site dataset support the feasibility and effectiveness of GCN in characterizing MDD, and also illustrate the potential utility of GCN for enhancing understanding of the neurobiology of MDD by detecting clinically-relevant disruption in functional network topology. FundingThis study was supported by the National Natural Science Foundation of China (Grant Nos. 81621003, 82027808, 81820108018).
Background: Establishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive disorder (MDD). However, most previous studies using machine learning to identify MDD were based on small sample size and did not account for the brain connectome that is associated with the pathophysiology of MDD. Here, we addressed these limitations by applying graph convolutional network (GCN) in a large multi-site MDD dataset. Methods: Resting-state functional MRI scans of 1586 participants (821 MDD vs. 765 controls) across 16 sites of Rest-meta-MDD consortium were collected. GCN model was trained with individual whole-brain functional network to identify MDD patients from controls, characterize the most salient regions contributing to classification, and explore the relationship between topological characteristics of salient regions and clinical measures. Findings: GCN achieved an accuracy of 81·5% (95%CI: 80·5–82·5%, AUC: 0·865), which was higher than other common machine learning classifiers. The most salient regions contributing to classification were primarily identified within the default mode, fronto-parietal, and cingulo-opercular networks. Nodal topologies of the left inferior parietal lobule and left dorsolateral prefrontal cortex were associated with depressive severity and illness duration, respectively. Interpretation: These findings based on a large, multi-site dataset support the feasibility and effectiveness of GCN in characterizing MDD, and also illustrate the potential utility of GCN for enhancing understanding of the neurobiology of MDD by detecting clinically-relevant disruption in functional network topology. Funding: This study was supported by the National Natural Science Foundation of China (Grant Nos. 81621003, 82027808, 81820108018).
Establishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive disorder (MDD). However, most previous studies using machine learning to identify MDD were based on small sample size and did not account for the brain connectome that is associated with the pathophysiology of MDD. Here, we addressed these limitations by applying graph convolutional network (GCN) in a large multi-site MDD dataset. Resting-state functional MRI scans of 1586 participants (821 MDD vs. 765 controls) across 16 sites of Rest-meta-MDD consortium were collected. GCN model was trained with individual whole-brain functional network to identify MDD patients from controls, characterize the most salient regions contributing to classification, and explore the relationship between topological characteristics of salient regions and clinical measures. GCN achieved an accuracy of 81·5% (95%CI: 80·5-82·5%, AUC: 0·865), which was higher than other common machine learning classifiers. The most salient regions contributing to classification were primarily identified within the default mode, fronto-parietal, and cingulo-opercular networks. Nodal topologies of the left inferior parietal lobule and left dorsolateral prefrontal cortex were associated with depressive severity and illness duration, respectively. These findings based on a large, multi-site dataset support the feasibility and effectiveness of GCN in characterizing MDD, and also illustrate the potential utility of GCN for enhancing understanding of the neurobiology of MDD by detecting clinically-relevant disruption in functional network topology. This study was supported by the National Natural Science Foundation of China (Grant Nos. 81621003, 82027808, 81820108018).
ArticleNumber 103977
Author Pan, Nanfang
Zhu, Ziyu
Qin, Kun
Pinaya, Walter H.L.
Gong, Qiyong
Lei, Du
Li, Wenbin
Sweeney, John A.
Mechelli, Andrea
Author_xml – sequence: 1
  givenname: Kun
  surname: Qin
  fullname: Qin, Kun
  organization: Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
– sequence: 2
  givenname: Du
  surname: Lei
  fullname: Lei, Du
  organization: Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, OH, USA
– sequence: 3
  givenname: Walter H.L.
  surname: Pinaya
  fullname: Pinaya, Walter H.L.
  organization: Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
– sequence: 4
  givenname: Nanfang
  orcidid: 0000-0002-5651-556X
  surname: Pan
  fullname: Pan, Nanfang
  organization: Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
– sequence: 5
  givenname: Wenbin
  surname: Li
  fullname: Li, Wenbin
  organization: Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
– sequence: 6
  givenname: Ziyu
  surname: Zhu
  fullname: Zhu, Ziyu
  organization: Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
– sequence: 7
  givenname: John A.
  surname: Sweeney
  fullname: Sweeney, John A.
  organization: Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
– sequence: 8
  givenname: Andrea
  surname: Mechelli
  fullname: Mechelli, Andrea
  organization: Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King's College London, De Crespigny Park, London, UK
– sequence: 9
  givenname: Qiyong
  orcidid: 0000-0002-5912-4871
  surname: Gong
  fullname: Gong, Qiyong
  email: qiyonggong@hmrrc.org.cn
  organization: Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35367775$$D View this record in MEDLINE/PubMed
BookMark eNqFkk9r3DAQxU1JadI0n6BQdOxlt7IkyxalgRL6JxDooQ30JmRpvCtHtraSvCH59JV305AESk4So3m_J2be6-Jg9CMUxdsSL0tc8g_9ElrrhyXBhOQKFXX9ojgitCILKjg7eHA_LE5i7DHGZcVysXlVHNKK8rquq6Pi9jLacYVWQW3WSPtx692UrB-VQyOkax-uUPJIr1VQOkGwt4DsaOzWmkm5iK5tWqNB9T4gA5sAMdotIGOjDwYCUjr4GNEwuWQ3LksHtZrtok0Q3xQvu8yAk7vzuLj8-uXX2ffFxY9v52efLxaaU5IWdaXbVgMWAAYwZqatBBcNNLzjNSGibIUxRnSUM8Cc1VpxoirRdS00pmIdPS7O91zjVS83IX8i3EivrNwVfFhJFZLVDiRmrM02daMawkQnWlXSWufhlmVTYdxm1umetZnaAYyGMQXlHkEfv4x2LVd-KxvRUEpZBry_AwT_Z4KY5GCjBufUCH6KknDGBcuOPLe-e-h1b_JvebmB7ht2Uw7Q3beUWM4pkb3cpUTOKZH7lGSVeKLSNql55_nD1j2j_bTXQt7X1kKQUVsYNRgbQKc8UPuM_vSJXjs7Wq3cFdxA7P0UcvKiLGUkEsufc4bnCBOS08vL3xnw8f-AZ-3_AhpHBgE
CitedBy_id crossref_primary_10_1016_j_neuroimage_2024_120750
crossref_primary_10_1016_j_bpsc_2025_04_005
crossref_primary_10_1007_s12021_025_09731_8
crossref_primary_10_1093_psyrad_kkaf024
crossref_primary_10_1016_j_psychres_2024_115841
crossref_primary_10_1093_gigascience_giad071
crossref_primary_10_1016_j_bspc_2023_105837
crossref_primary_10_1016_j_ress_2025_110928
crossref_primary_10_1016_j_jad_2024_11_061
crossref_primary_10_1016_j_bbr_2025_115756
crossref_primary_10_1016_j_asoc_2024_111769
crossref_primary_10_1016_j_neubiorev_2025_106201
crossref_primary_10_3389_fnhum_2023_1094592
crossref_primary_10_1016_j_nicl_2022_103082
crossref_primary_10_1109_ACCESS_2025_3581065
crossref_primary_10_1016_j_media_2024_103144
crossref_primary_10_1109_JBHI_2024_3366662
crossref_primary_10_1109_TNSRE_2023_3341923
crossref_primary_10_1111_nyas_15366
crossref_primary_10_1016_j_engappai_2024_109347
crossref_primary_10_3389_fncom_2025_1537284
crossref_primary_10_1155_da_9062022
crossref_primary_10_3390_biomimetics10070415
crossref_primary_10_1016_j_jad_2023_08_034
crossref_primary_10_1109_TSIPN_2025_3577354
crossref_primary_10_1186_s13195_024_01425_8
crossref_primary_10_3389_fpsyt_2023_1125339
crossref_primary_10_1017_S0033291722002173
crossref_primary_10_1016_j_eswa_2025_127984
crossref_primary_10_1016_j_jad_2023_07_077
crossref_primary_10_1016_j_phrs_2023_106984
crossref_primary_10_1016_j_jad_2025_120230
crossref_primary_10_1016_j_biopsych_2025_08_013
crossref_primary_10_1016_j_bspc_2024_107166
crossref_primary_10_1016_j_neuroimage_2025_121422
crossref_primary_10_1016_j_neuroimage_2023_120497
crossref_primary_10_1016_j_inffus_2022_12_010
crossref_primary_10_1109_TAFFC_2024_3401251
crossref_primary_10_1016_j_jad_2024_10_006
crossref_primary_10_1080_07853890_2025_2520394
crossref_primary_10_1016_j_jneumeth_2023_110014
crossref_primary_10_1038_s41598_023_47934_8
crossref_primary_10_1016_j_neuroscience_2024_06_018
crossref_primary_10_1109_TCDS_2024_3390005
crossref_primary_10_1016_j_cpnec_2025_100306
crossref_primary_10_1016_j_compmedimag_2025_102612
crossref_primary_10_1088_1741_2552_ad038b
crossref_primary_10_1109_TMI_2024_3368064
crossref_primary_10_1016_j_bspc_2025_108123
crossref_primary_10_1016_j_neuroscience_2024_12_045
crossref_primary_10_3390_brainsci13101462
crossref_primary_10_1016_j_jad_2025_02_076
crossref_primary_10_1162_netn_a_00451
crossref_primary_10_1016_j_jad_2025_119783
crossref_primary_10_1111_jcpp_13946
crossref_primary_10_1002_hbm_70326
crossref_primary_10_1007_s00429_024_02780_w
crossref_primary_10_1016_j_ajp_2023_103687
crossref_primary_10_1016_j_neucom_2024_128098
crossref_primary_10_1109_JIOT_2023_3281648
crossref_primary_10_1016_j_scib_2024_03_006
crossref_primary_10_1109_TMI_2023_3327283
Cites_doi 10.1038/nrn2575
10.1016/j.tics.2008.01.001
10.1016/j.jad.2016.04.046
10.1016/j.jad.2021.03.031
10.1126/science.1194144
10.1093/biostatistics/kxj037
10.1016/j.media.2018.06.001
10.1016/j.neuroimage.2017.08.047
10.1177/0004867416661426
10.1002/hbm.24863
10.1002/hbm.25175
10.1038/nm.4246
10.1109/TMI.2021.3051604
10.1016/j.jad.2013.12.036
10.1007/s11682-018-0003-1
10.1016/j.neuroimage.2014.04.057
10.1016/j.neuroimage.2017.12.052
10.1016/j.nicl.2018.07.002
10.1148/radiol.2016152149
10.1038/ncomms11254
10.1016/S0140-6736(13)61611-6
10.1016/j.biopsych.2014.08.009
10.1001/jamapsychiatry.2015.0071
10.1016/j.biopsych.2011.10.035
10.1109/MSP.2017.2693418
10.1038/s41380-019-0574-2
10.1002/hbm.24241
10.1073/pnas.1900390116
10.1002/hbm.21252
10.1093/psyrad/kkab009
10.3389/fpsyt.2017.00294
10.1002/mrm.22159
10.1177/0004867419832106
10.1016/j.neubiorev.2017.01.002
10.1038/nrn3901
10.1002/da.22901
10.3389/fpsyt.2016.00050
10.1016/j.neuroimage.2020.116956
10.1186/s12888-021-03211-4
10.1146/annurev-clinpsy-032511-143049
10.1016/j.biopsych.2016.10.028
10.1016/j.neuroimage.2016.09.046
10.1016/j.neuroimage.2007.09.066
10.1016/j.biopsych.2011.05.018
10.1038/s41386-021-01020-7
10.1038/s41380-021-01247-2
10.1016/j.pnpbp.2019.109759
10.1371/journal.pbio.3000966
10.1016/j.neuroimage.2017.11.024
ContentType Journal Article
Copyright 2022 The Author(s)
The Author(s)
Copyright © 2022 The Author(s). Published by Elsevier B.V. All rights reserved.
2022 The Author(s) 2022
Copyright_xml – notice: 2022 The Author(s)
– notice: The Author(s)
– notice: Copyright © 2022 The Author(s). Published by Elsevier B.V. All rights reserved.
– notice: 2022 The Author(s) 2022
DBID 6I.
AAFTH
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
5PM
DOA
DOI 10.1016/j.ebiom.2022.103977
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic


MEDLINE


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 2352-3964
EndPage 103977
ExternalDocumentID oai_doaj_org_article_044beed78a8249f9ba137c397118500b
PMC8983334
35367775
10_1016_j_ebiom_2022_103977
S235239642200161X
1_s2_0_S235239642200161X
Genre Journal Article
GrantInformation This study was supported by the National Natural Science Foundation of China (Grant Nos. 81621003, 82027808, 81820108018).
GroupedDBID .1-
.FO
0R~
4.4
457
53G
5VS
AAEDT
AAEDW
AAIKJ
AALRI
AAMRU
AAXUO
AAYWO
ABMAC
ACGFS
ACVFH
ADBBV
ADCNI
ADEZE
ADRAZ
ADVLN
AEUPX
AEXQZ
AFPUW
AFRHN
AFTJW
AGHFR
AIGII
AITUG
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
AOIJS
APXCP
BCNDV
EBS
EJD
FDB
GROUPED_DOAJ
HYE
HZ~
IPNFZ
KQ8
M41
M48
O9-
OK1
RIG
ROL
RPM
SSZ
Z5R
0SF
6I.
AACTN
AAFTH
AFCTW
NCXOZ
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
5PM
ID FETCH-LOGICAL-c632t-75cbbce09eede004db59698e86f672291b9ddd9f364e0647ca62a59ffbe8d54f3
IEDL.DBID DOA
ISICitedReferencesCount 70
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000795959900011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2352-3964
IngestDate Fri Oct 03 12:43:37 EDT 2025
Tue Nov 04 01:49:35 EST 2025
Fri Sep 05 12:54:19 EDT 2025
Mon Jul 21 05:46:04 EDT 2025
Tue Nov 18 22:37:52 EST 2025
Thu Nov 13 04:17:29 EST 2025
Tue Jul 25 20:58:08 EDT 2023
Tue Feb 25 20:10:19 EST 2025
Tue Aug 26 17:01:11 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Depression
Graph theory
Magnetic resonance imaging
Graph neural network
Multi-site
Language English
License This is an open access article under the CC BY-NC-ND license.
Copyright © 2022 The Author(s). Published by Elsevier B.V. All rights reserved.
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c632t-75cbbce09eede004db59698e86f672291b9ddd9f364e0647ca62a59ffbe8d54f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
These authors contributed equally to this work.
ORCID 0000-0002-5651-556X
0000-0002-5912-4871
OpenAccessLink https://doaj.org/article/044beed78a8249f9ba137c397118500b
PMID 35367775
PQID 2646943976
PQPubID 23479
PageCount 1
ParticipantIDs doaj_primary_oai_doaj_org_article_044beed78a8249f9ba137c397118500b
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8983334
proquest_miscellaneous_2646943976
pubmed_primary_35367775
crossref_primary_10_1016_j_ebiom_2022_103977
crossref_citationtrail_10_1016_j_ebiom_2022_103977
elsevier_sciencedirect_doi_10_1016_j_ebiom_2022_103977
elsevier_clinicalkeyesjournals_1_s2_0_S235239642200161X
elsevier_clinicalkey_doi_10_1016_j_ebiom_2022_103977
PublicationCentury 2000
PublicationDate 2022-04-01
PublicationDateYYYYMMDD 2022-04-01
PublicationDate_xml – month: 04
  year: 2022
  text: 2022-04-01
  day: 01
PublicationDecade 2020
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
PublicationTitle EBioMedicine
PublicationTitleAlternate EBioMedicine
PublicationYear 2022
Publisher Elsevier B.V
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier
References Kawahara, Brown, Miller (bib0037) 2017; 146
Korgaonkar, Goldstein-Piekarski, Fornito, Williams (bib0043) 2020; 25
Drysdale, Grosenick, Downar (bib0050) 2017; 23
Zhang, Wang, Wu (bib0015) 2011; 70
Yan, Chen, Li (bib0021) 2019; 116
Qin, Lei, Yang (bib0051) 2021; 21
Lai, Wu (bib0003) 2014; 160
Fey M., Lenssen J.E. Fast graph representation learning with PyTorch geometric [Internet]. arXiv [preprint]. 2019 [cited 2021 July 29]: arXiv:1903.02428. Available from
Dosenbach, Nardos, Cohen (bib0023) 2010; 329
Yahata, Morimoto, Hashimoto (bib0026) 2016; 7
Yu, Linn, Cook (bib0032) 2018; 39
Fortin, Cullen, Sheline (bib0030) 2018; 167
Lui, Zhou, Sweeney, Gong (bib0002) 2016; 281
Chen, Wang, Niu (bib0006) 2018; 20
Schnack, Kahn (bib0008) 2016; 7
Gong, He (bib0040) 2015; 77
Kostro, Abdulkadir, Durr (bib0027) 2014; 98
Shi, Li, Feng (bib0014) 2020; 97
Flint, Cearns, Opel (bib0010) 2021; 46
.
Radua, Vieta, Shinohara (bib0033) 2020; 218
Godwin, Ji, Kandala, Mamah (bib0052) 2017; 8
Zhu, Wang, Xiao (bib0005) 2012; 71
Bullmore, Sporns (bib0041) 2009; 10
Yang, Chen, Chen (bib0049) 2021; 26
Craddock, Holtzheimer, Hu, Mayberg (bib0038) 2009; 62
Fornito, Zalesky, Breakspear (bib0012) 2015; 16
Whitfield-Gabrieli, Ford (bib0042) 2012; 8
Whiteford, Degenhardt, Rehm (bib0001) 2013; 382
Fortin, Parker, Tunç (bib0031) 2017; 161
Bronstein, Bruna, LeCun, Szlam, Vandergheynst (bib0016) 2017; 34
Gong (bib54) 2020; 30
Zhou, Khosla, Lapedriza, Oliva, Torralba (bib0036) 2016
Dohm, Redlich, Zwitserlood, Dannlowski (bib0048) 2017; 51
Stonnington, Tan, Klöppel (bib0025) 2008; 39
Johnson, Li, Rabinovic (bib0029) 2007; 8
Tomasi, Volkow (bib0024) 2012; 33
Li, Sun, Biswal, Sweeney, Gong (bib53) 2021; 1
Arslan, Ktena, Glocker, Rueckert (bib0034) 2018
Yao, Fu, Wu (bib0004) 2020; 14
Dosenbach, Fair, Cohen, Schlaggar, Petersen (bib0045) 2008; 12
Tang, Li, Lu (bib0007) 2019; 36
Kambeitz, Cabral, Sacchet (bib0009) 2017; 82
Lei, Pinaya, Young (bib0028) 2020; 41
Yao, Sui, Wang (bib0019) 2021; 40
Yamashita, Sakai, Yamada (bib0011) 2020; 18
Ktena, Parisot, Ferrante (bib0017) 2018; 169
Chao-Gan, Yu-Feng (bib0022) 2010; 4
Cai, Elsayed, Barch (bib0044) 2021; 287
Kaiser, Andrews-Hanna, Wager, Pizzagalli (bib0046) 2015; 72
He, Lu, Sheng (bib0013) 2019; 53
Jun, Na, Kang, Lee, Suk, Ham (bib0039) 2020; 41
Wu, Lin, Yang, Song, Yang, Yang (bib0047) 2016; 200
Vieira, Pinaya, Mechelli (bib0020) 2017; 74
Parisot, Ktena, Ferrante (bib0018) 2018; 48
Lei (10.1016/j.ebiom.2022.103977_bib0028) 2020; 41
Cai (10.1016/j.ebiom.2022.103977_bib0044) 2021; 287
Lui (10.1016/j.ebiom.2022.103977_bib0002) 2016; 281
Chao-Gan (10.1016/j.ebiom.2022.103977_bib0022) 2010; 4
Li (10.1016/j.ebiom.2022.103977_bib53) 2021; 1
Whiteford (10.1016/j.ebiom.2022.103977_bib0001) 2013; 382
Ktena (10.1016/j.ebiom.2022.103977_bib0017) 2018; 169
Schnack (10.1016/j.ebiom.2022.103977_bib0008) 2016; 7
Whitfield-Gabrieli (10.1016/j.ebiom.2022.103977_bib0042) 2012; 8
Kaiser (10.1016/j.ebiom.2022.103977_bib0046) 2015; 72
Tang (10.1016/j.ebiom.2022.103977_bib0007) 2019; 36
10.1016/j.ebiom.2022.103977_bib0035
Stonnington (10.1016/j.ebiom.2022.103977_bib0025) 2008; 39
Yao (10.1016/j.ebiom.2022.103977_bib0004) 2020; 14
Dosenbach (10.1016/j.ebiom.2022.103977_bib0023) 2010; 329
Lai (10.1016/j.ebiom.2022.103977_bib0003) 2014; 160
Yan (10.1016/j.ebiom.2022.103977_bib0021) 2019; 116
Parisot (10.1016/j.ebiom.2022.103977_bib0018) 2018; 48
Johnson (10.1016/j.ebiom.2022.103977_bib0029) 2007; 8
Gong (10.1016/j.ebiom.2022.103977_bib0040) 2015; 77
Kambeitz (10.1016/j.ebiom.2022.103977_bib0009) 2017; 82
Fornito (10.1016/j.ebiom.2022.103977_bib0012) 2015; 16
Dohm (10.1016/j.ebiom.2022.103977_bib0048) 2017; 51
Drysdale (10.1016/j.ebiom.2022.103977_bib0050) 2017; 23
Fortin (10.1016/j.ebiom.2022.103977_bib0031) 2017; 161
Qin (10.1016/j.ebiom.2022.103977_bib0051) 2021; 21
Flint (10.1016/j.ebiom.2022.103977_bib0010) 2021; 46
Korgaonkar (10.1016/j.ebiom.2022.103977_bib0043) 2020; 25
Yamashita (10.1016/j.ebiom.2022.103977_bib0011) 2020; 18
Godwin (10.1016/j.ebiom.2022.103977_bib0052) 2017; 8
Bronstein (10.1016/j.ebiom.2022.103977_bib0016) 2017; 34
Gong (10.1016/j.ebiom.2022.103977_bib54) 2020; 30
Arslan (10.1016/j.ebiom.2022.103977_bib0034) 2018
Kawahara (10.1016/j.ebiom.2022.103977_bib0037) 2017; 146
Tomasi (10.1016/j.ebiom.2022.103977_bib0024) 2012; 33
Wu (10.1016/j.ebiom.2022.103977_bib0047) 2016; 200
Bullmore (10.1016/j.ebiom.2022.103977_bib0041) 2009; 10
Zhou (10.1016/j.ebiom.2022.103977_bib0036) 2016
Dosenbach (10.1016/j.ebiom.2022.103977_bib0045) 2008; 12
Zhu (10.1016/j.ebiom.2022.103977_bib0005) 2012; 71
Yao (10.1016/j.ebiom.2022.103977_bib0019) 2021; 40
Vieira (10.1016/j.ebiom.2022.103977_bib0020) 2017; 74
Chen (10.1016/j.ebiom.2022.103977_bib0006) 2018; 20
He (10.1016/j.ebiom.2022.103977_bib0013) 2019; 53
Radua (10.1016/j.ebiom.2022.103977_bib0033) 2020; 218
Craddock (10.1016/j.ebiom.2022.103977_bib0038) 2009; 62
Yang (10.1016/j.ebiom.2022.103977_bib0049) 2021; 26
Kostro (10.1016/j.ebiom.2022.103977_bib0027) 2014; 98
Jun (10.1016/j.ebiom.2022.103977_bib0039) 2020; 41
Zhang (10.1016/j.ebiom.2022.103977_bib0015) 2011; 70
Yu (10.1016/j.ebiom.2022.103977_bib0032) 2018; 39
Yahata (10.1016/j.ebiom.2022.103977_bib0026) 2016; 7
Shi (10.1016/j.ebiom.2022.103977_bib0014) 2020; 97
Fortin (10.1016/j.ebiom.2022.103977_bib0030) 2018; 167
References_xml – volume: 53
  start-page: 528
  year: 2019
  end-page: 539
  ident: bib0013
  article-title: Functional dysconnectivity within the emotion-regulating system is associated with affective symptoms in major depressive disorder: a resting-state fMRI study
  publication-title: Aust N Z J Psychiatry
– volume: 169
  start-page: 431
  year: 2018
  end-page: 442
  ident: bib0017
  article-title: Metric learning with spectral graph convolutions on brain connectivity networks
  publication-title: Neuroimage
– volume: 41
  start-page: 4997
  year: 2020
  end-page: 5014
  ident: bib0039
  article-title: Identifying resting-state effective connectivity abnormalities in drug-naïve major depressive disorder diagnosis via graph convolutional networks
  publication-title: Hum Brain Mapp
– volume: 74
  start-page: 58
  year: 2017
  end-page: 75
  ident: bib0020
  article-title: Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: methods and applications
  publication-title: Neurosci Biobehav Rev
– volume: 218
  year: 2020
  ident: bib0033
  article-title: Increased power by harmonizing structural MRI site differences with the ComBat batch adjustment method in ENIGMA
  publication-title: Neuroimage
– start-page: 2921
  year: 2016
  end-page: 2929
  ident: bib0036
  article-title: Learning deep features for discriminative localization
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
– volume: 20
  start-page: 42
  year: 2018
  end-page: 50
  ident: bib0006
  article-title: Common and distinct abnormal frontal-limbic system structural and functional patterns in patients with major depression and bipolar disorder
  publication-title: Neuroimage Clin
– volume: 12
  start-page: 99
  year: 2008
  end-page: 105
  ident: bib0045
  article-title: A dual-networks architecture of top-down control
  publication-title: Trends Cogn Sci
– volume: 200
  start-page: 275
  year: 2016
  end-page: 283
  ident: bib0047
  article-title: Dysfunction of the cingulo-opercular network in first-episode medication-naive patients with major depressive disorder
  publication-title: J Affect Disord
– volume: 48
  start-page: 117
  year: 2018
  end-page: 130
  ident: bib0018
  article-title: Disease prediction using graph convolutional networks: application to autism spectrum disorder and Alzheimer's disease
  publication-title: Med Image Anal
– volume: 46
  start-page: 1510
  year: 2021
  end-page: 1517
  ident: bib0010
  article-title: Systematic misestimation of machine learning performance in neuroimaging studies of depression
  publication-title: Neuropsychopharmacology
– volume: 281
  start-page: 357
  year: 2016
  end-page: 372
  ident: bib0002
  article-title: Psychoradiology: the frontier of neuroimaging in psychiatry
  publication-title: Radiology
– volume: 7
  start-page: 11254
  year: 2016
  ident: bib0026
  article-title: A small number of abnormal brain connections predicts adult autism spectrum disorder
  publication-title: Nat Commun
– volume: 4
  start-page: 13
  year: 2010
  ident: bib0022
  article-title: DPARSF: a MATLAB toolbox for "pipeline" data analysis of resting-state fMRI
  publication-title: Front Syst Neurosci
– volume: 51
  start-page: 441
  year: 2017
  end-page: 454
  ident: bib0048
  article-title: Trajectories of major depression disorders: a systematic review of longitudinal neuroimaging findings
  publication-title: Aust N Z J Psychiatry
– volume: 329
  start-page: 1358
  year: 2010
  end-page: 1361
  ident: bib0023
  article-title: Prediction of individual brain maturity using fMRI
  publication-title: Science
– volume: 41
  start-page: 1119
  year: 2020
  end-page: 1135
  ident: bib0028
  article-title: Integrating machining learning and multimodal neuroimaging to detect schizophrenia at the level of the individual
  publication-title: Hum Brain Mapp
– volume: 1
  start-page: 94
  year: 2021
  end-page: 107
  ident: bib53
  article-title: Artificial intelligence applications in psychoradiology
  publication-title: Pyschoradiology
– volume: 34
  start-page: 18
  year: 2017
  end-page: 42
  ident: bib0016
  article-title: Geometric deep learning: going beyond euclidean data
  publication-title: IEEE Signal Process Mag
– volume: 382
  start-page: 1575
  year: 2013
  end-page: 1586
  ident: bib0001
  article-title: Global burden of disease attributable to mental and substance use disorders: findings from the Global Burden of Disease Study 2010
  publication-title: Lancet
– volume: 30
  start-page: 1
  year: 2020
  end-page: 123
  ident: bib54
  publication-title: Psychoradiology, An Issue of Neuroimaging Clinics of North America
– volume: 161
  start-page: 149
  year: 2017
  end-page: 170
  ident: bib0031
  article-title: Harmonization of multi-site diffusion tensor imaging data
  publication-title: Neuroimage
– reference: Fey M., Lenssen J.E. Fast graph representation learning with PyTorch geometric [Internet]. arXiv [preprint]. 2019 [cited 2021 July 29]: arXiv:1903.02428. Available from:
– volume: 77
  start-page: 223
  year: 2015
  end-page: 235
  ident: bib0040
  article-title: Depression, neuroimaging and connectomics: a selective overview
  publication-title: Biol Psychiatry
– volume: 98
  start-page: 405
  year: 2014
  end-page: 415
  ident: bib0027
  article-title: Correction of inter-scanner and within-subject variance in structural MRI based automated diagnosing
  publication-title: Neuroimage
– volume: 39
  start-page: 1180
  year: 2008
  end-page: 1185
  ident: bib0025
  article-title: Interpreting scan data acquired from multiple scanners: a study with Alzheimer's disease
  publication-title: Neuroimage
– volume: 8
  start-page: 118
  year: 2007
  end-page: 127
  ident: bib0029
  article-title: Adjusting batch effects in microarray expression data using empirical Bayes methods
  publication-title: Biostatistics
– volume: 116
  start-page: 9078
  year: 2019
  end-page: 9083
  ident: bib0021
  article-title: Reduced default mode network functional connectivity in patients with recurrent major depressive disorder
  publication-title: Proc Natl Acad Sci U S A
– volume: 97
  year: 2020
  ident: bib0014
  article-title: Abnormal functional connectivity strength in first-episode, drug-naïve adult patients with major depressive disorder
  publication-title: Prog Neuropsychopharmacol Biol Psychiatry
– volume: 8
  start-page: 294
  year: 2017
  ident: bib0052
  article-title: Functional connectivity of cognitive brain networks in schizophrenia during a working memory task
  publication-title: Front Psychiatry
– volume: 62
  start-page: 1619
  year: 2009
  end-page: 1628
  ident: bib0038
  article-title: Disease state prediction from resting state functional connectivity
  publication-title: Magn Reson Med
– volume: 23
  start-page: 28
  year: 2017
  end-page: 38
  ident: bib0050
  article-title: Resting-state connectivity biomarkers define neurophysiological subtypes of depression
  publication-title: Nat Med
– volume: 25
  start-page: 1537
  year: 2020
  end-page: 1549
  ident: bib0043
  article-title: Intrinsic connectomes are a predictive biomarker of remission in major depressive disorder
  publication-title: Mol Psychiatry
– volume: 82
  start-page: 330
  year: 2017
  end-page: 338
  ident: bib0009
  article-title: Detecting neuroimaging biomarkers for depression: a meta-analysis of multivariate pattern recognition studies
  publication-title: Biol Psychiatry
– volume: 7
  start-page: 50
  year: 2016
  ident: bib0008
  article-title: Detecting neuroimaging biomarkers for psychiatric disorders: sample size matters
  publication-title: Front Psychiatry
– volume: 160
  start-page: 74
  year: 2014
  end-page: 79
  ident: bib0003
  article-title: Frontal-insula gray matter deficits in first-episode medication-naïve patients with major depressive disorder
  publication-title: J Affect Disord
– volume: 16
  start-page: 159
  year: 2015
  end-page: 172
  ident: bib0012
  article-title: The connectomics of brain disorders
  publication-title: Nat Rev Neurosci
– volume: 21
  start-page: 213
  year: 2021
  ident: bib0051
  article-title: Network-level functional topological changes after mindfulness-based cognitive therapy in mood dysregulated adolescents at familial risk for bipolar disorder: a pilot study
  publication-title: BMC Psychiatry
– volume: 36
  start-page: 712
  year: 2019
  end-page: 722
  ident: bib0007
  article-title: Anomalous functional connectivity of amygdala subregional networks in major depressive disorder
  publication-title: Depress Anxiety
– volume: 146
  start-page: 1038
  year: 2017
  end-page: 1049
  ident: bib0037
  article-title: BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment
  publication-title: Neuroimage
– volume: 40
  start-page: 1279
  year: 2021
  end-page: 1289
  ident: bib0019
  article-title: A mutual multi-scale triplet graph convolutional network for classification of brain disorders using functional or structural connectivity
  publication-title: IEEE Trans Med Imaging
– volume: 8
  start-page: 49
  year: 2012
  end-page: 76
  ident: bib0042
  article-title: Default mode network activity and connectivity in psychopathology
  publication-title: Annu Rev Clin Psychol
– volume: 18
  year: 2020
  ident: bib0011
  article-title: Generalizable brain network markers of major depressive disorder across multiple imaging sites
  publication-title: PLoS Biol
– volume: 10
  start-page: 186
  year: 2009
  end-page: 198
  ident: bib0041
  article-title: Complex brain networks: graph theoretical analysis of structural and functional systems
  publication-title: Nat Rev Neurosci
– volume: 33
  start-page: 849
  year: 2012
  end-page: 860
  ident: bib0024
  article-title: Gender differences in brain functional connectivity density
  publication-title: Hum Brain Mapp
– volume: 167
  start-page: 104
  year: 2018
  end-page: 120
  ident: bib0030
  article-title: Harmonization of cortical thickness measurements across scanners and sites
  publication-title: Neuroimage
– volume: 70
  start-page: 334
  year: 2011
  end-page: 342
  ident: bib0015
  article-title: Disrupted brain connectivity networks in drug-naive, first-episode major depressive disorder
  publication-title: Biol Psychiatry
– reference: .
– volume: 14
  start-page: 653
  year: 2020
  end-page: 667
  ident: bib0004
  article-title: Morphological changes in subregions of hippocampus and amygdala in major depressive disorder patients
  publication-title: Brain Imaging Behav
– volume: 72
  start-page: 603
  year: 2015
  end-page: 611
  ident: bib0046
  article-title: Large-scale network dysfunction in major depressive disorder: a meta-analysis of resting-state functional connectivity
  publication-title: JAMA Psychiatry
– start-page: 3
  year: 2018
  end-page: 13
  ident: bib0034
  article-title: Graph saliency maps through spectral convolutional networks: application to sex classification with brain connectivity
  publication-title: Graphs in Biomedical Image Analysis and Integrating Medical Imaging and Non-Imaging Modalities
– volume: 39
  start-page: 4213
  year: 2018
  end-page: 4227
  ident: bib0032
  article-title: Statistical harmonization corrects site effects in functional connectivity measurements from multi-site fMRI data
  publication-title: Hum Brain Mapp
– volume: 287
  start-page: 229
  year: 2021
  end-page: 239
  ident: bib0044
  article-title: Contributions from resting state functional connectivity and familial risk to early adolescent-onset MDD: results from the adolescent brain cognitive development study
  publication-title: J Affect Disord
– volume: 71
  start-page: 611
  year: 2012
  end-page: 617
  ident: bib0005
  article-title: Evidence of a dissociation pattern in resting-state default mode network connectivity in first-episode, treatment-naive major depression patients
  publication-title: Biol Psychiatry
– volume: 26
  start-page: 7363
  year: 2021
  end-page: 7371
  ident: bib0049
  article-title: Disrupted intrinsic functional brain topology in patients with major depressive disorder
  publication-title: Mol Psychiatry
– volume: 10
  start-page: 186
  year: 2009
  ident: 10.1016/j.ebiom.2022.103977_bib0041
  article-title: Complex brain networks: graph theoretical analysis of structural and functional systems
  publication-title: Nat Rev Neurosci
  doi: 10.1038/nrn2575
– volume: 12
  start-page: 99
  year: 2008
  ident: 10.1016/j.ebiom.2022.103977_bib0045
  article-title: A dual-networks architecture of top-down control
  publication-title: Trends Cogn Sci
  doi: 10.1016/j.tics.2008.01.001
– volume: 200
  start-page: 275
  year: 2016
  ident: 10.1016/j.ebiom.2022.103977_bib0047
  article-title: Dysfunction of the cingulo-opercular network in first-episode medication-naive patients with major depressive disorder
  publication-title: J Affect Disord
  doi: 10.1016/j.jad.2016.04.046
– volume: 287
  start-page: 229
  year: 2021
  ident: 10.1016/j.ebiom.2022.103977_bib0044
  article-title: Contributions from resting state functional connectivity and familial risk to early adolescent-onset MDD: results from the adolescent brain cognitive development study
  publication-title: J Affect Disord
  doi: 10.1016/j.jad.2021.03.031
– volume: 329
  start-page: 1358
  year: 2010
  ident: 10.1016/j.ebiom.2022.103977_bib0023
  article-title: Prediction of individual brain maturity using fMRI
  publication-title: Science
  doi: 10.1126/science.1194144
– volume: 8
  start-page: 118
  year: 2007
  ident: 10.1016/j.ebiom.2022.103977_bib0029
  article-title: Adjusting batch effects in microarray expression data using empirical Bayes methods
  publication-title: Biostatistics
  doi: 10.1093/biostatistics/kxj037
– volume: 48
  start-page: 117
  year: 2018
  ident: 10.1016/j.ebiom.2022.103977_bib0018
  article-title: Disease prediction using graph convolutional networks: application to autism spectrum disorder and Alzheimer's disease
  publication-title: Med Image Anal
  doi: 10.1016/j.media.2018.06.001
– volume: 161
  start-page: 149
  year: 2017
  ident: 10.1016/j.ebiom.2022.103977_bib0031
  article-title: Harmonization of multi-site diffusion tensor imaging data
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2017.08.047
– volume: 51
  start-page: 441
  year: 2017
  ident: 10.1016/j.ebiom.2022.103977_bib0048
  article-title: Trajectories of major depression disorders: a systematic review of longitudinal neuroimaging findings
  publication-title: Aust N Z J Psychiatry
  doi: 10.1177/0004867416661426
– volume: 41
  start-page: 1119
  year: 2020
  ident: 10.1016/j.ebiom.2022.103977_bib0028
  article-title: Integrating machining learning and multimodal neuroimaging to detect schizophrenia at the level of the individual
  publication-title: Hum Brain Mapp
  doi: 10.1002/hbm.24863
– volume: 41
  start-page: 4997
  year: 2020
  ident: 10.1016/j.ebiom.2022.103977_bib0039
  article-title: Identifying resting-state effective connectivity abnormalities in drug-naïve major depressive disorder diagnosis via graph convolutional networks
  publication-title: Hum Brain Mapp
  doi: 10.1002/hbm.25175
– volume: 23
  start-page: 28
  year: 2017
  ident: 10.1016/j.ebiom.2022.103977_bib0050
  article-title: Resting-state connectivity biomarkers define neurophysiological subtypes of depression
  publication-title: Nat Med
  doi: 10.1038/nm.4246
– volume: 40
  start-page: 1279
  year: 2021
  ident: 10.1016/j.ebiom.2022.103977_bib0019
  article-title: A mutual multi-scale triplet graph convolutional network for classification of brain disorders using functional or structural connectivity
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2021.3051604
– start-page: 3
  year: 2018
  ident: 10.1016/j.ebiom.2022.103977_bib0034
  article-title: Graph saliency maps through spectral convolutional networks: application to sex classification with brain connectivity
– volume: 160
  start-page: 74
  year: 2014
  ident: 10.1016/j.ebiom.2022.103977_bib0003
  article-title: Frontal-insula gray matter deficits in first-episode medication-naïve patients with major depressive disorder
  publication-title: J Affect Disord
  doi: 10.1016/j.jad.2013.12.036
– volume: 14
  start-page: 653
  year: 2020
  ident: 10.1016/j.ebiom.2022.103977_bib0004
  article-title: Morphological changes in subregions of hippocampus and amygdala in major depressive disorder patients
  publication-title: Brain Imaging Behav
  doi: 10.1007/s11682-018-0003-1
– volume: 98
  start-page: 405
  year: 2014
  ident: 10.1016/j.ebiom.2022.103977_bib0027
  article-title: Correction of inter-scanner and within-subject variance in structural MRI based automated diagnosing
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2014.04.057
– volume: 169
  start-page: 431
  year: 2018
  ident: 10.1016/j.ebiom.2022.103977_bib0017
  article-title: Metric learning with spectral graph convolutions on brain connectivity networks
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2017.12.052
– volume: 20
  start-page: 42
  year: 2018
  ident: 10.1016/j.ebiom.2022.103977_bib0006
  article-title: Common and distinct abnormal frontal-limbic system structural and functional patterns in patients with major depression and bipolar disorder
  publication-title: Neuroimage Clin
  doi: 10.1016/j.nicl.2018.07.002
– volume: 281
  start-page: 357
  year: 2016
  ident: 10.1016/j.ebiom.2022.103977_bib0002
  article-title: Psychoradiology: the frontier of neuroimaging in psychiatry
  publication-title: Radiology
  doi: 10.1148/radiol.2016152149
– volume: 7
  start-page: 11254
  year: 2016
  ident: 10.1016/j.ebiom.2022.103977_bib0026
  article-title: A small number of abnormal brain connections predicts adult autism spectrum disorder
  publication-title: Nat Commun
  doi: 10.1038/ncomms11254
– volume: 382
  start-page: 1575
  year: 2013
  ident: 10.1016/j.ebiom.2022.103977_bib0001
  article-title: Global burden of disease attributable to mental and substance use disorders: findings from the Global Burden of Disease Study 2010
  publication-title: Lancet
  doi: 10.1016/S0140-6736(13)61611-6
– volume: 77
  start-page: 223
  year: 2015
  ident: 10.1016/j.ebiom.2022.103977_bib0040
  article-title: Depression, neuroimaging and connectomics: a selective overview
  publication-title: Biol Psychiatry
  doi: 10.1016/j.biopsych.2014.08.009
– volume: 72
  start-page: 603
  year: 2015
  ident: 10.1016/j.ebiom.2022.103977_bib0046
  article-title: Large-scale network dysfunction in major depressive disorder: a meta-analysis of resting-state functional connectivity
  publication-title: JAMA Psychiatry
  doi: 10.1001/jamapsychiatry.2015.0071
– volume: 71
  start-page: 611
  year: 2012
  ident: 10.1016/j.ebiom.2022.103977_bib0005
  article-title: Evidence of a dissociation pattern in resting-state default mode network connectivity in first-episode, treatment-naive major depression patients
  publication-title: Biol Psychiatry
  doi: 10.1016/j.biopsych.2011.10.035
– volume: 34
  start-page: 18
  year: 2017
  ident: 10.1016/j.ebiom.2022.103977_bib0016
  article-title: Geometric deep learning: going beyond euclidean data
  publication-title: IEEE Signal Process Mag
  doi: 10.1109/MSP.2017.2693418
– volume: 25
  start-page: 1537
  year: 2020
  ident: 10.1016/j.ebiom.2022.103977_bib0043
  article-title: Intrinsic connectomes are a predictive biomarker of remission in major depressive disorder
  publication-title: Mol Psychiatry
  doi: 10.1038/s41380-019-0574-2
– volume: 39
  start-page: 4213
  year: 2018
  ident: 10.1016/j.ebiom.2022.103977_bib0032
  article-title: Statistical harmonization corrects site effects in functional connectivity measurements from multi-site fMRI data
  publication-title: Hum Brain Mapp
  doi: 10.1002/hbm.24241
– volume: 116
  start-page: 9078
  year: 2019
  ident: 10.1016/j.ebiom.2022.103977_bib0021
  article-title: Reduced default mode network functional connectivity in patients with recurrent major depressive disorder
  publication-title: Proc Natl Acad Sci U S A
  doi: 10.1073/pnas.1900390116
– volume: 33
  start-page: 849
  year: 2012
  ident: 10.1016/j.ebiom.2022.103977_bib0024
  article-title: Gender differences in brain functional connectivity density
  publication-title: Hum Brain Mapp
  doi: 10.1002/hbm.21252
– volume: 1
  start-page: 94
  year: 2021
  ident: 10.1016/j.ebiom.2022.103977_bib53
  article-title: Artificial intelligence applications in psychoradiology
  publication-title: Pyschoradiology
  doi: 10.1093/psyrad/kkab009
– volume: 8
  start-page: 294
  year: 2017
  ident: 10.1016/j.ebiom.2022.103977_bib0052
  article-title: Functional connectivity of cognitive brain networks in schizophrenia during a working memory task
  publication-title: Front Psychiatry
  doi: 10.3389/fpsyt.2017.00294
– volume: 62
  start-page: 1619
  year: 2009
  ident: 10.1016/j.ebiom.2022.103977_bib0038
  article-title: Disease state prediction from resting state functional connectivity
  publication-title: Magn Reson Med
  doi: 10.1002/mrm.22159
– volume: 53
  start-page: 528
  year: 2019
  ident: 10.1016/j.ebiom.2022.103977_bib0013
  article-title: Functional dysconnectivity within the emotion-regulating system is associated with affective symptoms in major depressive disorder: a resting-state fMRI study
  publication-title: Aust N Z J Psychiatry
  doi: 10.1177/0004867419832106
– volume: 74
  start-page: 58
  year: 2017
  ident: 10.1016/j.ebiom.2022.103977_bib0020
  article-title: Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: methods and applications
  publication-title: Neurosci Biobehav Rev
  doi: 10.1016/j.neubiorev.2017.01.002
– volume: 16
  start-page: 159
  year: 2015
  ident: 10.1016/j.ebiom.2022.103977_bib0012
  article-title: The connectomics of brain disorders
  publication-title: Nat Rev Neurosci
  doi: 10.1038/nrn3901
– volume: 36
  start-page: 712
  year: 2019
  ident: 10.1016/j.ebiom.2022.103977_bib0007
  article-title: Anomalous functional connectivity of amygdala subregional networks in major depressive disorder
  publication-title: Depress Anxiety
  doi: 10.1002/da.22901
– volume: 7
  start-page: 50
  year: 2016
  ident: 10.1016/j.ebiom.2022.103977_bib0008
  article-title: Detecting neuroimaging biomarkers for psychiatric disorders: sample size matters
  publication-title: Front Psychiatry
  doi: 10.3389/fpsyt.2016.00050
– volume: 30
  start-page: 1
  year: 2020
  ident: 10.1016/j.ebiom.2022.103977_bib54
– volume: 218
  year: 2020
  ident: 10.1016/j.ebiom.2022.103977_bib0033
  article-title: Increased power by harmonizing structural MRI site differences with the ComBat batch adjustment method in ENIGMA
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2020.116956
– volume: 21
  start-page: 213
  year: 2021
  ident: 10.1016/j.ebiom.2022.103977_bib0051
  article-title: Network-level functional topological changes after mindfulness-based cognitive therapy in mood dysregulated adolescents at familial risk for bipolar disorder: a pilot study
  publication-title: BMC Psychiatry
  doi: 10.1186/s12888-021-03211-4
– volume: 8
  start-page: 49
  year: 2012
  ident: 10.1016/j.ebiom.2022.103977_bib0042
  article-title: Default mode network activity and connectivity in psychopathology
  publication-title: Annu Rev Clin Psychol
  doi: 10.1146/annurev-clinpsy-032511-143049
– volume: 82
  start-page: 330
  year: 2017
  ident: 10.1016/j.ebiom.2022.103977_bib0009
  article-title: Detecting neuroimaging biomarkers for depression: a meta-analysis of multivariate pattern recognition studies
  publication-title: Biol Psychiatry
  doi: 10.1016/j.biopsych.2016.10.028
– volume: 146
  start-page: 1038
  year: 2017
  ident: 10.1016/j.ebiom.2022.103977_bib0037
  article-title: BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2016.09.046
– volume: 39
  start-page: 1180
  year: 2008
  ident: 10.1016/j.ebiom.2022.103977_bib0025
  article-title: Interpreting scan data acquired from multiple scanners: a study with Alzheimer's disease
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2007.09.066
– volume: 70
  start-page: 334
  year: 2011
  ident: 10.1016/j.ebiom.2022.103977_bib0015
  article-title: Disrupted brain connectivity networks in drug-naive, first-episode major depressive disorder
  publication-title: Biol Psychiatry
  doi: 10.1016/j.biopsych.2011.05.018
– volume: 46
  start-page: 1510
  year: 2021
  ident: 10.1016/j.ebiom.2022.103977_bib0010
  article-title: Systematic misestimation of machine learning performance in neuroimaging studies of depression
  publication-title: Neuropsychopharmacology
  doi: 10.1038/s41386-021-01020-7
– volume: 26
  start-page: 7363
  year: 2021
  ident: 10.1016/j.ebiom.2022.103977_bib0049
  article-title: Disrupted intrinsic functional brain topology in patients with major depressive disorder
  publication-title: Mol Psychiatry
  doi: 10.1038/s41380-021-01247-2
– volume: 97
  year: 2020
  ident: 10.1016/j.ebiom.2022.103977_bib0014
  article-title: Abnormal functional connectivity strength in first-episode, drug-naïve adult patients with major depressive disorder
  publication-title: Prog Neuropsychopharmacol Biol Psychiatry
  doi: 10.1016/j.pnpbp.2019.109759
– volume: 18
  year: 2020
  ident: 10.1016/j.ebiom.2022.103977_bib0011
  article-title: Generalizable brain network markers of major depressive disorder across multiple imaging sites
  publication-title: PLoS Biol
  doi: 10.1371/journal.pbio.3000966
– volume: 4
  start-page: 13
  year: 2010
  ident: 10.1016/j.ebiom.2022.103977_bib0022
  article-title: DPARSF: a MATLAB toolbox for "pipeline" data analysis of resting-state fMRI
  publication-title: Front Syst Neurosci
– volume: 167
  start-page: 104
  year: 2018
  ident: 10.1016/j.ebiom.2022.103977_bib0030
  article-title: Harmonization of cortical thickness measurements across scanners and sites
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2017.11.024
– ident: 10.1016/j.ebiom.2022.103977_bib0035
– start-page: 2921
  year: 2016
  ident: 10.1016/j.ebiom.2022.103977_bib0036
  article-title: Learning deep features for discriminative localization
SSID ssj0001542358
Score 2.5200288
Snippet Establishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive disorder...
SummaryBackgroundEstablishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major...
Background: Establishing objective and quantitative neuroimaging biomarkers at individual level can assist in early and accurate diagnosis of major depressive...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
elsevier
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 103977
SubjectTerms Advanced Basic Science
Brain - diagnostic imaging
Brain Mapping
Connectome
Deep learning
Depression
Depressive Disorder, Major - diagnostic imaging
Graph neural network
Graph theory
Humans
Internal Medicine
Magnetic Resonance Imaging
Multi-site
Neuroimaging
Title Using graph convolutional network to characterize individuals with major depressive disorder across multiple imaging sites
URI https://www.clinicalkey.com/#!/content/1-s2.0-S235239642200161X
https://www.clinicalkey.es/playcontent/1-s2.0-S235239642200161X
https://dx.doi.org/10.1016/j.ebiom.2022.103977
https://www.ncbi.nlm.nih.gov/pubmed/35367775
https://www.proquest.com/docview/2646943976
https://pubmed.ncbi.nlm.nih.gov/PMC8983334
https://doaj.org/article/044beed78a8249f9ba137c397118500b
Volume 78
WOSCitedRecordID wos000795959900011&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2352-3964
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001542358
  issn: 2352-3964
  databaseCode: DOA
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagAokLojxDaWUkjkQkfvtYEBUHVCHx0N6s-BGRimbRZluJ_nrGdhJtALUXrptMsh5_GX9OZr5B6FWrLPfEqpLampaM1KxUraxK1QBYmKtCnXQKvn2Up6dqtdKfdlp9xZywLA-cHfemYsxCHJdgDDuFVtumptLBKgrMmFeVjdEXWM_OZirXB7NYA5o6y3FSUi3YJDmUkrtCLG6H3SEhseocONBiWUrq_YvV6W_2-WcS5c6qdPIA3R_pJD7Ow9hHt0L_EN3NDSZ_PUJXKSMAJ1VqHBPMR6CBSZ_zv_F2jd0s2nwVcDdXaA04vqTF583ZeoOnjNnLgP0o2ImbNBY85STi7jy1PMLxg_TwGH09ef_l3Ydy7LZQOkHJtpTcWetCpcHbAR4db7kWWgUlWiEJ0bXV3nvdUsFCrFB1jSAN121rg_KctfQJ2uvXfXiGsAde6b3zQG44a0RllWXEVo67YFuhbIHI5GzjRiny2BHjh5lyzs5MmiETZ8jkGSrQ69noZ1biuP70t3EW51OjjHb6AcBlRnCZm8BVIDZhwEyVqhBb4ULd9feW_zILwxgfBlObgZjKfI7ojOAkJHHvVYHEbDlSoExtbr7lywmiBgJE_OrT9GF9MRhgvEIn2lmgpxmys1Mop0JKyeEPL8C88NrySN99TyLkSitKKXv-P9x8gO7FoeSEqBdob7u5CIfojrvcdsPmCN2WK3WUnu_fpVlVSw
linkProvider Directory of Open Access Journals
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=Using+graph+convolutional+network+to+characterize+individuals+with+major+depressive+disorder+across+multiple+imaging+sites&rft.jtitle=EBioMedicine&rft.au=Qin%2C+Kun&rft.au=Lei%2C+Du&rft.au=Pinaya%2C+Walter+H.L.&rft.au=Pan%2C+Nanfang&rft.date=2022-04-01&rft.issn=2352-3964&rft.eissn=2352-3964&rft.volume=78&rft.spage=103977&rft_id=info:doi/10.1016%2Fj.ebiom.2022.103977&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ebiom_2022_103977
thumbnail_m http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F23523964%2FS2352396422X00042%2Fcov150h.gif