Learning Similarity-Preserving Representations of Brain Structure-Function Coupling

Advances in graph signal processing for network neuroscience offer a unique pathway to integrate brain structure and function, with the goal of revealing some of the brain's organizing principles at the system level. In this direction, we develop a supervised graph representation learning frame...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2022 30th European Signal Processing Conference (EUSIPCO) S. 922 - 926
Hauptverfasser: Li, Yang, Mateos, Gonzalo
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: EUSIPCO 29.08.2022
Schlagworte:
ISSN:2076-1465
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Advances in graph signal processing for network neuroscience offer a unique pathway to integrate brain structure and function, with the goal of revealing some of the brain's organizing principles at the system level. In this direction, we develop a supervised graph representation learning framework to model the relationship between brain structural connectivity (SC) and functional connectivity (FC) via a graph encoder-decoder system. Specifically, we propose a Siamese network architecture equipped with graph convolutional encoders to learn graph (i.e., subject)-level embeddings that preserve application-dependent similarity measures between brain networks. This way, we effectively increase the number of training samples and bring in the flexibility to incorporate additional prior information via the prescribed target graph-level distance. While information on the brain structure-function coupling is implicitly distilled via reconstruction of brain FC from SC, our model also manages to learn representations that preserve the similarity between input graphs. The superior discriminative power of the learnt representations is demonstrated in downstream tasks including subject classification and visualization. All in all, this work advocates the prospect of leveraging learnt graph-level, similarity-preserving embeddings for brain network analysis, by bringing to bear standard tools of metric data analysis.
AbstractList Advances in graph signal processing for network neuroscience offer a unique pathway to integrate brain structure and function, with the goal of revealing some of the brain's organizing principles at the system level. In this direction, we develop a supervised graph representation learning framework to model the relationship between brain structural connectivity (SC) and functional connectivity (FC) via a graph encoder-decoder system. Specifically, we propose a Siamese network architecture equipped with graph convolutional encoders to learn graph (i.e., subject)-level embeddings that preserve application-dependent similarity measures between brain networks. This way, we effectively increase the number of training samples and bring in the flexibility to incorporate additional prior information via the prescribed target graph-level distance. While information on the brain structure-function coupling is implicitly distilled via reconstruction of brain FC from SC, our model also manages to learn representations that preserve the similarity between input graphs. The superior discriminative power of the learnt representations is demonstrated in downstream tasks including subject classification and visualization. All in all, this work advocates the prospect of leveraging learnt graph-level, similarity-preserving embeddings for brain network analysis, by bringing to bear standard tools of metric data analysis.
Author Li, Yang
Mateos, Gonzalo
Author_xml – sequence: 1
  givenname: Yang
  surname: Li
  fullname: Li, Yang
  email: yli131@ur.rochester.edu
  organization: University of Rochester,Dept. of Electrical and Computer Engineering,Rochester,NY,USA
– sequence: 2
  givenname: Gonzalo
  surname: Mateos
  fullname: Mateos, Gonzalo
  email: gmateosb@ece.rochester.edu
  organization: University of Rochester,Dept. of Electrical and Computer Engineering,Rochester,NY,USA
BookMark eNotkEFrAjEUhNPSQtX6C3pZel_7kphs3rFdtBUWlG49S9y8lIBmJbtb8N-3Uk_DzMfMYcbsLraRGHvmMBMSOb4stvVqU66VApQzAULMEAGV1jdsjGBEgQVgcctGAgqd87lWD2zadWEPwoApOOgRqyuyKYb4ndXhGA42hf6cbxJ1lH4u6SedLib2tg9t7LLWZ2_JhpjVfRqafkiUL4fYXGBWtsPp8Fd6ZPfeHjqaXnXCtsvFV_mRV-v3Vfla5YGD6nPlkObOIxrjfLN3yhLKwjpv9N4raea84RaAHJdGIXJotLNolNegLUcnJ-zpfzcQ0e6UwtGm8-76gfwFQqdWPA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.23919/EUSIPCO55093.2022.9909566
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9082797097
9789082797091
EISSN 2076-1465
EndPage 926
ExternalDocumentID 9909566
Genre orig-research
GrantInformation_xml – fundername: NSF
  grantid: CCF-1750428,CCF-1934962,ECCS-1809356
  funderid: 10.13039/100000001
GroupedDBID 6IE
6IL
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i105t-5d9e4df9988dfcbd5ae937adf86bf53841c1a00ed13859910c6da985f606a19d3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000918827600182&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:52:09 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i105t-5d9e4df9988dfcbd5ae937adf86bf53841c1a00ed13859910c6da985f606a19d3
PageCount 5
ParticipantIDs ieee_primary_9909566
PublicationCentury 2000
PublicationDate 2022-Aug.-29
PublicationDateYYYYMMDD 2022-08-29
PublicationDate_xml – month: 08
  year: 2022
  text: 2022-Aug.-29
  day: 29
PublicationDecade 2020
PublicationTitle 2022 30th European Signal Processing Conference (EUSIPCO)
PublicationTitleAbbrev EUSIPCO
PublicationYear 2022
Publisher EUSIPCO
Publisher_xml – name: EUSIPCO
SSID ssib028087106
ssib025355106
Score 1.8053551
Snippet Advances in graph signal processing for network neuroscience offer a unique pathway to integrate brain structure and function, with the goal of revealing some...
SourceID ieee
SourceType Publisher
StartPage 922
SubjectTerms Brain connectomics
Convolution
Couplings
graph convolutional network
graph representation learning
Network analyzers
Pipelines
Representation learning
Siamese network
Training
Training data
Title Learning Similarity-Preserving Representations of Brain Structure-Function Coupling
URI https://ieeexplore.ieee.org/document/9909566
WOSCitedRecordID wos000918827600182&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELbaioEJUIt4KwMjbh3HduyVqhUspSJU6lY5flQZSFBfv59zGgpILGyRE1nJxbr7Pvu-O4TuaeI9i3ODPSMWM-ccljkTWEnJQ9aFJ6mtm02kk4mcz9W0hR4OWhh4uk4-c_1wWZ_l28psw1bZADwnwHnRRu00Tfdara-1QzkEzh8nhlQSoAJE7OuM0kTFajCaZc_T4QtgcpUAM6S030z4q7NKHVjGJ_97pVPU-1boRdND7DlDLVd2UdYUS11GWfFeAGUFhI1DjkXwBzD6Wme9NmKjch1VPnoMHSKirC4iu105PIYwF25Gw2obtLrLHpqNR2_DJ9w0TcAFQKUN5lY5Zj2wKGm9yS3XDhCItl6K3IN3Y7GJNSHOxonkAA6JEVYryT0wGR0rm5yjTlmV7gJFjHnhmKCKQyDPrdFG5KlkSa4tcSrVl6gbDLL42NfFWDS2uPp7-BodB5uH_ViqblAHvszdoiOz2xTr1V39Mz8B2eag8w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZKQYIJUIt4k4ERt4ljJ_ZK1aoVpVSklbpVjh9VBhLUB7-fcxoKSCxskRNZycW6-z77vjuE7kloLQ1ShS31NabGGMxTGmHBOXNZF9aPddlsIh6N-GwmxjX0sNPCwNNl8plpucvyLF8XauO2ytrgOQHOR3ton1FKgq1a62v1EAah88eZIeE-kAE_2lYaJaEIRLs7TQbjzgugchECNySkVU35q7dKGVp6x_97qRPU_NboeeNd9DlFNZM3UFKVS114SfaWAWkFjI1dloXzCDD6Wua9VnKjfOUV1nt0PSK8pCwju1ka3INA5256nWLj1LqLJpr2upNOH1dtE3AGYGmNmRaGags8imurUs2kAQwiteVRasG_0UAF0veNDkLOAB76KtJScGaBy8hA6PAM1fMiN-fIo9RGhkZEMAjlqVZSRWnMaZhK7RsRywvUcAaZv28rY8wrW1z-PXyHDvuT5-F8OBg9XaEjZ3-3O0vENarDV5obdKA-1tlqeVv-2E9nLqQ6
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=proceeding&rft.title=2022+30th+European+Signal+Processing+Conference+%28EUSIPCO%29&rft.atitle=Learning+Similarity-Preserving+Representations+of+Brain+Structure-Function+Coupling&rft.au=Li%2C+Yang&rft.au=Mateos%2C+Gonzalo&rft.date=2022-08-29&rft.pub=EUSIPCO&rft.eissn=2076-1465&rft.spage=922&rft.epage=926&rft_id=info:doi/10.23919%2FEUSIPCO55093.2022.9909566&rft.externalDocID=9909566