MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images

Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction t...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) Ročník 2025; s. 15611 - 15620
Hlavní autori: Ganguly, Aniruddha, Chatterjee, Debolina, Huang, Wentao, Zhang, Jie, Yurovsky, Alisa, Johnson, Travis Steele, Chen, Chao
Médium: Konferenčný príspevok.. Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.06.2025
Predmet:
ISSN:1063-6919, 1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods fail to fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce MERGE (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques across multiple metrics.
AbstractList Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods fail to fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques across multiple metrics.
Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods fail to fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce MERGE (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques across multiple metrics.
Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods fail to fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce MERGE (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques across multiple metrics.Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods fail to fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce MERGE (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques across multiple metrics.
Author Ganguly, Aniruddha
Chen, Chao
Zhang, Jie
Yurovsky, Alisa
Chatterjee, Debolina
Huang, Wentao
Johnson, Travis Steele
AuthorAffiliation 1 Stony Brook University, NY, USA
2 Indiana University School of Medicine, IN, USA
AuthorAffiliation_xml – name: 1 Stony Brook University, NY, USA
– name: 2 Indiana University School of Medicine, IN, USA
Author_xml – sequence: 1
  givenname: Aniruddha
  surname: Ganguly
  fullname: Ganguly, Aniruddha
  email: aniganguly@cs.stonybrook.edu
  organization: Stony Brook University,NY,USA
– sequence: 2
  givenname: Debolina
  surname: Chatterjee
  fullname: Chatterjee, Debolina
  organization: Indiana University School of Medicine,IN,USA
– sequence: 3
  givenname: Wentao
  surname: Huang
  fullname: Huang, Wentao
  organization: Stony Brook University,NY,USA
– sequence: 4
  givenname: Jie
  surname: Zhang
  fullname: Zhang, Jie
  organization: Indiana University School of Medicine,IN,USA
– sequence: 5
  givenname: Alisa
  surname: Yurovsky
  fullname: Yurovsky, Alisa
  organization: Stony Brook University,NY,USA
– sequence: 6
  givenname: Travis Steele
  surname: Johnson
  fullname: Johnson, Travis Steele
  organization: Indiana University School of Medicine,IN,USA
– sequence: 7
  givenname: Chao
  surname: Chen
  fullname: Chen, Chao
  organization: Stony Brook University,NY,USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40873441$$D View this record in MEDLINE/PubMed
BookMark eNpVkU9v1DAQxQ0qoqXsN6iQj1yyjP9uzAWh1ZJWaktVKjhGjjPeNUri1M4C_fakaqnKaZ7mPf2eNPOGHAxxQEJOGCwZA_Nh_f3qWvGVkEsOXC2BSaVekIVZmVIIpqTQsnxJjhhoUWjDzMEzfUgWOf8EAMEZ06Z8TQ4llDNLsiPy-2JzXW0-0ot9N4XCW4cTtvQ0YLLJ7YKzHa2SHXdFY_NsVJeX1MdEKxyQbv6MCXMOcaBXCdvgpnvpU-zpj13skH7rQoszLE9xtNO8its7etbbLea35JW3XcbF4zwmN182N-vT4vxrdbb-fF4EJgQUykswyrYtsgYd2JUR0KBWvtHSWg9Sq5U22mHTgmfouDWsFEp7xb2fCcfk0wN23Dc9tg6HKdmuHlPobbqrow31_84QdvU2_qoZFyWAhJnw_pGQ4u0e81T3ITvsOjtg3OdacKkFlFyYOfruedlTy79rz4GTh0BAxCf7_sFSai7-AjD7kmw
CODEN IEEPAD
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
RIE
RIO
NPM
7X8
5PM
DOI 10.1109/CVPR52734.2025.01455
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP) 1998-present
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList PubMed

MEDLINE - Academic

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISBN 9798331543648
EISSN 1063-6919
EndPage 15620
ExternalDocumentID PMC12380040
40873441
11094462
Genre orig-research
Journal Article
GrantInformation_xml – fundername: Health
  funderid: 10.13039/100018696
– fundername: National Science Foundation
  funderid: 10.13039/100000001
– fundername: NIGMS NIH HHS
  grantid: R01 GM148970
– fundername: NIGMS NIH HHS
  grantid: R01 GM153028
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
23M
29F
29O
6IK
ABDPE
ACGFS
IPLJI
M43
NPM
RNS
7X8
5PM
ID FETCH-LOGICAL-i1330-5f4095adde1bec0a7930be65fb64aaf04657696cebd0f1ec2a918356f52ff133
IEDL.DBID RIE
ISSN 1063-6919
IngestDate Tue Sep 30 17:01:20 EDT 2025
Sat Nov 01 14:25:06 EDT 2025
Thu Sep 04 05:07:34 EDT 2025
Wed Aug 20 06:20:56 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i1330-5f4095adde1bec0a7930be65fb64aaf04657696cebd0f1ec2a918356f52ff133
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 40873441
PQID 3246308239
PQPubID 23479
PageCount 10
ParticipantIDs proquest_miscellaneous_3246308239
pubmed_primary_40873441
ieee_primary_11094462
pubmedcentral_primary_oai_pubmedcentral_nih_gov_12380040
PublicationCentury 2000
PublicationDate 20250601
PublicationDateYYYYMMDD 2025-06-01
PublicationDate_xml – month: 6
  year: 2025
  text: 20250601
  day: 1
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationTitleAlternate Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
ssj0023720
Score 2.4773366
Snippet Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression...
SourceID pubmedcentral
proquest
pubmed
ieee
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 15611
SubjectTerms Accuracy
cell microscopy
computer vision
Gene expression
Graph neural networks
Histopathology
Image edge detection
Measurement
medical and biological vision
Pattern recognition
Smoothing methods
Spatial resolution
spatial transcriptomics
Transcriptomics
Title MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images
URI https://ieeexplore.ieee.org/document/11094462
https://www.ncbi.nlm.nih.gov/pubmed/40873441
https://www.proquest.com/docview/3246308239
https://pubmed.ncbi.nlm.nih.gov/PMC12380040
Volume 2025
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFG-UePCEH6j4QWridbKN7ssrGeDBhSBRbku3tnGJDsNA_fN9rxtTjB68LVnXNX3t-2p_v0fIFTidtqXc1BCgIA1mWdzgXEmIUuyUMS7ASgldbMKLIn82C8YVWF1jYaSU-vKZvMZHfZYv5ukKU2VdZMeE8AU07rbneSVYq06o9CCUcQO_gsdBy27_YTxBfjFMndjIzskQ0KeLqPzmT_68FvnNzgya_xzhHml9IfbouLZF-2RL5gekWbmYtNrAxSF5vwsnw_CGatytoXgKPrOgowxhyLoqyjMdIoW1gdZN0GEUUfBqKZJT0_CjujSbw6_wfAdlShGfQh-xyi69f86EpJp4BAsd64Q9vX0BjVW0yHQQTvsjo6q9YGQQtZqGoyDwc1D5WSBlk8M2NhPpOipxGQgTomoIVAI3lYkwlSVTmwegHBxXObZS0MMRaeTzXJ4QypxeYiaeZyY8geceZ6DShGCpCjgXjtUmLZzH-LVk14jXU9gml2sRxbDk8RyD53K-KmLwAV3NshO0yXEpsvprZvogcAa9-hvCrBsgnfbmmzx70rTaYMN91GmnfwzojOziOirviZ2TxnKxkhdkJ31bZsWiA0ty5nf0kvwEiuri8w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bT4MwFG6MmujTvEyd15r4igNWGPi6sEvcyDIX3RsptI0kk5ld1J_vOR1DZ_TBNxJKaXrac2u_7xByA06nbSk3MQQoSINZFjc4VxKiFDthjAuwUkIXm6iHoTca-f0crK6xMFJKfflM3uKjPssXk2SBqbIqsmNC-AIad8thzLaWcK0ipVKDYMb1vRwgB22rjcf-ABnGMHliIz8nQ0ifLqPym0f582LkN0vTLP1zjHuk_IXZo_3CGu2TDZkdkFLuZNJ8C88OyXsvGLSCO6qRt4biCXjNgrZTBCLruihj2kISawPtm6CtMKTg11Kkp6bBR35tNoNf4QkPSpUiQoU-YZ1d-jBOhaSaegRLHeuUPe28gM6alcmwGQwbbSOvvmCkELeahqMg9HNQ_VkgZ5PDRjZj6ToqdhmIE-JqCFV8N5GxMJUlE5v7oB4cVzm2UtDDEdnMJpk8IZQ5tdiM63Uz5jE81zgDpSYES5TPuXCsCinjPEavS36NaDWFFXK9ElEEix5PMngmJ4tZBF6gq3l2_Ao5Xoqs-JqZHgicQa_emjCLBkiovf4mS581sTZYcQ-12ukfA7oiO-1hrxt1O-H9GdnFNbW8NXZONufThbwg28nbPJ1NL_XC_AQdUeVS
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=MERGE%3A+Multi-faceted+Hierarchical+Graph-based+GNN+for+Gene+Expression+Prediction+from+Whole+Slide+Histopathology+Images&rft.au=Ganguly%2C+Aniruddha&rft.au=Chatterjee%2C+Debolina&rft.au=Huang%2C+Wentao&rft.au=Zhang%2C+Jie&rft.date=2025-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=15611&rft.epage=15620&rft_id=info:doi/10.1109%2FCVPR52734.2025.01455&rft.externalDocID=11094462
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon