Generation of 12-Lead Electrocardiogram with Subject-Specific, Image-Derived Characteristics Using a Conditional Variational Autoencoder

Deep learning models have proven their value in the analysis of electrocardiogram (ECG). Among these, deep generative models have shown their ability in ECG generation. In this paper, we propose a conditional variational autoencoder (cVAE) to automatically generate realistic 12-lead ECG signals. Our...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (International Symposium on Biomedical Imaging) s. 1 - 5
Hlavní autori: Sang, Yuling, Beetz, Marcel, Grau, Vicente
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 28.03.2022
Predmet:
ISSN:1945-8452
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Deep learning models have proven their value in the analysis of electrocardiogram (ECG). Among these, deep generative models have shown their ability in ECG generation. In this paper, we propose a conditional variational autoencoder (cVAE) to automatically generate realistic 12-lead ECG signals. Our method differs from previous papers in that (i) it generates complete 12-lead studies and (ii) generated ECGs can be adjusted to correspond to specific subject characteristics, particularly those from images. We demonstrate the ability of the model to adjust to age, sex and Body Mass Index (BMI) values. Our model is the first to incorporate imaging information by including heart position and orientation as input conditions, to analyse anatomical influences on generated ECG morphology. The network shows high accuracy and sensitivity to different conditions. In addition, our method can extract a ten-dimensional latent space containing interpreted features of the 12 ECG leads, which correspond to interpretable ECG features.
AbstractList Deep learning models have proven their value in the analysis of electrocardiogram (ECG). Among these, deep generative models have shown their ability in ECG generation. In this paper, we propose a conditional variational autoencoder (cVAE) to automatically generate realistic 12-lead ECG signals. Our method differs from previous papers in that (i) it generates complete 12-lead studies and (ii) generated ECGs can be adjusted to correspond to specific subject characteristics, particularly those from images. We demonstrate the ability of the model to adjust to age, sex and Body Mass Index (BMI) values. Our model is the first to incorporate imaging information by including heart position and orientation as input conditions, to analyse anatomical influences on generated ECG morphology. The network shows high accuracy and sensitivity to different conditions. In addition, our method can extract a ten-dimensional latent space containing interpreted features of the 12 ECG leads, which correspond to interpretable ECG features.
Author Sang, Yuling
Beetz, Marcel
Grau, Vicente
Author_xml – sequence: 1
  givenname: Yuling
  surname: Sang
  fullname: Sang, Yuling
  organization: University of Oxford,Institute of Biomedical Engineering,Department of Engineering Science,UK
– sequence: 2
  givenname: Marcel
  surname: Beetz
  fullname: Beetz, Marcel
  organization: University of Oxford,Institute of Biomedical Engineering,Department of Engineering Science,UK
– sequence: 3
  givenname: Vicente
  surname: Grau
  fullname: Grau, Vicente
  organization: University of Oxford,Institute of Biomedical Engineering,Department of Engineering Science,UK
BookMark eNotUNtOwkAUXI0mAvIFJmY_wOLe2mUfsSI2aeID4is5uz2FJdAl26LxD_xsa2ReZiYzOSeZIblqQoOE3HM24ZyZx2L5VKRiKsxEMCEmRmdcSX5BhjzLUiWMkOKSDLhRaTJVqbgh47bdsR5aKcnUgPwssMEInQ8NDTXlIikRKjrfo-ticBArHzYRDvTLd1u6PNldHyTLIzpfe_dAiwNsMHnG6D-xovkWIriud23nXUtXrW82FGgemsr__YA9_YDo4axnpy5g40KF8ZZc17BvcXzmEVm9zN_z16R8WxT5rEw8l7JL0tpxoXkNNkOmsaoY1yJDpbWxVqGyhrNe8EylVmrMLEghUBlhHfQlK0fk7v-uR8T1MfoDxO_1eTj5C1lxZqU
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ISBI52829.2022.9761431
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
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 Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 1665429232
9781665429238
EISSN 1945-8452
EndPage 5
ExternalDocumentID 9761431
Genre orig-research
GrantInformation_xml – fundername: European Commission
  funderid: 10.13039/501100000780
GroupedDBID 23N
6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i133t-5fc1271fab6e07edd01726e4779bb4e4b910bb41645b37e6ba322e492bca477b3
IEDL.DBID RIE
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000836243800032&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Fri Jul 18 03:48:17 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i133t-5fc1271fab6e07edd01726e4779bb4e4b910bb41645b37e6ba322e492bca477b3
PageCount 5
ParticipantIDs ieee_primary_9761431
PublicationCentury 2000
PublicationDate 2022-March-28
PublicationDateYYYYMMDD 2022-03-28
PublicationDate_xml – month: 03
  year: 2022
  text: 2022-March-28
  day: 28
PublicationDecade 2020
PublicationTitle Proceedings (International Symposium on Biomedical Imaging)
PublicationTitleAbbrev ISBI
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000744304
Score 2.225788
Snippet Deep learning models have proven their value in the analysis of electrocardiogram (ECG). Among these, deep generative models have shown their ability in ECG...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Analytical models
Biological system modeling
Deep learning
ECG Generation
Electrocardiography
Heart
Heart Position and Orientation
Morphology
Sensitivity
Variational Auto-encoder
Title Generation of 12-Lead Electrocardiogram with Subject-Specific, Image-Derived Characteristics Using a Conditional Variational Autoencoder
URI https://ieeexplore.ieee.org/document/9761431
WOSCitedRecordID wos000836243800032&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/eLvHCXMwlV3PS8MwFA5zeNCLPzbxNzl4XLa1TZrmqHPDgYyBOnYbTfIKPbjK7PY3-Gf7kpbpwIu3UJq2vEC-fl_e-x4hdyCch4rkzAaRYc5hjikbxyzQSkRpIjX4QtrZs5xMkvlcTRuks62FAQCffAZdN_Rn-bYwayeV9RA6Ed6R6-xJKatara2eglDIkZrXRcBBX_XGLw9j4Q4KkQWGYbeevNNFxYPI6Oh_rz8m7Z9qPDrd4swJacDylBz-MhJska_KPdoFmRYZDULmWmfSYdXjxvicU5eGRZ3sSnGzcOoL873ns9x06PgdtxX2iE_bgKWDXRNn6tMKaErxe2xeaYd0hhy71hHp_bosnB-mhVWbvI2Gr4MnVvdYYDmy05KJzAShDLJUx9CXYK3jhDFwKZXWHLjG3wkcIKkSOpIQ6xR3AOAq1CbFm3R0RprLYgnnhBqOWI_zkBBlPE2FcmxLJSCMFrIP-oK0XEwXH5WNxqIO5-Xfl6_IgVs2l-4VJtekWa7WcEP2zabMP1e3fu2_ATwzsL8
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dT8IwFG2ImqgvfoDx2z74SIFt7bo-KkJYREIiEt7I2t0le5AZHPwGf7a324KS-OJbs6xL0y337Jzeey4h9yCsh4rkLHY8w6zDHFOx7zNHK-FFgdRQFNJOh3I0CmYzNa6R5qYWBgCK5DNo2WFxlh9nZmWlsjZCJ8I7cp1dwbnrlNVaG0UFwZAjOa_KgJ2Oaoevj6GwR4XIA123VU3f6qNSwEj_6H8LOCaNn3o8Ot4gzQmpweKUHP6yEqyTr9I_2m4zzRLquMw2z6S9ssuNKbJObSIWtcIrxXBh9RdWdJ9PUtOk4TsGFvaET1tDTLvbNs60SCygEcX1xGmpHtIpsuxKSaQPqzyzjpgxLBvkrd-bdAes6rLAUuSnOROJcVzpJJH2oSMhji0r9IFLqbTmwDX-UOAAaZXQngRfRxgDgCtXmwhv0t4Z2VlkCzgn1HBEe5yHlCjhUSSU5VsqAGG0kB3QF6Ru93T-URppzKvtvPz78h3ZH0xehvNhOHq-Igf2FdrkLze4Jjv5cgU3ZM-s8_RzeVt8B9-WxrQG
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=Proceedings+%28International+Symposium+on+Biomedical+Imaging%29&rft.atitle=Generation+of+12-Lead+Electrocardiogram+with+Subject-Specific%2C+Image-Derived+Characteristics+Using+a+Conditional+Variational+Autoencoder&rft.au=Sang%2C+Yuling&rft.au=Beetz%2C+Marcel&rft.au=Grau%2C+Vicente&rft.date=2022-03-28&rft.pub=IEEE&rft.eissn=1945-8452&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FISBI52829.2022.9761431&rft.externalDocID=9761431