Combining generative modelling and semi-supervised domain adaptation for whole heart cardiovascular magnetic resonance angiography segmentation

Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA),...

Full description

Saved in:
Bibliographic Details
Published inJournal of cardiovascular magnetic resonance Vol. 25; no. 1; p. 80
Main Authors Muffoletto, Marica, Xu, Hao, Kunze, Karl P., Neji, Radhouene, Botnar, René, Prieto, Claudia, Rückert, Daniel, Young, Alistair A.
Format Journal Article
LanguageEnglish
Published London Elsevier Inc 20.12.2023
BioMed Central
BioMed Central Ltd
Subjects
Online AccessGet full text
ISSN1097-6647
1532-429X
1532-429X
DOI10.1186/s12968-023-00981-6

Cover

Abstract Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.
AbstractList Background Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. Methods Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. Results The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. Conclusions Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods. Keywords: Deep learning, Whole-heart segmentation, Domain adaptation, Generative adversarial networks, Variational auto-encoders
Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data.BACKGROUNDQuantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data.Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark.METHODSTwo state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark.The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained.RESULTSThe addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained.Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.CONCLUSIONSUnsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.
Background Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. Methods Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. Results The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. Conclusions Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.
Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.
Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.
BackgroundQuantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data.MethodsTwo state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark.ResultsThe addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained.ConclusionsUnsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.
ArticleNumber 80
Audience Academic
Author Xu, Hao
Neji, Radhouene
Botnar, René
Prieto, Claudia
Young, Alistair A.
Kunze, Karl P.
Muffoletto, Marica
Rückert, Daniel
Author_xml – sequence: 1
  givenname: Marica
  orcidid: 0000-0003-0756-0054
  surname: Muffoletto
  fullname: Muffoletto, Marica
  email: marica.muffoletto@kcl.ac.uk
  organization: School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, SW1 7EH, London, UK
– sequence: 2
  givenname: Hao
  surname: Xu
  fullname: Xu, Hao
  organization: School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, SW1 7EH, London, UK
– sequence: 3
  givenname: Karl P.
  surname: Kunze
  fullname: Kunze, Karl P.
  organization: School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, SW1 7EH, London, UK
– sequence: 4
  givenname: Radhouene
  surname: Neji
  fullname: Neji, Radhouene
  organization: School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, SW1 7EH, London, UK
– sequence: 5
  givenname: René
  surname: Botnar
  fullname: Botnar, René
  organization: School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, SW1 7EH, London, UK
– sequence: 6
  givenname: Claudia
  surname: Prieto
  fullname: Prieto, Claudia
  organization: School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, SW1 7EH, London, UK
– sequence: 7
  givenname: Daniel
  surname: Rückert
  fullname: Rückert, Daniel
  organization: Biomedical Image Analysis Group, Department of Computing, Imperial College London, London, UK
– sequence: 8
  givenname: Alistair A.
  surname: Young
  fullname: Young, Alistair A.
  organization: School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, SW1 7EH, London, UK
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38124106$$D View this record in MEDLINE/PubMed
BookMark eNqNkl2LEzEUhgdZcT_0D3ghA4J4M2uSSZMMCMtS_IIFbxS8C2lyZpplJqnJTJf-Cv-yp7barcgiuUhInvdN8p5zXpyEGKAonlNySakSbzJljVAVYXVFSKNoJR4VZ3RWs4qz5tsJrkkjKyG4PC3Oc74lhDaSyCfFaa0o45SIs-LHPA4LH3zoyg4CJDP6NZRDdND3200TXJlh8FWeVpDWPoMrXRyMD6VxZjUiH0PZxlTeLWMP5RJMGktrkvNxbbKdepPKwXQBRm_LBDkGEyygb-djl8xquUH_boCws3paPG5Nn-HZfr4ovr5_92X-sbr5_OHT_PqmsjMpx6oB0i7amvEZX7SKEC4VMVw23AnGHae0FUDszKkG2IIKBUaSWglg0jZGMVJfFPXOdwors7kzfa9XyQ8mbTQlehuv3sWrMV79K14tUHW1U62mxQDO4quTOSij8fr4JPil7uIaPWWNr5qhw-u9Q4rfJ8ijHny2GLYJEKesWUP4TPKm4Yi-_Au9jVMKmApSlDMleC0OVGd60D60ES-2W1N9LaVQioq6RuryHxQOh7W12Fatx_0jwat7AqxqPy5z7KdtjfIx-OJ-JH-y-N1iCLAdYFPMOUH7f0Hvy5MRDh2kw98fVL3dqQA7Z-1Rla0HbDfnE9hRu-gfkv8Es8QIJw
Cites_doi 10.1109/TMI.2021.3090412
10.1371/journal.pone.0230415
10.1016/j.ahj.2005.03.022
10.24963/ijcai.2018/96
10.1016/j.media.2019.101537
10.1109/ICCV.2017.244
10.1109/VCIP47243.2019.8965736
10.1016/j.media.2016.02.006
10.1007/s10334-015-0521-4
10.1038/s41592-020-01008-z
10.1161/CIRCIMAGING.119.009214
10.1109/TMI.2018.2837502
10.1186/s12968-020-00611-5
10.18773/austprescr.2017.045
10.1186/s12968-015-0170-9
10.1007/978-3-031-23443-9_9
10.1109/42.796284
10.14797/mdcj-10-3-139
10.1007/s10994-009-5152-4
10.1109/TMI.2020.2972701
10.1609/aaai.v33i01.3301865
ContentType Journal Article
Copyright 2023 © 2023 THE AUTHORS. Published by Elsevier Inc on behalf of the Society for Cardiovascular Magnetic Resonance
The Author(s) 2023
2023. The Author(s).
COPYRIGHT 2023 BioMed Central Ltd.
2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2023 © 2023 THE AUTHORS. Published by Elsevier Inc on behalf of the Society for Cardiovascular Magnetic Resonance
– notice: The Author(s) 2023
– notice: 2023. The Author(s).
– notice: COPYRIGHT 2023 BioMed Central Ltd.
– notice: 2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 6I.
AAFTH
C6C
AAYXX
CITATION
NPM
3V.
7SC
7SP
7U5
7X7
7XB
88E
8FD
8FE
8FG
8FH
8FI
8FJ
8FK
ABUWG
AFKRA
ARAPS
AZQEC
BBNVY
BENPR
BGLVJ
BHPHI
CCPQU
DWQXO
FR3
FYUFA
GHDGH
GNUQQ
HCIFZ
JQ2
K9.
L7M
LK8
L~C
L~D
M0S
M1P
M7P
M7Z
P5Z
P62
P64
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
7X8
5PM
ADTOC
UNPAY
DOI 10.1186/s12968-023-00981-6
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
Springer Nature OA Free Journals
CrossRef
PubMed
ProQuest Central (Corporate)
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Solid State and Superconductivity Abstracts
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Medical Database (Alumni Edition)
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Natural Science Journals
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
Biological Science Collection
ProQuest Central
Technology Collection
Natural Science Collection
ProQuest One Community College
ProQuest Central
Engineering Research Database
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
ProQuest Health & Medical Complete (Alumni)
Advanced Technologies Database with Aerospace
Biological Sciences
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Health & Medical Collection (Alumni Edition)
ProQuest Medical Database
Biological Science Database
Biochemistry Abstracts 1
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
Biotechnology and BioEngineering Abstracts
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
PubMed
Publicly Available Content Database
ProQuest Central Student
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
SciTech Premium Collection
ProQuest Central China
ProQuest One Applied & Life Sciences
Health Research Premium Collection
Natural Science Collection
Health & Medical Research Collection
Biological Science Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
Advanced Technologies & Aerospace Collection
ProQuest Biological Science Collection
ProQuest One Academic Eastern Edition
Electronics & Communications Abstracts
ProQuest Hospital Collection
ProQuest Technology Collection
Health Research Premium Collection (Alumni)
Biological Science Database
ProQuest Hospital Collection (Alumni)
Biotechnology and BioEngineering Abstracts
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
Solid State and Superconductivity Abstracts
Engineering Research Database
ProQuest One Academic
ProQuest One Academic (New)
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Natural Science Collection
ProQuest Central
ProQuest Health & Medical Research Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Advanced Technologies Database with Aerospace
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest Medical Library
Biochemistry Abstracts 1
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic



PubMed
Publicly Available Content Database

Database_xml – sequence: 1
  dbid: C6C
  name: Springer Nature OA Free Journals
  url: http://www.springeropen.com/
  sourceTypes: Publisher
– sequence: 2
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
– sequence: 4
  dbid: 8FG
  name: ProQuest Technology Collection
  url: https://search.proquest.com/technologycollection1
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 1532-429X
ExternalDocumentID 10.1186/s12968-023-00981-6
PMC10734115
A776881633
38124106
10_1186_s12968_023_00981_6
S1097664724010548
Genre Journal Article
GrantInformation_xml – fundername: EPSRC Centre for Doctoral Training in Medical Imaging
  grantid: EP/S022104/1
  funderid: http://dx.doi.org/10.13039/501100013915
– fundername: EPSRC Centre for Doctoral Training in Medical Imaging
  grantid: EP/S022104/1
GroupedDBID ---
-5E
-5G
-A0
-BR
0R~
29K
2WC
36B
3V.
53G
5GY
5VS
6I.
7X7
88E
8FE
8FG
8FH
8FI
8FJ
AAFTH
AAFWJ
AAJSJ
AAWTL
ABDBF
ABMYL
ABUWG
ABVAZ
ACGEJ
ACGFO
ACGFS
ACIWK
ACPRK
ACRMQ
ADBBV
ADCVX
ADINQ
ADRAZ
ADXPE
AENEX
AFGXO
AFKRA
AFNRJ
AFPKN
AFRAH
AHBYD
AHMBA
AHYZX
AJWEG
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMTXH
AOIJS
ARAPS
B0M
BAPOH
BAWUL
BBNVY
BCNDV
BENPR
BFQNJ
BGLVJ
BHPHI
BMC
BPHCQ
BVXVI
C24
C6C
CCPQU
CS3
D-I
DIK
DU5
E3Z
EAD
EAP
EBC
EBD
EBS
EMB
EMK
EMOBN
EPL
EST
ESX
F5P
FDB
FRP
FYUFA
GROUPED_DOAJ
GX1
HCIFZ
HMCUK
HYE
IAO
IHR
IHW
INH
INR
ITC
KQ8
LK8
M1P
M7P
M~E
O5R
O5S
OK1
P2P
P62
P6G
PIMPY
PQQKQ
PROAC
PSQYO
RBZ
RNS
RPM
RSV
SMD
SOJ
SV3
TFW
TR2
TUS
UKHRP
ZA5
ZCN
~8M
.1-
.FO
AALRI
AAXUO
AAYWO
ACVFH
ADCNI
ADVLN
AEUPX
AFJKZ
AFPUW
AFRHN
AIGII
AITUG
AJUYK
AKBMS
AKYEP
AMRAJ
M41
M48
OVT
PHGZM
PHGZT
PJZUB
PPXIY
PQGLB
PUEGO
ROL
TDBHL
Z5R
2VQ
4.4
AAYXX
ACUHS
ADUKV
AFFHD
AHSBF
APXCP
AQTUD
AWYRJ
CAG
CITATION
COF
EBLON
EJD
H13
HZ~
IPNFZ
O9-
RIG
AFCTW
ALIPV
NPM
7SC
7SP
7U5
7XB
8FD
8FK
AZQEC
DWQXO
FR3
GNUQQ
JQ2
K9.
L7M
L~C
L~D
M7Z
P64
PKEHL
PQEST
PQUKI
PRINS
7X8
5PM
ADTOC
UNPAY
ID FETCH-LOGICAL-c577t-9e0fbf32454bf8004780a4794d624d411f6e0c5d89e2b168ea70386e27c9a8203
IEDL.DBID M48
ISSN 1097-6647
1532-429X
IngestDate Sun Oct 26 04:06:05 EDT 2025
Tue Sep 30 17:10:30 EDT 2025
Tue Sep 30 21:35:03 EDT 2025
Tue Oct 07 05:56:52 EDT 2025
Mon Oct 20 23:11:20 EDT 2025
Mon Oct 20 17:09:08 EDT 2025
Thu May 22 21:17:10 EDT 2025
Mon Jul 21 06:06:45 EDT 2025
Wed Oct 29 21:10:42 EDT 2025
Sat Sep 06 07:28:48 EDT 2025
Sat Mar 23 16:30:20 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Deep learning
Domain adaptation
Generative adversarial networks
Variational auto-encoders
Whole-heart segmentation
Language English
License http://creativecommons.org/licenses/by-nc-nd/4.0
2023. The Author(s).
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.
cc-by-nc-nd
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c577t-9e0fbf32454bf8004780a4794d624d411f6e0c5d89e2b168ea70386e27c9a8203
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-0756-0054
OpenAccessLink http://journals.scholarsportal.info/openUrl.xqy?doi=10.1186/s12968-023-00981-6
PMID 38124106
PQID 2914286436
PQPubID 55371
ParticipantIDs unpaywall_primary_10_1186_s12968_023_00981_6
pubmedcentral_primary_oai_pubmedcentral_nih_gov_10734115
proquest_miscellaneous_2904574994
proquest_journals_2914286436
gale_infotracmisc_A776881633
gale_infotracacademiconefile_A776881633
gale_healthsolutions_A776881633
pubmed_primary_38124106
crossref_primary_10_1186_s12968_023_00981_6
springer_journals_10_1186_s12968_023_00981_6
elsevier_sciencedirect_doi_10_1186_s12968_023_00981_6
PublicationCentury 2000
PublicationDate 2023-12-20
PublicationDateYYYYMMDD 2023-12-20
PublicationDate_xml – month: 12
  year: 2023
  text: 2023-12-20
  day: 20
PublicationDecade 2020
PublicationPlace London
PublicationPlace_xml – name: London
– name: England
– name: New York
PublicationTitle Journal of cardiovascular magnetic resonance
PublicationTitleAbbrev J Cardiovasc Magn Reson
PublicationTitleAlternate J Cardiovasc Magn Reson
PublicationYear 2023
Publisher Elsevier Inc
BioMed Central
BioMed Central Ltd
Publisher_xml – name: Elsevier Inc
– name: BioMed Central
– name: BioMed Central Ltd
References Isensee, Jaeger, Kohl, Petersen, Maier-Hein (bib11) 2021; 18
VCIP.
Dou Q, Ouyang C, Chen C, Chen H, Heng P. Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss. IJCAI. 2018.
The MONAI Consortium (bib9) 2020
Stokes, Roberts-Thomson (bib16) 2017; 40
Bernard, Lalande, Zotti, Cervenansky, Yang, Heng, Cetin (bib2) 2018; 37
Xu, Niederer, Williams, Newby, Williams, Young (bib21) 2021
Muffoletto M, Xu H, Barbaroux H, Kunze KP, Neji R, Botnar R, Prieto C, Rueckert D, Young A. Comparison of semi- and un-supervised domain adaptation methods for whole-heart segmentation. In Statistical Atlases and Computational Models of the Heart. Regular and Cmrxmotion Challenge Papers. Cham: Springer Nature Switzerland; 2022, 91–100
Ben-David, Blitzer, Crammer, Kulesza, Pereira, Vaughan (bib1) 2010; 79
Peng, Lekadir, Gooya, Shao, Petersen, Frangi (bib15) 2016; 29
Luo, Shi, Li, Gao (bib12) 2020; 15
Zhu JY, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision 2017. pp. 2223–2232.
Zoghbi (bib26) 2014; 10
Zhuang, Li, Payer, Štern, Urschler, Heinrich, Oster (bib25) 2019; 58
Bustin, Rashid, Cruz, Hajhosseiny, Correia, Neji, Rajani, Ismail, Botnar, Prieto (bib4) 2020; 22
Chen, Chen, Huaqi, Giacomo, Jinming, Wenjia, Daniel (bib6) 2020
Rueckert, Sonoda, Hayes, Hill, Leach, Hawkes (bib17) 1999; 18
Luo, Zhuang (bib13) 2022
Charlier F, Weber M, Izak D, Harkin E, Magnus M, Lalli J, Fresnais L, et al, Statannotations, 2022, 10.5281/zenodo.7213391, Zenodo.
Schuijf, Bax, Shaw, de Roos, Lamb, van der Wall, Wijns (bib18) 2006; 151
Zhang T, Yang J, Zheng C, Lin G, Cai J, Kot AC. 2019. Task-in-all domain adaptation for semantic segmentation. IEEE International Conference on Visual Communications and Image Processing
.
Chen, Dou, Chen, Qin, Heng (bib7) 2019; 33
Chen, Dou, Chen, Qin, Heng (bib8) 2020; 39
Wu, Zhuang (bib20) 2021; 40
Zhuang, Shen (bib24) 2016; 31
Bhuva, Bai, Lau, Davies, Ye, Bulluck, McAlindon, Culotta, Swoboda, Captur, Treibel, Augusto, Knott, Seraphim, Cole, Petersen, Edwards, Greenwood, Bucciarelli-Ducci, Hughes, Rueckert, Moon, Manisty (bib3) 2019; 12
Suinesiaputra, Bluemke, Cowan, Friedrich, Kramer, Kwong, Plein, Schulz-Menger, Westenberg, Young, Nagel (bib19) 2015; 17
Luo (10.1186/s12968-023-00981-6_bib12) 2020; 15
Bhuva (10.1186/s12968-023-00981-6_bib3) 2019; 12
The MONAI Consortium (10.1186/s12968-023-00981-6_bib9) 2020
Zoghbi (10.1186/s12968-023-00981-6_bib26) 2014; 10
Xu (10.1186/s12968-023-00981-6_bib21) 2021
Zhuang (10.1186/s12968-023-00981-6_bib24) 2016; 31
10.1186/s12968-023-00981-6_bib14
Rueckert (10.1186/s12968-023-00981-6_bib17) 1999; 18
Bustin (10.1186/s12968-023-00981-6_bib4) 2020; 22
Schuijf (10.1186/s12968-023-00981-6_bib18) 2006; 151
10.1186/s12968-023-00981-6_bib5
10.1186/s12968-023-00981-6_bib10
Chen (10.1186/s12968-023-00981-6_bib6) 2020
Isensee (10.1186/s12968-023-00981-6_bib11) 2021; 18
Chen (10.1186/s12968-023-00981-6_bib7) 2019; 33
Stokes (10.1186/s12968-023-00981-6_bib16) 2017; 40
Wu (10.1186/s12968-023-00981-6_bib20) 2021; 40
Ben-David (10.1186/s12968-023-00981-6_bib1) 2010; 79
Chen (10.1186/s12968-023-00981-6_bib8) 2020; 39
Luo (10.1186/s12968-023-00981-6_bib13) 2022
Bernard (10.1186/s12968-023-00981-6_bib2) 2018; 37
Suinesiaputra (10.1186/s12968-023-00981-6_bib19) 2015; 17
10.1186/s12968-023-00981-6_bib23
Peng (10.1186/s12968-023-00981-6_bib15) 2016; 29
Zhuang (10.1186/s12968-023-00981-6_bib25) 2019; 58
10.1186/s12968-023-00981-6_bib22
References_xml – volume: 15
  year: 2020
  ident: bib12
  article-title: Cardiac MR segmentation based on sequence propagation by deep learning
  publication-title: PLoS ONE
– year: 2022
  ident: bib13
  article-title: Metric: an N-dimensional information-theoretic framework for groupwise registration and deep combined computing
  publication-title: IEEE Trans Pattern Anal Mach Intell
– reference: Zhang T, Yang J, Zheng C, Lin G, Cai J, Kot AC. 2019. Task-in-all domain adaptation for semantic segmentation. IEEE International Conference on Visual Communications and Image Processing
– year: 2020
  ident: bib9
  article-title: Project MONAI
  publication-title: Zenodo
– volume: 10
  start-page: 139
  year: 2014
  end-page: 145
  ident: bib26
  article-title: Cardiovascular imaging: a glimpse into the future
  publication-title: Methodist Debakey Cardiovasc J
– volume: 18
  start-page: 203
  year: 2021
  end-page: 211
  ident: bib11
  article-title: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
  publication-title: Nat Methods
– volume: 151
  start-page: 404
  year: 2006
  end-page: 411
  ident: bib18
  article-title: Meta-analysis of comparative diagnostic performance of magnetic resonance imaging and multislice computed tomography for noninvasive coronary angiography
  publication-title: Am Heart J
– volume: 79
  start-page: 151
  year: 2010
  end-page: 175
  ident: bib1
  article-title: A theory of learning from different domains
  publication-title: Mach Learn
– reference: Charlier F, Weber M, Izak D, Harkin E, Magnus M, Lalli J, Fresnais L, et al, Statannotations, 2022, 10.5281/zenodo.7213391, Zenodo.
– volume: 40
  start-page: 3555
  year: 2021
  end-page: 3667
  ident: bib20
  article-title: Unsupervised domain adaptation with variational approximation for cardiac segmentation
  publication-title: IEEE Trans Med Imaging
– volume: 18
  start-page: 712
  year: 1999
  end-page: 721
  ident: bib17
  article-title: Nonrigid registration using free-form deformations: application to breast MR images
  publication-title: IEEE Trans Med Imaging
– volume: 22
  start-page: 24
  year: 2020
  ident: bib4
  article-title: 3D whole-heart isotropic sub-millimeter resolution coronary magnetic resonance angiography with non-rigid motion-compensated PROST
  publication-title: J Cardiovasc Magn Reson
– volume: 39
  start-page: 2494
  year: 2020
  ident: bib8
  article-title: “Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation
  publication-title: IEEE Trans Med Imaging
– volume: 17
  start-page: 63
  year: 2015
  ident: bib19
  article-title: Quantification of LV function and mass by cardiovascular magnetic resonance: multi-center variability and consensus contours
  publication-title: J Cardiovasc Magn Reson
– reference: Dou Q, Ouyang C, Chen C, Chen H, Heng P. Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss. IJCAI. 2018.
– volume: 12
  year: 2019
  ident: bib3
  article-title: A multicenter, scan-rescan, human and machine learning cmr study to test generalizability and precision in imaging biomarker analysis
  publication-title: Circ Cardiovasc Imaging
– volume: 37
  start-page: 2514
  year: 2018
  end-page: 2525
  ident: bib2
  article-title: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?
  publication-title: IEEE Trans Med Imaging
– reference: .
– start-page: 63
  year: 2021
  end-page: 70
  ident: bib21
  article-title: Whole heart anatomical refinement from ccta using extrapolation and parcellation
  publication-title: VY Wang Functional Imaging and Modeling of the Heart
– year: 2020
  ident: bib6
  article-title: Deep learning for cardiac image segmentation: a review
  publication-title: Front Cardiovasc Med
– volume: 58
  year: 2019
  ident: bib25
  article-title: Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge
  publication-title: Med Image Anal
– reference: VCIP.
– reference: Muffoletto M, Xu H, Barbaroux H, Kunze KP, Neji R, Botnar R, Prieto C, Rueckert D, Young A. Comparison of semi- and un-supervised domain adaptation methods for whole-heart segmentation. In Statistical Atlases and Computational Models of the Heart. Regular and Cmrxmotion Challenge Papers. Cham: Springer Nature Switzerland; 2022, 91–100
– volume: 29
  start-page: 155
  year: 2016
  end-page: 195
  ident: bib15
  article-title: A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging
  publication-title: Magn Reson Mater Phys, Biol Med
– volume: 40
  start-page: 151
  year: 2017
  ident: bib16
  article-title: The role of cardiac imaging in clinical practice
  publication-title: Austr Prescr
– reference: Zhu JY, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision 2017. pp. 2223–2232.
– volume: 31
  start-page: 77
  year: 2016
  end-page: 87
  ident: bib24
  article-title: Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI
  publication-title: Med Image Anal
– volume: 33
  start-page: 865
  year: 2019
  ident: bib7
  article-title: Synergistic image and feature adaptation: towards cross-modality domain adaptation for medical image segmentation
  publication-title: AAAI.
– volume: 40
  start-page: 3555
  issue: 2
  year: 2021
  ident: 10.1186/s12968-023-00981-6_bib20
  article-title: Unsupervised domain adaptation with variational approximation for cardiac segmentation
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2021.3090412
– start-page: 63
  year: 2021
  ident: 10.1186/s12968-023-00981-6_bib21
  article-title: Whole heart anatomical refinement from ccta using extrapolation and parcellation
– volume: 15
  issue: 4
  year: 2020
  ident: 10.1186/s12968-023-00981-6_bib12
  article-title: Cardiac MR segmentation based on sequence propagation by deep learning
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0230415
– volume: 151
  start-page: 404
  issue: 2
  year: 2006
  ident: 10.1186/s12968-023-00981-6_bib18
  article-title: Meta-analysis of comparative diagnostic performance of magnetic resonance imaging and multislice computed tomography for noninvasive coronary angiography
  publication-title: Am Heart J
  doi: 10.1016/j.ahj.2005.03.022
– ident: 10.1186/s12968-023-00981-6_bib10
  doi: 10.24963/ijcai.2018/96
– volume: 58
  year: 2019
  ident: 10.1186/s12968-023-00981-6_bib25
  article-title: Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge
  publication-title: Med Image Anal
  doi: 10.1016/j.media.2019.101537
– ident: 10.1186/s12968-023-00981-6_bib23
  doi: 10.1109/ICCV.2017.244
– ident: 10.1186/s12968-023-00981-6_bib22
  doi: 10.1109/VCIP47243.2019.8965736
– volume: 31
  start-page: 77
  year: 2016
  ident: 10.1186/s12968-023-00981-6_bib24
  article-title: Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI
  publication-title: Med Image Anal
  doi: 10.1016/j.media.2016.02.006
– volume: 29
  start-page: 155
  issue: 2
  year: 2016
  ident: 10.1186/s12968-023-00981-6_bib15
  article-title: A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging
  publication-title: Magn Reson Mater Phys, Biol Med
  doi: 10.1007/s10334-015-0521-4
– year: 2020
  ident: 10.1186/s12968-023-00981-6_bib9
  article-title: Project MONAI
  publication-title: Zenodo
– volume: 18
  start-page: 203
  issue: 2
  year: 2021
  ident: 10.1186/s12968-023-00981-6_bib11
  article-title: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
  publication-title: Nat Methods
  doi: 10.1038/s41592-020-01008-z
– year: 2022
  ident: 10.1186/s12968-023-00981-6_bib13
  article-title: Metric: an N-dimensional information-theoretic framework for groupwise registration and deep combined computing
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 12
  issue: 10
  year: 2019
  ident: 10.1186/s12968-023-00981-6_bib3
  article-title: A multicenter, scan-rescan, human and machine learning cmr study to test generalizability and precision in imaging biomarker analysis
  publication-title: Circ Cardiovasc Imaging
  doi: 10.1161/CIRCIMAGING.119.009214
– volume: 37
  start-page: 2514
  issue: 11
  year: 2018
  ident: 10.1186/s12968-023-00981-6_bib2
  article-title: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2018.2837502
– volume: 22
  start-page: 24
  issue: 1
  year: 2020
  ident: 10.1186/s12968-023-00981-6_bib4
  article-title: 3D whole-heart isotropic sub-millimeter resolution coronary magnetic resonance angiography with non-rigid motion-compensated PROST
  publication-title: J Cardiovasc Magn Reson
  doi: 10.1186/s12968-020-00611-5
– volume: 40
  start-page: 151
  issue: 4
  year: 2017
  ident: 10.1186/s12968-023-00981-6_bib16
  article-title: The role of cardiac imaging in clinical practice
  publication-title: Austr Prescr
  doi: 10.18773/austprescr.2017.045
– volume: 17
  start-page: 63
  issue: 1
  year: 2015
  ident: 10.1186/s12968-023-00981-6_bib19
  article-title: Quantification of LV function and mass by cardiovascular magnetic resonance: multi-center variability and consensus contours
  publication-title: J Cardiovasc Magn Reson
  doi: 10.1186/s12968-015-0170-9
– ident: 10.1186/s12968-023-00981-6_bib5
– ident: 10.1186/s12968-023-00981-6_bib14
  doi: 10.1007/978-3-031-23443-9_9
– volume: 18
  start-page: 712
  issue: 8
  year: 1999
  ident: 10.1186/s12968-023-00981-6_bib17
  article-title: Nonrigid registration using free-form deformations: application to breast MR images
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/42.796284
– volume: 10
  start-page: 139
  issue: 3
  year: 2014
  ident: 10.1186/s12968-023-00981-6_bib26
  article-title: Cardiovascular imaging: a glimpse into the future
  publication-title: Methodist Debakey Cardiovasc J
  doi: 10.14797/mdcj-10-3-139
– volume: 79
  start-page: 151
  issue: 1–2
  year: 2010
  ident: 10.1186/s12968-023-00981-6_bib1
  article-title: A theory of learning from different domains
  publication-title: Mach Learn
  doi: 10.1007/s10994-009-5152-4
– year: 2020
  ident: 10.1186/s12968-023-00981-6_bib6
  article-title: Deep learning for cardiac image segmentation: a review
  publication-title: Front Cardiovasc Med
– volume: 39
  start-page: 2494
  year: 2020
  ident: 10.1186/s12968-023-00981-6_bib8
  article-title: “Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2020.2972701
– volume: 33
  start-page: 865
  year: 2019
  ident: 10.1186/s12968-023-00981-6_bib7
  article-title: Synergistic image and feature adaptation: towards cross-modality domain adaptation for medical image segmentation
  publication-title: AAAI.
  doi: 10.1609/aaai.v33i01.3301865
SSID ssj0019707
Score 2.3934855
Snippet Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of...
Background Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are...
Background Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are...
BackgroundQuantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are...
SourceID unpaywall
pubmedcentral
proquest
gale
pubmed
crossref
springer
elsevier
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 80
SubjectTerms Adaptation
Anatomy
Angiography
Angiology
Benchmarks
Cardiology
Cardiovascular diseases
Computed tomography
CT imaging
Datasets
Deep learning
Domain adaptation
Generative adversarial networks
Heart
Heart diseases
High resolution
Image processing
Imaging
Machine learning
Magnetic resonance
Medical imaging
Medicine
Medicine & Public Health
Modelling
Noise control
Performance enhancement
Radiology
Random variables
Registration
Segmentation
Signal to noise ratio
Variational auto-encoders
Whole-heart segmentation
SummonAdditionalLinks – databaseName: ProQuest Central
  dbid: BENPR
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3da9RAEB_qFfx4EL9qo1VXEHywS29zyWbzIFKlpQg9RCz0bdlkN-dBLzmbO4p_hf-yM5uPNgUPn3c2XDKzv5m52fkNwDuLNiGyOOFGKioziohn-aTgzqZpniphIl89P53Kk7Po63l8vgXTrheGrlV2mOiB2lY5_Ud-EKbEDYb-U35a_uI0NYqqq90IDdOOVrAfPcXYHdgOiRlrBNufj6bfvvd1hTTxDdRUduVSRknXRqPkQY2eTyqOPowTyabg8l-u6jZ233Bety9W9tXVB3BvXS7N7ytzcXHDgR0_godt5MkOG1N5DFuufAJ3T9va-lP4g9CQ-XERbOa5qAkImZ-UQy3rzJSW1W4x5_V6SQBTO8tstTDzkhlrlk1Jn2EMzK5o5i6jUdkrlg_uu7KFmZXUNskwy6-I68Phc2fzljcbnz9btM1Q5TM4Oz768eWEt-MaeB4nyYqnblxkBQZocZQVimgo1dgQgb2VYWTRDArpxnlsVerCTEjlDKKNki5M8tRgIDLZgVFZlW4XmDShFdI44SLcKjLMgaJERmJcOJMaUwTwodOMXjasHNpnM0rqRo8a9ai9HrUMIO6Up9u4ookXNLqNjfvekKZ105HaQ4E-TDBHUxjITgJ47yUIDFDhuWl7GvAtiFZrILk3kMRDnA-XO2vSLYjU-trkA3jbL9NOuhhXumpNMhiTJ5i2RgE8b4yv_yITCt4w5Q9ADcyyFyBq8eFKOf_pKcYFIj9qLA5gv7Pg69-16Yvt91b-H4p5sfmtX8L9kI6jCBHL92C0uly7VxgCrrLX7bn-C2vwV9w
  priority: 102
  providerName: ProQuest
– databaseName: Springer Nature OA Free Journals
  dbid: C6C
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5BkXgcEG8CBYyExIFaxNnEdo5VRVUhlROVerOc2FlW6npXZFcVv4K_zIzzYFNBBWc_5GRe32g8nwHeOdQJURWKW6mpzChyXtWzhntXlnWphc1j9fz0izw5yz-fF-c9TQ71wuzW74WWH1uMR1JzjCycqC8FlzfhFgYpGQuz8misGJQqVUNTzB_X_S3wXPXEO6Ho6jXJsVZ6D-5sw9r-uLQXFzvh6PgB3O9xJDvsBP8QbvjwCG6f9pXyx_ATDb2Kjz-weWSWJrfG4rs31IDObHCs9csFb7drchetd8ytlnYRmHV23RXoGSJadkkv6DJ6-HrD6sntVba080BNkAxz9hUxd3jcd77oWbBx__myb20KT-Ds-NPXoxPeP77A60KpDS992lQNwq0irxpNpJI6tURH72SWOxRqI31aF06XPquE1N6i79DSZ6ouLcKK2VPYC6vgnwOTNnNCWi98jktFhRlNrmQu0sbb0tomgQ-DZMy649gwMTfR0nRyNChHE-VoZALFIDzTo4Qu-hvUnWvXvSFJm66_dDRsc6gw49IIS2cJvI8zyLRR4LXtOxTwK4gkazJzfzITTbKeDg_aZHqX0JqsJHI7BIB4krfjMK2ka27Br7Y0BxG2wiQ0T-BZp3zjH5kRFMMEPgE9UctxAhGFT0fC4lskDMcUH8GKKBI4GDT497mu-2MHo5b_g2Be_N_uL-FuRuYpMvTU-7C3-b71rxDgbarX0bJ_AdG1SFY
  priority: 102
  providerName: Springer Nature
– databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lj9MwELagK_E48H4EFjASEgfWS5wmjnOsEKsV0q44UKmcLCd2SsXWrTapVvAn-MvMOA-aClbL2WMrsefxWeP5hpA3BnSC50nKtJCYZuQxy4txyazJsiKTXMc-e35yKo6n8adZMmtpcrAWZjt_z6V4X0E8EpJBZGFIfcmZuE72RAK4e0T2pqefJ199OjNLmRC-mxhYcMTAyc66Cpm_LvKvKLTrlrfi0u6byT5xepvc3Li1_nGhz862YtPR3abJUeUpDfFJyvfDTZ0fFj93CB-v9tv3yJ0WotJJo1P3yTXrHpAbJ20S_iH5BT4k930l6NyTVqPHpL6lDta2U-0MrexywarNGj1RZQ01q6VeOKqNXje5fwpgmV5gc16KPbVrWgwextKlnjusr6TnFi8LoJqw7nzREmzD-vNlWzXlHpHp0ccvH45Z29eBFUma1iyzYZmXgOSSOC8l8lXKUCPTvRFRbEBfSmHDIjEys1HOhbQa3JIUNkqLTANiGT8mI7dy9imhQkeGC225jWEqz-GyFKci5mFpdaZ1GZB33TmrdUPfofy1RwrV7LGCPVZ-j5UISNKpgmoBSAMsFJzPpfNeod6opnS19xlqksJlTgLiHQfkrZdArwHqU-i2-AH-Avm3BpL7A0mw9mI43Ommar1NpaIMefMAW8KXvO6HcSa-oHN2tUEZAO8p3G_jgDxpVLnfkTGiPB7CbDlQ8l4AOciHI27xzXORcwgRcGJJQA46e_jzXZft2EFvM1c4mGf_J_6c3IrQdHgEQWCfjOrzjX0B2LHOX7ZO4zf_amLQ
  priority: 102
  providerName: Unpaywall
Title Combining generative modelling and semi-supervised domain adaptation for whole heart cardiovascular magnetic resonance angiography segmentation
URI https://dx.doi.org/10.1186/s12968-023-00981-6
https://link.springer.com/article/10.1186/s12968-023-00981-6
https://www.ncbi.nlm.nih.gov/pubmed/38124106
https://www.proquest.com/docview/2914286436
https://www.proquest.com/docview/2904574994
https://pubmed.ncbi.nlm.nih.gov/PMC10734115
https://doi.org/10.1186/s12968-023-00981-6
UnpaywallVersion publishedVersion
Volume 25
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVADU
  databaseName: BioMedCentral
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: RBZ
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://www.biomedcentral.com/search/
  providerName: BioMedCentral
– providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: KQ8
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAON
  databaseName: Directory of Open Access Journals
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: DOA
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVBFR
  databaseName: Free Medical Journals
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: DIK
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: http://www.freemedicaljournals.com
  providerName: Flying Publisher
– providerCode: PRVFQY
  databaseName: GFMER Free Medical Journals
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: GX1
  dateStart: 0
  isFulltext: true
  titleUrlDefault: http://www.gfmer.ch/Medical_journals/Free_medical.php
  providerName: Geneva Foundation for Medical Education and Research
– providerCode: PRVLSH
  databaseName: Elsevier Journals
  customDbUrl:
  mediaType: online
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: AKRWK
  dateStart: 20081022
  isFulltext: true
  providerName: Library Specific Holdings
– providerCode: PRVAQN
  databaseName: PubMed Central
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: RPM
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://www.ncbi.nlm.nih.gov/pmc/
  providerName: National Library of Medicine
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl: http://www.proquest.com/pqcentral?accountid=15518
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: BENPR
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Health & Medical Collection
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: 7X7
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Technology Collection
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: 8FG
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/technologycollection1
  providerName: ProQuest
– providerCode: PRVFZP
  databaseName: Scholars Portal Journals: Open Access
  customDbUrl:
  eissn: 1532-429X
  dateEnd: 20250430
  omitProxy: true
  ssIdentifier: ssj0019707
  issn: 1532-429X
  databaseCode: M48
  dateStart: 20081001
  isFulltext: true
  titleUrlDefault: http://journals.scholarsportal.info
  providerName: Scholars Portal
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1bb9MwFLZ2kWA8IO4LjGIkJB6YR5M6tvOAUKlWJqRWE6JSebKcxCmV2rSsrcZ-BX-Zc5zLlmkMXiJFvij1uX2nx-ccQt6kwBN-HEpmhMIwo89ZnHQyZtMoSiLlG-6i54OhOBnxL-NwvEWqdkflAa5udO2wn9TobHb06-fFRxD4D07glXi_ApslFAPrw7A8ps_ENtkFSxVhK4cBv4wqRNKlT2PQlQnBZZVEc-MefzNU1zX3FdN1_VplHVu9R-5u8qW5ODez2RXz1X9A7pe4k3YLRnlItmz-iNwZlJH1x-Q3KIbYNYugE1eJGtUgdX1yMGGdmjylKzufstVmieplZVOaLuZmmlOTmmUR0KeAgOk5dtyl2Ch7TZPGbVc6N5MckyYp-PgLrPRhYd_JtKyaDftP5mUqVP6EjPrH33onrGzWwJJQyjWLbDuLM4BnIY8zhUUoVdtg-fpUBDwFJsiEbSdhqiIbxL5Q1oCuUcIGMokMwJDOU7KTL3K7T6gwQeoLY33LYakfgwfEpeB-O7MmMibzyLuKMnpZ1OTQzpdRQhd01EBH7eiohUfCini6RBUFWtDAQ7eue4WU1kU-aq0IdFeCh6YAxnY88tbNQOYEgiemzGiAX4FFtRozDxozQYST5nDFTbqSAB1EWAwPACN8yet6GFfitbjcLjY4BxC5BKeVe-RZwXz1iXQQuoHD7xHVYMt6AhYWb47k0x-uwLgPeh8oFnrksOLgy--67cQOay7_D8I8_-cBvyB7AUqkH4AyPyA767ONfQkYcB23yLYcS3iq_ucW2f10PDz9Cm890Wu5f1VaTvBhZDQ87X7_A29xXJQ
linkProvider Scholars Portal
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELZKkSgcEK9CoFAjgThQq-us4zgHhCqg2tJuT63Um3FiZ1mpm12aXa36K_gn_EZmnEebSqy49OyHknzjb2YynhlC3lmQCZ5GMTNSYZiRC5Zm_Zw5myRZorgRPno-PJaDU_H9LDpbI3-aXBi8VtlwoidqO83wH_lumGBtMNCf8vPsF8OuURhdbVpoVGJx6C6X4LKVnw6-Ar7vw3D_28mXAau7CrAsiuM5S1wvT3OwIyKR5gqrJaqewTrrVobCwtPm0vWyyKrEhSmXyhk4FEq6MM4SA_qyD_veIXdFH7gEzk981jp4PIl9ejYGdZmUIm6SdJTcLUGvSsVAQzIs4cmZ_JcivKkZrqnGm9c229jtA7KxKGbmcmnOz6-px_1H5GFt19K9ShAfkzVXPCH3hnXk_in5DcST-mYUdOQrXSPNUt-HBxPiqSksLd1kzMrFDOmrdJba6cSMC2qsmVUXBihY2HSJHX0pNuKe06xzm5ZOzKjApEx64dDDAHmGfUfjuio37D-a1KlWxTNyeiuwbZL1Ylq4F4RKE1oujeNOwFKegoclYil4L3cmMSYPyMcGGT2ran5o7yspqSscNeCoPY5aBiRqwNO11VJZIxqU0sp124i0rvJdW6LRezF4gArM5H5APvgZSDUAeGbqjAl4Cyza1Zm51ZkJFJF1hxtp0jVFlfrqQAXkbTuMK_HaXeGmC5wDFn8MTrEIyPNK-Nov0kfTkPdgteqIZTsBC5d3R4rxT1_AnINeAcSigOw0Enz1XKu-2E4r5f8BzMvVb71NNgYnwyN9dHB8-IrcD_Fo8hC0xhZZn18s3GswNufpG3_CKflx25TyF2XqjI8
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELagSIUeEK_SQKFGQuJArcZZx3GO1cKqPFpxoFJvlhM7y0pdb0SyqvgV_GVm8mJTQQXn2FaSeX2j8XxDyGsLOsGzOGFGKiwzcsGyfFIwZ9M0TxU3oqmen57Jk3Px8SK-2Ojib2679yXJtqcBWZp8fVTaojVxJY8qiFJSMYg3DAkxOZO3yR0B0Q1nGEzldKgjpEmY9K0yf9z3t3B03T9vBKjrlyeHCuoOubv2pflxZS4vN4LU7AG536FLetyqw0Nyy_lHZPu0q58_Jj_B_LNmJASdN3zT6OxoMw0H29Kp8ZZWbrlg1bpEJ1I5S-1qaRaeGmvKtmxPAefSK5yrS3Ecdk3z0Z1WujRzj62RFDL5FfJ5ODh3vui4seH8-bJrePJPyPns_dfpCetGMrA8TpKapS4ssgJAWCyyQiHVpAoNktRbGQkLoi6kC_PYqtRFGZfKGfAoSrooyVMDYGOyS7b8yrs9QqWJLJfGcSdgK88gzxGJFDwsnEmNKQLytpeMLlvmDd1kLErqVo4a5KgbOWoZkLgXnu6wQ4sJNISGG_cdoKR123U6mLs-TiAPUwBWJwF506xAgweB56brW4CvQOqs0cr90Uow1Hz8uNcm3TmKSkcpUt4BLIQ3eTU8xp14-c271RrXAO5OIDUVAXnaKt_wRyYI0CCtD4gaqeWwAOnDx0_84ltDIw6JP0AYHgfksNfg3-910x87HLT8HwTz7P9OPyDbX97N9OcPZ5-ek3sRWiqPwJXvk636-9q9AARYZy8bI_8FEzhTjA
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lj9MwELagK_E48H4EFjASEgfWS5wmjnOsEKsV0q44UKmcLCd2SsXWrTapVvAn-MvMOA-aClbL2WPLsccznzOebwh5Y0AneJ6kTAuJYUYes7wYl8yaLCsyyXXso-cnp-J4Gn-aJbOWJgdzYbbj91yK9xX4IyEZeBaG1JecietkTySAu0dkb3r6efLVhzOzlAnhq4nBCY4YGNlZlyHz10H-5YV2zfKWX9p9M9kHTm-Tmxu31j8u9NnZlm86utsUOao8pSE-Sfl-uKnzw-LnDuHj1T77HrnTQlQ6aXTqPrlm3QNy46QNwj8kv8CG5L6uBJ170mq0mNSX1MHcdqqdoZVdLli1WaMlqqyhZrXUC0e10esm9k8BLNMLLM5LsaZ2TYvBw1i61HOH-ZX03OJlAVQTxp0vWoJtGH--bLOm3CMyPfr45cMxa-s6sCJJ05plNizzEpBcEuelRL5KGWpkujciig3oSylsWCRGZjbKuZBWg1mSwkZpkWlALOPHZORWzj4lVOjIcKEttzF05TlcluJUxDwsrc60LgPyrttntW7oO5S_9kihmjVWsMbKr7ESAUk6VVAtAGmAhYL9ubTfK9Qb1aSu9jZDTVK4zElAvOOAvPUSaDVAfQrdJj_AVyD_1kByfyAJp70YNne6qVprU6koQ948wJYwk9d9M_bEF3TOrjYoA-A9hfttHJAnjSr3KzJGlMdD6C0HSt4LIAf5sMUtvnkucg4uAnYsCchBdx7-zOuyFTvoz8wVNubZ_4k_J7cA1_o_ZVG4T0b1-ca-AOxY5y9bo_Eb_25i0A
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=Combining+generative+modelling+and+semi-supervised+domain+adaptation+for+whole+heart+cardiovascular+magnetic+resonance+angiography+segmentation&rft.jtitle=Journal+of+cardiovascular+magnetic+resonance&rft.au=Young%2C+Alistair+A&rft.au=Xu%2C+Hao&rft.au=Muffoletto%2C+Marica&rft.au=R%C3%BCckert%2C+Daniel&rft.date=2023-12-20&rft.pub=BioMed+Central+Ltd&rft.issn=1097-6647&rft.volume=25&rft.issue=1&rft_id=info:doi/10.1186%2Fs12968-023-00981-6&rft.externalDBID=n%2Fa&rft.externalDocID=A776881633
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1097-6647&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1097-6647&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1097-6647&client=summon