Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach

Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. I...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging Vol. 38; no. 9; pp. 2151 - 2164
Main Authors: Duan, Jinming, Bello, Ghalib, Schlemper, Jo, Bai, Wenjia, Dawes, Timothy J. W., Biffi, Carlo, de Marvao, Antonio, Doumoud, Georgia, O'Regan, Declan P., Rueckert, Daniel
Format: Journal Article
Language:English
Published: United States IEEE 01.09.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:0278-0062, 1558-254X, 1558-254X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localization tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artifacts (e.g., due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network's ability to infer landmarks, which are then used downstream in the pipeline to initialize atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution, and anatomically smooth bi-ventricular 3D models, despite the presence of artifacts in input CMR volumes.
AbstractList Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localisation tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artefacts (e.g. due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network’s ability to infer landmarks, which are then used downstream in the pipeline to initialise atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution and anatomically smooth bi-ventricular 3D models, despite the presence of artefacts in input CMR volumes.
Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localization tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artifacts (e.g., due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network’s ability to infer landmarks, which are then used downstream in the pipeline to initialize atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution, and anatomically smooth bi-ventricular 3D models, despite the presence of artifacts in input CMR volumes.
Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localization tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artifacts (e.g., due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network's ability to infer landmarks, which are then used downstream in the pipeline to initialize atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution, and anatomically smooth bi-ventricular 3D models, despite the presence of artifacts in input CMR volumes.Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localization tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artifacts (e.g., due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network's ability to infer landmarks, which are then used downstream in the pipeline to initialize atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution, and anatomically smooth bi-ventricular 3D models, despite the presence of artifacts in input CMR volumes.
Author Biffi, Carlo
Duan, Jinming
Schlemper, Jo
de Marvao, Antonio
Doumoud, Georgia
Rueckert, Daniel
Bello, Ghalib
Dawes, Timothy J. W.
Bai, Wenjia
O'Regan, Declan P.
Author_xml – sequence: 1
  givenname: Jinming
  orcidid: 0000-0002-5108-2128
  surname: Duan
  fullname: Duan, Jinming
  email: j.duan@imperial.ac.uk
  organization: Biomedical Image Analysis Group, Imperial College London, London, U.K
– sequence: 2
  givenname: Ghalib
  orcidid: 0000-0002-7893-743X
  surname: Bello
  fullname: Bello, Ghalib
  organization: MRC London Institute of Medical Sciences, Imperial College London, London, U.K
– sequence: 3
  givenname: Jo
  orcidid: 0000-0003-1867-1155
  surname: Schlemper
  fullname: Schlemper, Jo
  organization: Biomedical Image Analysis Group, Imperial College London, London, U.K
– sequence: 4
  givenname: Wenjia
  orcidid: 0000-0003-2943-7698
  surname: Bai
  fullname: Bai, Wenjia
  organization: Biomedical Image Analysis Group, Imperial College London, London, U.K
– sequence: 5
  givenname: Timothy J. W.
  orcidid: 0000-0001-7871-524X
  surname: Dawes
  fullname: Dawes, Timothy J. W.
  organization: MRC London Institute of Medical Sciences, Imperial College London, London, U.K
– sequence: 6
  givenname: Carlo
  surname: Biffi
  fullname: Biffi, Carlo
  organization: Biomedical Image Analysis Group, Imperial College London, London, U.K
– sequence: 7
  givenname: Antonio
  orcidid: 0000-0001-9095-5887
  surname: de Marvao
  fullname: de Marvao, Antonio
  organization: MRC London Institute of Medical Sciences, Imperial College London, London, U.K
– sequence: 8
  givenname: Georgia
  surname: Doumoud
  fullname: Doumoud, Georgia
  organization: MRC London Institute of Medical Sciences, Imperial College London, London, U.K
– sequence: 9
  givenname: Declan P.
  orcidid: 0000-0002-0691-0270
  surname: O'Regan
  fullname: O'Regan, Declan P.
  organization: MRC London Institute of Medical Sciences, Imperial College London, London, U.K
– sequence: 10
  givenname: Daniel
  orcidid: 0000-0002-5683-5889
  surname: Rueckert
  fullname: Rueckert, Daniel
  organization: Biomedical Image Analysis Group, Imperial College London, London, U.K
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30676949$$D View this record in MEDLINE/PubMed
BookMark eNp9kcGL1DAUxoPs4s6u3gVBAl68dEzSJG0uwjir7sAsgjuKt5CmrzNZ26YmrbD_vRlmHHQPnkJ43_fe9_G7RGe97wGhF5TMKSXq7eZ2NWeEqjkrFc8Ze4JmVIgyY4J_P0MzwooyI0SyC3QZ4z0hlAuinqKLnMhCKq5maFhMo-_M6CzOr_F7l32DfgzOTq0J-A62Xfqmqe-xb_DShNoZi1ed2ULE1QM2-G5nBsi-QON6qPHt1I4uwxsTf-BrgAGvwYTe9Vu8GIbgjd09Q-eNaSM8P75X6OvHD5vlTbb-_Gm1XKwzyzkfs7xqKiJNilyXQpicMEGNyonlzBSsEgJyKRvWFLxRTaNq4LlQlsjalLIouMiv0LvD3mGqOqjtvpZp9RBcZ8KD9sbpfye92-mt_6VlwUoqSVrw5rgg-J8TxFF3LlpoW9ODn6JmtFBcMC73t14_kt77KfSpnmas5IzwgtKkevV3olOUPzCSgBwENvgYAzQnCSV6z1sn3nrPWx95J4t8ZLHuwCt1cu3_jC8PRgcApzulZFykJL8B6RK2TA
CODEN ITMID4
CitedBy_id crossref_primary_10_1109_ACCESS_2024_3373046
crossref_primary_10_1007_s10489_021_02720_9
crossref_primary_10_1016_j_media_2020_101685
crossref_primary_10_1186_s12968_021_00712_9
crossref_primary_10_7759_cureus_37698
crossref_primary_10_1007_s13239_020_00494_8
crossref_primary_10_1109_TMI_2023_3243069
crossref_primary_10_3389_fcvm_2021_818765
crossref_primary_10_3389_fcvm_2022_983868
crossref_primary_10_1016_j_compbiomed_2023_106998
crossref_primary_10_1016_j_compmedimag_2020_101786
crossref_primary_10_1007_s11548_024_03089_z
crossref_primary_10_1109_ACCESS_2021_3062380
crossref_primary_10_1016_j_media_2022_102498
crossref_primary_10_1016_j_artmed_2021_102189
crossref_primary_10_1016_j_media_2022_102533
crossref_primary_10_1109_TAI_2024_3394798
crossref_primary_10_1038_s41598_020_77733_4
crossref_primary_10_1186_s12968_023_00934_z
crossref_primary_10_1016_j_media_2021_102303
crossref_primary_10_1016_j_jbi_2023_104366
crossref_primary_10_1002_mrm_28294
crossref_primary_10_1016_j_compbiomed_2023_106648
crossref_primary_10_1109_ACCESS_2021_3129333
crossref_primary_10_1038_s42256_025_01035_5
crossref_primary_10_1007_s11042_022_14202_2
crossref_primary_10_1016_j_compbiomed_2020_104168
crossref_primary_10_1155_2021_4989297
crossref_primary_10_1148_ryai_230132
crossref_primary_10_1007_s11831_022_09805_9
crossref_primary_10_3390_opt3010002
crossref_primary_10_1007_s00500_021_06519_1
crossref_primary_10_1007_s12410_020_09550_2
crossref_primary_10_1016_j_ailsci_2023_100083
crossref_primary_10_1109_TMI_2022_3154599
crossref_primary_10_1186_s12968_023_00924_1
crossref_primary_10_1109_TIP_2021_3106799
crossref_primary_10_21693_1933_088X_18_4_126
crossref_primary_10_1016_j_measurement_2022_111414
crossref_primary_10_1016_j_knosys_2020_106210
crossref_primary_10_3390_medicina61010085
crossref_primary_10_1038_s41569_021_00527_2
crossref_primary_10_1016_j_compbiomed_2022_106496
crossref_primary_10_1038_s41598_023_40841_y
crossref_primary_10_1016_j_inffus_2021_01_009
crossref_primary_10_3389_frai_2023_1142895
crossref_primary_10_3390_diagnostics14242820
crossref_primary_10_1016_j_media_2020_101896
crossref_primary_10_1093_eurheartj_ehac758
crossref_primary_10_1016_j_pcad_2024_06_004
crossref_primary_10_1109_TMI_2020_3003240
crossref_primary_10_1109_TRPMS_2025_3539739
crossref_primary_10_3389_fnbot_2023_1093132
crossref_primary_10_1007_s11760_021_01978_3
crossref_primary_10_3389_fcvm_2020_00102
crossref_primary_10_1038_s41598_022_10464_w
crossref_primary_10_1109_TMI_2023_3340118
crossref_primary_10_1371_journal_pone_0309379
crossref_primary_10_1016_j_jer_2023_10_043
crossref_primary_10_1016_j_compbiomed_2024_108218
crossref_primary_10_1007_s10278_022_00708_6
crossref_primary_10_1016_j_mri_2019_07_014
crossref_primary_10_1016_j_patcog_2020_107756
crossref_primary_10_1109_ACCESS_2020_3003624
crossref_primary_10_1016_j_inffus_2023_101864
crossref_primary_10_1177_01617346221099435
crossref_primary_10_1002_pul2_70092
crossref_primary_10_3390_data4010045
crossref_primary_10_1016_j_media_2022_102383
crossref_primary_10_1016_j_jocmr_2024_101051
crossref_primary_10_1109_TMI_2024_3514869
crossref_primary_10_1007_s40747_023_00968_x
crossref_primary_10_1038_s41598_021_95526_1
crossref_primary_10_1016_j_rineng_2023_100927
crossref_primary_10_1109_ACCESS_2020_3047848
crossref_primary_10_3390_math10122099
crossref_primary_10_1016_j_neucom_2024_127379
crossref_primary_10_1016_j_compbiomed_2023_107486
crossref_primary_10_3390_app9132683
crossref_primary_10_1016_j_compmedimag_2024_102383
crossref_primary_10_1016_j_artmed_2021_102140
crossref_primary_10_1161_JAHA_119_014781
crossref_primary_10_1016_j_media_2022_102447
crossref_primary_10_1109_TMI_2020_3046672
crossref_primary_10_1016_j_compmedimag_2023_102287
crossref_primary_10_1007_s00330_023_09807_6
crossref_primary_10_1161_CIRCGEN_123_004200
crossref_primary_10_1002_ehf2_12929
crossref_primary_10_1007_s40305_025_00612_0
crossref_primary_10_3389_fcvm_2019_00195
crossref_primary_10_1016_j_compbiomed_2023_107897
crossref_primary_10_1016_j_compmedimag_2023_102203
crossref_primary_10_1016_j_media_2022_102445
crossref_primary_10_1016_j_scs_2020_102589
crossref_primary_10_1016_j_compbiomed_2024_109173
crossref_primary_10_1016_j_media_2022_102683
crossref_primary_10_1186_s12880_023_01149_5
crossref_primary_10_3390_s22062084
crossref_primary_10_1007_s10489_022_03690_2
crossref_primary_10_1002_mp_15285
crossref_primary_10_4103_jcecho_jcecho_62_25
crossref_primary_10_1016_j_knosys_2021_106776
crossref_primary_10_1109_ACCESS_2020_2986365
crossref_primary_10_1109_ACCESS_2020_2971383
crossref_primary_10_47164_ijngc_v13i3_825
crossref_primary_10_1016_j_compbiomed_2023_107266
crossref_primary_10_1109_JBHI_2023_3323533
crossref_primary_10_1109_JBHI_2021_3122581
crossref_primary_10_1016_j_jacc_2021_07_017
crossref_primary_10_1016_j_media_2023_102925
crossref_primary_10_1007_s11831_021_09667_7
crossref_primary_10_1016_j_cmpb_2023_107615
crossref_primary_10_1109_JBHI_2023_3337521
crossref_primary_10_3389_fcvm_2020_00025
crossref_primary_10_1016_j_compmedimag_2022_102088
crossref_primary_10_1109_TMI_2021_3108881
crossref_primary_10_1016_j_compbiomed_2023_106748
crossref_primary_10_1002_ima_22947
crossref_primary_10_1007_s10334_024_01180_9
crossref_primary_10_1016_j_bspc_2022_103567
crossref_primary_10_1016_j_icte_2025_07_008
crossref_primary_10_1007_s11042_021_10841_z
crossref_primary_10_1016_j_media_2021_102201
crossref_primary_10_3390_diagnostics13162667
crossref_primary_10_1016_j_media_2020_101693
Cites_doi 10.1007/978-3-319-66185-8_43
10.1186/s12968-016-0227-4
10.1016/j.media.2016.01.005
10.1007/978-3-030-04747-4_24
10.1016/j.media.2016.06.009
10.1109/TMI.2017.2743464
10.1109/TMI.2002.804426
10.1109/42.52980
10.1109/CVPR.2005.38
10.1016/j.media.2010.12.004
10.1186/s12968-018-0471-x
10.1007/s10898-015-0290-7
10.1109/TMI.2018.2820742
10.1016/j.media.2016.10.004
10.1109/EMBC.2018.8512536
10.1007/978-3-030-00937-3_68
10.1109/42.796284
10.1109/TMI.2013.2256922
10.1109/JBHI.2018.2882647
10.1007/978-3-319-66182-7_24
10.1136/heartjnl-2015-307896
10.1016/j.media.2014.09.005
10.1007/978-3-030-00928-1_30
10.1016/j.media.2016.05.009
10.1109/TMI.2018.2837502
10.1364/BOE.10.002684
10.1007/s11886-015-0563-2
10.1109/3DV.2016.79
10.1186/1532-429X-16-16
10.1016/j.media.2012.02.003
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
5PM
DOI 10.1109/TMI.2019.2894322
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Ceramic Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
Materials Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Nursing & Allied Health Premium
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Materials Research Database
Civil Engineering Abstracts
Aluminium Industry Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Ceramic Abstracts
Materials Business File
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Aerospace Database
Nursing & Allied Health Premium
Engineered Materials Abstracts
Biotechnology Research Abstracts
Solid State and Superconductivity Abstracts
Engineering Research Database
Corrosion Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
MEDLINE - Academic
DatabaseTitleList
Materials Research Database
MEDLINE - Academic

MEDLINE
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 Electronic Library (IEL)
  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 Medicine
Engineering
EISSN 1558-254X
EndPage 2164
ExternalDocumentID PMC6728160
30676949
10_1109_TMI_2019_2894322
8624549
Genre orig-research
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: National Institute for Health Research
  funderid: 10.13039/501100000272
– fundername: British Heart Foundation
  grantid: NH/17/1/32725; RE/13/4/30184
  funderid: 10.13039/501100000274
– fundername: Medical Research Council
  funderid: 10.13039/501100000265
– fundername: Engineering and Physical Sciences Research Council
  grantid: EP/P001009/1
  funderid: 10.13039/501100000266
– fundername: Medical Research Council
  grantid: MC_UP_1102/19
– fundername: Department of Health
– fundername: British Heart Foundation
  grantid: NH/17/1/32725
– fundername: British Heart Foundation
  grantid: RE/13/4/30184
GroupedDBID ---
-DZ
-~X
.GJ
0R~
29I
4.4
53G
5GY
5RE
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
ACPRK
AENEX
AETIX
AFRAH
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
ESBDL
F5P
HZ~
H~9
IBMZZ
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
VH1
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
RIG
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
5PM
ID FETCH-LOGICAL-c444t-3bfb06a001d855a30251a930c42a72b55e366f2f74f9ff9de4359c06da8677453
IEDL.DBID RIE
ISICitedReferencesCount 153
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000484290400014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0278-0062
1558-254X
IngestDate Tue Sep 30 16:56:46 EDT 2025
Sun Nov 09 12:52:27 EST 2025
Mon Jun 30 02:20:35 EDT 2025
Mon Jul 21 05:36:04 EDT 2025
Tue Nov 18 21:15:24 EST 2025
Sat Nov 29 05:14:06 EST 2025
Wed Aug 27 02:46:13 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Issue 9
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
This work is licensed under a Creative Commons Attribution 3.0 License. For more information, see http://creativecommons.org/licenses/by/3.0/.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c444t-3bfb06a001d855a30251a930c42a72b55e366f2f74f9ff9de4359c06da8677453
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-5683-5889
0000-0002-5108-2128
0000-0002-0691-0270
0000-0003-1867-1155
0000-0002-7893-743X
0000-0001-9095-5887
0000-0001-7871-524X
0000-0003-2943-7698
OpenAccessLink https://ieeexplore.ieee.org/document/8624549
PMID 30676949
PQID 2284204711
PQPubID 85460
PageCount 14
ParticipantIDs proquest_journals_2284204711
proquest_miscellaneous_2179452465
crossref_primary_10_1109_TMI_2019_2894322
ieee_primary_8624549
crossref_citationtrail_10_1109_TMI_2019_2894322
pubmedcentral_primary_oai_pubmedcentral_nih_gov_6728160
pubmed_primary_30676949
PublicationCentury 2000
PublicationDate 2019-09-01
PublicationDateYYYYMMDD 2019-09-01
PublicationDate_xml – month: 09
  year: 2019
  text: 2019-09-01
  day: 01
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on medical imaging
PublicationTitleAbbrev TMI
PublicationTitleAlternate IEEE Trans Med Imaging
PublicationYear 2019
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref34
ref15
ref36
ref14
ref31
ref30
ref33
ref11
ref32
ref2
ref1
ref17
winther (ref4) 2017
ref38
ref16
bai (ref37) 2013; 32
ref19
khened (ref10) 2018
ref18
oktay (ref21) 2016
çiçek (ref35) 2016
ref24
ref23
ref26
ref25
isensee (ref7) 2017
tarroni (ref20) 2018
ref22
baumgartner (ref6) 2017
tran (ref12) 2016
ref28
ref27
ref29
ref8
patravali (ref5) 2017
ref9
erin (ref39) 2015
ref3
ref40
References_xml – ident: ref26
  doi: 10.1007/978-3-319-66185-8_43
– ident: ref19
  doi: 10.1186/s12968-016-0227-4
– start-page: 2475
  year: 2015
  ident: ref39
  article-title: Deep hashing for compact binary codes learning
  publication-title: Proc CVPR
– year: 2017
  ident: ref5
  article-title: 2D-3D fully convolutional neural networks for cardiac MR segmentation
  publication-title: ArXiv Preprint ArXiv 1707 09813
– ident: ref15
  doi: 10.1016/j.media.2016.01.005
– ident: ref28
  doi: 10.1007/978-3-030-04747-4_24
– year: 2017
  ident: ref6
  publication-title: An exploration of 2D and 3D deep learning techniques for cardiac MR image segmentation
– ident: ref3
  doi: 10.1016/j.media.2016.06.009
– year: 2017
  ident: ref7
  publication-title: Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features
– ident: ref11
  doi: 10.1109/TMI.2017.2743464
– ident: ref30
  doi: 10.1109/TMI.2002.804426
– ident: ref38
  doi: 10.1109/42.52980
– ident: ref31
  doi: 10.1109/CVPR.2005.38
– ident: ref22
  doi: 10.1016/j.media.2010.12.004
– ident: ref13
  doi: 10.1186/s12968-018-0471-x
– ident: ref32
  doi: 10.1007/s10898-015-0290-7
– ident: ref8
  doi: 10.1109/TMI.2018.2820742
– ident: ref25
  doi: 10.1016/j.media.2016.10.004
– start-page: 424
  year: 2016
  ident: ref35
  article-title: 3D U-Net: learning dense volumetric segmentation from sparse annotation
  publication-title: Proc MICCAI
– start-page: 246
  year: 2016
  ident: ref21
  article-title: Multi-input cardiac image super-resolution using convolutional neural networks
  publication-title: Proc MICCAI
– ident: ref9
  doi: 10.1109/EMBC.2018.8512536
– ident: ref16
  doi: 10.1007/978-3-030-00937-3_68
– ident: ref29
  doi: 10.1109/42.796284
– year: 2018
  ident: ref10
  publication-title: Fully convolutional multi-scale residual densenets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers
– year: 2016
  ident: ref12
  publication-title: A fully convolutional neural network for cardiac segmentation in short-axis mri
– volume: 32
  start-page: 1302
  year: 2013
  ident: ref37
  article-title: A probabilistic patch-based label fusion model for multi-atlas segmentation with registration refinement: Application to cardiac MR images
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/TMI.2013.2256922
– ident: ref40
  doi: 10.1109/JBHI.2018.2882647
– ident: ref36
  doi: 10.1007/978-3-319-66182-7_24
– ident: ref1
  doi: 10.1136/heartjnl-2015-307896
– ident: ref34
  doi: 10.1016/j.media.2014.09.005
– ident: ref17
  doi: 10.1007/978-3-030-00928-1_30
– ident: ref14
  doi: 10.1016/j.media.2016.05.009
– ident: ref18
  doi: 10.1109/TMI.2018.2837502
– ident: ref33
  doi: 10.1364/BOE.10.002684
– ident: ref2
  doi: 10.1007/s11886-015-0563-2
– year: 2018
  ident: ref20
  publication-title: Learning-based quality control for cardiac MR images
– ident: ref24
  doi: 10.1109/3DV.2016.79
– ident: ref23
  doi: 10.1186/1532-429X-16-16
– year: 2017
  ident: ref4
  publication-title: $V$ -Net Deep learning for generalized biventricular cardiac mass and function parameters
– ident: ref27
  doi: 10.1016/j.media.2012.02.003
SSID ssj0014509
Score 2.658214
Snippet Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have...
SourceID pubmedcentral
proquest
pubmed
crossref
ieee
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 2151
SubjectTerms Algorithms
Automation
bi-ventricular CMR segmentation
cardiac artifacts
Cardiac Imaging Techniques - methods
Computer applications
Deep Learning
Heart
Heart - diagnostic imaging
Humans
Hypertension
Image processing
Image segmentation
Imaging
Imaging, Three-Dimensional - methods
label fusion
landmark localization
Localization
Machine learning
Magnetic resonance
Magnetic resonance imaging
Magnetic Resonance Imaging, Cine - methods
multi-atlas segmentation
non-rigid registration
Pipelines
Propagation
Robustness (mathematics)
Shape
shape prior
Three dimensional models
Three-dimensional displays
Ventricle
Title Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach
URI https://ieeexplore.ieee.org/document/8624549
https://www.ncbi.nlm.nih.gov/pubmed/30676949
https://www.proquest.com/docview/2284204711
https://www.proquest.com/docview/2179452465
https://pubmed.ncbi.nlm.nih.gov/PMC6728160
Volume 38
WOSCitedRecordID wos000484290400014&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-254X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014509
  issn: 0278-0062
  databaseCode: RIE
  dateStart: 19820101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9QwDLe2CSF44GMDVhhTkHhBors0SdPm8diYmMQmxI7p3qqkdbYTW--0u0PivydJc9UNTUi8VYobpbVd27X9M8B7Z-VkLXKbypLzVFhDU4PGyTItjRMQkxUBp_via3F2Vo7H6tsGfOx7YRAxFJ_hgb8MufxmWi_9r7KBb2Zw8cwmbBaF7Hq1-oyByLtyDuYRY6lkq5QkVYPR6Ymv4VIHzIONMz_AxjvKUnkAzTVrFMar3Odp_l0wuWaBjp_-39mfwZPoaZJhJxrPYQPbbXi8hj-4DQ9PY2Z9B2bD5WIa4FsJPyKfJumFP8QkVKmSc7y8iT1KLZlachjEqiYnN-5rNCfmN9Hk_ErPMP2O1m3XkNDXm5KRnv8kR4gzEnFcL8kwgpi_gB_Hn0eHX9I4jSGthRCLlBvHSKndq27KPNfcBydacVoLpgtm8hy5lJbZQlhlrWrQOWKqprLRHjJP5PwlbLXTFneBoDQcFWbGunCuZk1pS5UprK2mpUVOExisuFLVEarcT8y4rkLIQlXlWFp5llaRpQl86O-YdTAd_6Dd8ezp6SJnEthbMb6KejyvmLPejDoDniXwrl92GujTKrrF6dLR-G9azoTME3jVyUm_90rOEijuSFBP4NG97660k6uA8i0LVmaSvr7_tG_gkX-mrtptD7YWt0t8Cw_qX4vJ_HbfKci43A8K8gf9OAoY
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwED-Ngfh44GPjIzDASLwgkdVxEid-LBvTKtoKsTLtLbKd81bBkmptkfjvsV036tCExFskO5aT3zl3l7v7HcB7q-W4znIT8zJN48woGitUVpZpqayAqKTwPN2nw2I8Ls_OxNct-NjVwiCiTz7DfXfpY_l1q5fuV1nPFTNYf-YW3Hads0K1VhczyPJVQgdznLGUs3VQkoreZDRwWVxinzm6ceZa2DhTmQtHobmhj3yDlZtszb9TJjd00NGj_9v9Y3gYbE3SXwnHE9jCZgcebDAQ7sDdUYit78Ksv1y0nsCVpIfk0zQ-dZuY-jxVcoLnl6FKqSGtIQdesDQZXNrv0Zyo30SSkws5w_gbGrtcTXxlb0wmcv6DHCLOSGByPSf9QGP-FL4ffZ4cHMehH0OssyxbxKmyUHJpX3Vd5rlMnXsiRUp1xmTBVJ5jyrlhpsiMMEbUaE0xoSmvpSPNy_L0GWw3bYMvgCBXKQpMlLEOnWZ1aUqRCNRG0tJgSiPorVGpdCArdz0zflbeaaGispBWDtIqQBrBh-6O2Yqo4x9zdx083byATAR7a-CrcJLnFbP6m1GrwpMI3nXD9gy6wIpssF3aOe6rlrOM5xE8X8lJt_ZaziIorklQN8Hxe18faaYXnuebF6xMOH15827fwr3jyWhYDQfjL6_gvnu-Ve7bHmwvrpb4Gu7oX4vp_OqNPyZ_ALKzDHk
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=Automatic+3D+Bi-Ventricular+Segmentation+of+Cardiac+Images+by+a+Shape-Refined+Multi-+Task+Deep+Learning+Approach&rft.jtitle=IEEE+transactions+on+medical+imaging&rft.au=Duan%2C+Jinming&rft.au=Bello%2C+Ghalib&rft.au=Schlemper%2C+Jo&rft.au=Bai%2C+Wenjia&rft.date=2019-09-01&rft.issn=0278-0062&rft.eissn=1558-254X&rft.volume=38&rft.issue=9&rft.spage=2151&rft.epage=2164&rft_id=info:doi/10.1109%2FTMI.2019.2894322&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMI_2019_2894322
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0278-0062&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0278-0062&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0278-0062&client=summon