3D cardiac shape analysis with variational point cloud autoencoders for myocardial infarction prediction and virtual heart synthesis
Cardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for both accurate clinical decision-making and realistic in silico modeling of cardiac function. In this work, we propose multi-class variational point clou...
Gespeichert in:
| Veröffentlicht in: | Computerized medical imaging and graphics Jg. 124; S. 102587 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
Elsevier Ltd
01.09.2025
|
| Schlagworte: | |
| ISSN: | 0895-6111, 1879-0771, 1879-0771 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Cardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for both accurate clinical decision-making and realistic in silico modeling of cardiac function. In this work, we propose multi-class variational point cloud autoencoders (Point VAE) as a novel geometric deep learning approach for 3D cardiac shape and function analysis. Its encoder–decoder architecture enables efficient multi-scale feature learning directly on high resolution point cloud representations of the multi-class 3D cardiac anatomy and can capture complex non-linear 3D shape variability in a low-dimensional and interpretable latent space. We first evaluate the Point VAE’s reconstruction ability on a dataset of over 10,000 subjects and find mean Chamfer distances between input and reconstructed point clouds below the pixel resolution of the underlying image acquisitions. Furthermore, we analyze the Point VAE’s latent space and observe a realistic and disentangled representation of morphological and functional variability. We test the latent space for pathology prediction and find it to outperform clinical benchmarks by 13% and 16% in area under the receiver operating characteristic (AUROC) curves for the tasks of prevalent myocardial infarction (MI) detection and incident MI prediction, respectively, and by 10% in terms of Harrell’s concordance index for MI survival analysis. Finally, we use the generated populations for in silico simulations of cardiac electrophysiology, demonstrating its ability to introduce realistic natural variability.
•Multi-class Point VAE: novel geometric DL for 3D cardiac shape & function analysis.•Point VAE shows sub-pixel reconstruction accuracy on 10,000+ cardiac point clouds.•Point VAE learns realistic, disentangled features of cardiac shape & function.•Latent space outperforms clinical benchmarks in MI prediction and survival.•In silico simulations of electrophysiology show realistic cardiac variability. |
|---|---|
| AbstractList | Cardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for both accurate clinical decision-making and realistic in silico modeling of cardiac function. In this work, we propose multi-class variational point cloud autoencoders (Point VAE) as a novel geometric deep learning approach for 3D cardiac shape and function analysis. Its encoder–decoder architecture enables efficient multi-scale feature learning directly on high resolution point cloud representations of the multi-class 3D cardiac anatomy and can capture complex non-linear 3D shape variability in a low-dimensional and interpretable latent space. We first evaluate the Point VAE’s reconstruction ability on a dataset of over 10,000 subjects and find mean Chamfer distances between input and reconstructed point clouds below the pixel resolution of the underlying image acquisitions. Furthermore, we analyze the Point VAE’s latent space and observe a realistic and disentangled representation of morphological and functional variability. We test the latent space for pathology prediction and find it to outperform clinical benchmarks by 13% and 16% in area under the receiver operating characteristic (AUROC) curves for the tasks of prevalent myocardial infarction (MI) detection and incident MI prediction, respectively, and by 10% in terms of Harrell’s concordance index for MI survival analysis. Finally, we use the generated populations for in silico simulations of cardiac electrophysiology, demonstrating its ability to introduce realistic natural variability.
•Multi-class Point VAE: novel geometric DL for 3D cardiac shape & function analysis.•Point VAE shows sub-pixel reconstruction accuracy on 10,000+ cardiac point clouds.•Point VAE learns realistic, disentangled features of cardiac shape & function.•Latent space outperforms clinical benchmarks in MI prediction and survival.•In silico simulations of electrophysiology show realistic cardiac variability. Cardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for both accurate clinical decision-making and realistic in silico modeling of cardiac function. In this work, we propose multi-class variational point cloud autoencoders (Point VAE) as a novel geometric deep learning approach for 3D cardiac shape and function analysis. Its encoder-decoder architecture enables efficient multi-scale feature learning directly on high resolution point cloud representations of the multi-class 3D cardiac anatomy and can capture complex non-linear 3D shape variability in a low-dimensional and interpretable latent space. We first evaluate the Point VAE's reconstruction ability on a dataset of over 10,000 subjects and find mean Chamfer distances between input and reconstructed point clouds below the pixel resolution of the underlying image acquisitions. Furthermore, we analyze the Point VAE's latent space and observe a realistic and disentangled representation of morphological and functional variability. We test the latent space for pathology prediction and find it to outperform clinical benchmarks by 13% and 16% in area under the receiver operating characteristic (AUROC) curves for the tasks of prevalent myocardial infarction (MI) detection and incident MI prediction, respectively, and by 10% in terms of Harrell's concordance index for MI survival analysis. Finally, we use the generated populations for in silico simulations of cardiac electrophysiology, demonstrating its ability to introduce realistic natural variability.Cardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for both accurate clinical decision-making and realistic in silico modeling of cardiac function. In this work, we propose multi-class variational point cloud autoencoders (Point VAE) as a novel geometric deep learning approach for 3D cardiac shape and function analysis. Its encoder-decoder architecture enables efficient multi-scale feature learning directly on high resolution point cloud representations of the multi-class 3D cardiac anatomy and can capture complex non-linear 3D shape variability in a low-dimensional and interpretable latent space. We first evaluate the Point VAE's reconstruction ability on a dataset of over 10,000 subjects and find mean Chamfer distances between input and reconstructed point clouds below the pixel resolution of the underlying image acquisitions. Furthermore, we analyze the Point VAE's latent space and observe a realistic and disentangled representation of morphological and functional variability. We test the latent space for pathology prediction and find it to outperform clinical benchmarks by 13% and 16% in area under the receiver operating characteristic (AUROC) curves for the tasks of prevalent myocardial infarction (MI) detection and incident MI prediction, respectively, and by 10% in terms of Harrell's concordance index for MI survival analysis. Finally, we use the generated populations for in silico simulations of cardiac electrophysiology, demonstrating its ability to introduce realistic natural variability. Cardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for both accurate clinical decision-making and realistic in silico modeling of cardiac function. In this work, we propose multi-class variational point cloud autoencoders (Point VAE) as a novel geometric deep learning approach for 3D cardiac shape and function analysis. Its encoder-decoder architecture enables efficient multi-scale feature learning directly on high resolution point cloud representations of the multi-class 3D cardiac anatomy and can capture complex non-linear 3D shape variability in a low-dimensional and interpretable latent space. We first evaluate the Point VAE's reconstruction ability on a dataset of over 10,000 subjects and find mean Chamfer distances between input and reconstructed point clouds below the pixel resolution of the underlying image acquisitions. Furthermore, we analyze the Point VAE's latent space and observe a realistic and disentangled representation of morphological and functional variability. We test the latent space for pathology prediction and find it to outperform clinical benchmarks by 13% and 16% in area under the receiver operating characteristic (AUROC) curves for the tasks of prevalent myocardial infarction (MI) detection and incident MI prediction, respectively, and by 10% in terms of Harrell's concordance index for MI survival analysis. Finally, we use the generated populations for in silico simulations of cardiac electrophysiology, demonstrating its ability to introduce realistic natural variability. AbstractCardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for both accurate clinical decision-making and realistic in silico modeling of cardiac function. In this work, we propose multi-class variational point cloud autoencoders (Point VAE) as a novel geometric deep learning approach for 3D cardiac shape and function analysis. Its encoder–decoder architecture enables efficient multi-scale feature learning directly on high resolution point cloud representations of the multi-class 3D cardiac anatomy and can capture complex non-linear 3D shape variability in a low-dimensional and interpretable latent space. We first evaluate the Point VAE’s reconstruction ability on a dataset of over 10,000 subjects and find mean Chamfer distances between input and reconstructed point clouds below the pixel resolution of the underlying image acquisitions. Furthermore, we analyze the Point VAE’s latent space and observe a realistic and disentangled representation of morphological and functional variability. We test the latent space for pathology prediction and find it to outperform clinical benchmarks by 13% and 16% in area under the receiver operating characteristic (AUROC) curves for the tasks of prevalent myocardial infarction (MI) detection and incident MI prediction, respectively, and by 10% in terms of Harrell’s concordance index for MI survival analysis. Finally, we use the generated populations for in silico simulations of cardiac electrophysiology, demonstrating its ability to introduce realistic natural variability. |
| ArticleNumber | 102587 |
| Author | Beetz, Marcel Camps, Julia Rodriguez, Blanca Li, Lei Grau, Vicente Banerjee, Abhirup |
| Author_xml | – sequence: 1 givenname: Marcel surname: Beetz fullname: Beetz, Marcel organization: Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, United Kingdom – sequence: 2 givenname: Abhirup orcidid: 0000-0001-8198-5128 surname: Banerjee fullname: Banerjee, Abhirup email: abhirup.banerjee@eng.ox.ac.uk organization: Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, United Kingdom – sequence: 3 givenname: Lei surname: Li fullname: Li, Lei organization: Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, United Kingdom – sequence: 4 givenname: Julia surname: Camps fullname: Camps, Julia organization: Department of Computer Science, University of Oxford, Oxford OX1 3QD, United Kingdom – sequence: 5 givenname: Blanca surname: Rodriguez fullname: Rodriguez, Blanca organization: Department of Computer Science, University of Oxford, Oxford OX1 3QD, United Kingdom – sequence: 6 givenname: Vicente surname: Grau fullname: Grau, Vicente organization: Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, United Kingdom |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40582300$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNkkuPFCEUhYkZ4_SM_gWDOzfVAtX1YGMy6fGVTOJCXZPbcMumrYISqDa194dLpUZjTExmBYHvHi7n3Cty4bxDQl5wtuWM169OW-2HcUBjB_i6FUxU-VxUbfOIbHjbyII1Db8gG9bKqqg555fkKsYTY0ywhj8hlztWtaJkbEN-lrdUQzAWNI1HGJGCg36ONtIfNh3pGYKFZH0-pKO3LlHd-8lQmJJHp73BEGnnAx1mv-r01LoOgl6K6Bhyk-sWnKFnG9KUiSNCSDTOLh0xP_WUPO6gj_jsfr0mX96--bx_X9x9fPdhf3NX6F3bpMLUpmQH3RmAxhjoWmnKVjCsq06DNgcpsDJVDbuyhQo67JjWRtZGYL6QZVNek5er7hj89wljUoONGvseHPopqlJkE2vJapnR5_fodMhGqzFkr8OsfjuXAbkCOvgYA3Z_EM7UkpI6qb9SUktKak0p1-7XWsyfPVsMKmqb3cxoQJ2U8fZBKq__UdG9dVZD_w1njCc_hZxaVFxFoZj6tEzDMgyiyoMg6yoL3Pxf4IFN_ALeVtA5 |
| Cites_doi | 10.1113/expphysiol.2008.044081 10.1016/j.media.2021.102143 10.1109/2945.817351 10.1109/EMBC48229.2022.9871643 10.3389/fcvm.2020.00102 10.1186/s12968-021-00780-x 10.1016/j.media.2021.102222 10.1016/j.media.2023.102975 10.1098/rsif.2013.1023 10.1145/2629697 10.11159/icsta21.127 10.1186/1532-429X-15-46 10.1109/MSP.2017.2693418 10.1136/hrt.40.11.1257 10.1371/journal.pcbi.1008851 10.1098/rsta.2020.0257 10.1016/j.media.2015.08.009 10.1093/bioinformatics/btr360 10.1016/j.neucom.2020.08.030 10.1109/JBHI.2017.2652449 10.1093/eurheartj/ehaa159 10.1038/s41598-018-37916-6 10.3389/fphys.2019.01103 10.1038/s41591-020-1009-y 10.1148/radiol.2017170213 10.1016/j.media.2015.11.004 10.3389/fphys.2022.880260 10.1016/j.media.2021.102276 10.1016/j.ppedcard.2016.07.010 10.1186/s12968-019-0551-6 10.1001/jama.1982.03320430047030 10.1109/ISBI52829.2022.9761590 10.1111/j.2517-6161.1972.tb00899.x |
| ContentType | Journal Article |
| Copyright | 2025 Copyright © 2025. Published by Elsevier Ltd. |
| Copyright_xml | – notice: 2025 – notice: Copyright © 2025. Published by Elsevier Ltd. |
| DBID | 6I. AAFTH AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1016/j.compmedimag.2025.102587 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | 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: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1879-0771 |
| EndPage | 102587 |
| ExternalDocumentID | 40582300 10_1016_j_compmedimag_2025_102587 S0895611125000965 1_s2_0_S0895611125000965 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M .1- .DC .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29F 4.4 457 4G. 53G 5GY 5RE 5VS 7-5 71M 8P~ 9JM 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABBQC ABFNM ABJNI ABMAC ABMZM ABWVN ABXDB ACDAQ ACGFS ACIEU ACIUM ACIWK ACLOT ACNNM ACPRK ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO AEBSH AEIPS AEKER AENEX AEUPX AEVXI AFJKZ AFPUW AFRAH AFRHN AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX AOUOD APXCP ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EFKBS EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HEI HLZ HMK HMO HVGLF HZ~ IHE J1W KOM LX9 M29 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- ROL RPZ SAE SBC SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSV SSZ T5K WUQ Z5R ZGI ~G- ~HD 6I. AAFTH 9DU AAYXX CITATION AGCQF CGR CUY CVF ECM EIF NPM 7X8 |
| ID | FETCH-LOGICAL-c487t-d6d30bcfdaa7ddaf89d3820e65fcacdb92e5d56a438a5afef0ccd96d2e2e59373 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001525914800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0895-6111 1879-0771 |
| IngestDate | Sat Nov 01 15:03:36 EDT 2025 Thu Sep 04 04:51:26 EDT 2025 Sat Nov 29 07:34:34 EST 2025 Sat Sep 27 17:13:54 EDT 2025 Sat Sep 27 20:32:13 EDT 2025 Sat Sep 27 06:15:34 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Point cloud VAE Geometric deep learning 3D anatomy modeling Myocardial infarction prediction Cardiac electrophysiology simulation Virtual population generation |
| Language | English |
| License | This is an open access article under the CC BY license. Copyright © 2025. Published by Elsevier Ltd. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c487t-d6d30bcfdaa7ddaf89d3820e65fcacdb92e5d56a438a5afef0ccd96d2e2e59373 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0001-8198-5128 |
| OpenAccessLink | https://www.clinicalkey.com/#!/content/1-s2.0-S0895611125000965 |
| PMID | 40582300 |
| PQID | 3225869069 |
| PQPubID | 23479 |
| PageCount | 1 |
| ParticipantIDs | proquest_miscellaneous_3225869069 pubmed_primary_40582300 crossref_primary_10_1016_j_compmedimag_2025_102587 elsevier_sciencedirect_doi_10_1016_j_compmedimag_2025_102587 elsevier_clinicalkeyesjournals_1_s2_0_S0895611125000965 elsevier_clinicalkey_doi_10_1016_j_compmedimag_2025_102587 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-09-01 |
| PublicationDateYYYYMMDD | 2025-09-01 |
| PublicationDate_xml | – month: 09 year: 2025 text: 2025-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Computerized medical imaging and graphics |
| PublicationTitleAlternate | Comput Med Imaging Graph |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Suk, Haan, Lippe, Brune, Wolterink (b71) 2021 Harrell, Califf, Pryor, Lee, Rosati (b40) 1982; 247 Engwirda (b34) 2014 Bai, Suzuki, Huang, Francis, Wang, Tarroni, Guitton, Aung, Fung, Petersen (b6) 2020; 26 Beetz, Banerjee, Grau (b11) 2022 Mincholé, Zacur, Ariga, Grau, Rodriguez (b56) 2019 Ye, Huang, Yang, Wu, Yi, Axel, Metaxas (b75) 2020 Cardone-Noott, Bueno-Orovio, Mincholé, Zemzemi, Rodriguez (b25) 2016; 18 Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., Lerchner, A., 2017. beta-VAE: Learning basic visual concepts with a constrained variational framework. In: 5th International Conference on Learning Representations. ICLR, pp. 1–13. Caldwell, Trew, Sands, Hooks, LeGrice, Smaill (b23) 2009; 2 Smith, Rodriguez, Sang, Beetz, Choudhury, Grau, Banerjee (b69) 2024 Petersen, Matthews, Francis, Robson, Zemrak, Boubertakh, Young, Hudson, Weale, Garratt, Collins, Piechnik, Neubauer (b59) 2015; 18 Cox (b30) 1972; 34 Gilbert, Mauger, Young, Suinesiaputra (b38) 2020; 7 Delaney, Brophy, Ward (b32) 2019 Beetz, Banerjee, Grau (b10) 2022 Beetz, M., Banerjee, A., Sang, Y., Grau, V., 2022c. Combined generation of electrocardiogram and cardiac anatomy models using multi-modal variational autoencoders. In: 2022 IEEE 19th International Symposium on Biomedical Imaging. ISBI, pp. 1–4. Petersen, Matthews, Bamberg, Bluemke, Francis, Friedrich, Leeson, Nagel, Plein, Rademakers (b58) 2013; 15 Banerjee, Camps, Zacur, Andrews, Rudy, Choudhury, Rodriguez, Grau (b7) 2021; 379 Beetz, Banerjee, Ossenberg-Engels, Grau (b14) 2023; 90 Cetin, Sanroma, Petersen, Napel, Camara, Ballester, Lekadir (b26) 2018 Baessler (b3) 2018; 286 Young, Frangi (b76) 2009; 94 Mauger, Govil, Chabiniok, Gilbert, Hegde, Hussain, McCulloch, Occleshaw, Omens, Perry (b53) 2021; 23 Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al., 2016. Tensorflow: A system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation. pp. 265–283. Gretton, Borgwardt, Rasch, Schölkopf, Smola (b39) 2012; 13 Bowman, Vilnis, Vinyals, Dai, Jozefowicz, Bengio (b21) 2015 Qi, C.R., Su, H., Mo, K., Guibas, L.J., 2017a. Pointnet: Deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 652–660. Wolterink (b72) 2018 Romero, Lozano, Martínez-Gil, Serra, Sebastián, Lamata, García-Fernández (b65) 2021 Yu, Zhang, Wang, Zhang, Song, Xiang, Liu, Cai (b77) 2021 Beetz, Banerjee, Grau (b13) 2023 Kong, Wilson, Shadden (b46) 2021; 74 Bai, Sinclair, Tarroni, Oktay, Rajchl, Vaillant, Lee, Aung, Lukaschuk, Sanghvi (b5) 2018; 20 Isensee (b42) 2018 Ardekani, Jain, Sanzi, Corona-Villalobos, Abraham, Abraham, Zimmerman, Wu, Winslow, Miller (b2) 2016; 29 Camps, Lawson, Drovandi, Minchole, Wang, Grau, Burrage, Rodriguez (b24) 2021; 73 Beetz, Corral Acero, Banerjee, Eitel, Zacur, Lange, Stiermaier, Evertz, Backhaus, Thiele (b16) 2022 Li, Camps, Banerjee, Beetz, Rodriguez, Grau (b48) 2023 Meng, Bai, Liu, O’Regan, Rueckert (b55) 2022 Gilbert, Bai, Mauger, Medrano-Gracia, Suinesiaputra, Lee, Sanghvi, Aung, Piechnik, Neubauer (b37) 2019; 9 Beetz, Corral Acero, Banerjee, Eitel, Zacur, Lange, Stiermaier, Evertz, Backhaus, Thiele (b18) 2023 Bronstein, Bruna, LeCun, Szlam, Vandergheynst (b22) 2017; 34 Lu, Bai, Rueckert, Noble (b51) 2021 Suinesiaputra, Ablin, Alba, Alessandrini, Allen, Bai, Cimen, Claes, Cowan, D’hooge (b70) 2017; 22 2 (3) 5. Beetz, Ossenberg-Engels, Banerjee, Grau (b19) 2021 Prakash (b60) 1978; 40 Kingma, Welling (b45) 2013 Dou, Virtanen, Ravikumar, Frangi (b33) 2022 Mauger, Gilbert, Lee, Sanghvi, Aung, Fung, Carapella, Piechnik, Neubauer, Petersen (b52) 2019; 21 Fonseca, Backhaus, Bluemke, Britten, Chung, Cowan, Dinov, Finn, Hunter, Kadish (b36) 2011; 27 Lamata, Sinclair, Kerfoot, Lee, Crozier, Blazevic, Land, Lewandowski, Barber, Niederer (b47) 2014; 11 Corral-Acero, Margara, Marciniak, Rodero, Loncaric, Feng, Gilbert, Fernandes, Bukhari, Wajdan (b28) 2020; 41 Beetz, Banerjee, Grau (b9) 2021 Bernardini, Mittleman, Rushmeier, Silva, Taubin (b20) 1999; 5 Farrar, Suinesiaputra, Gilbert, Perry, Hegde, Marsden, Young, Omens, McCulloch (b35) 2016; 43 Bai, Shi, de Marvao, Dawes, O’Regan, Cook, Rueckert (b4) 2015; 26 Puyol-Antón, Chen, Clough, Ruijsink, Sidhu, Gould, Porter, Elliott, Mehta, Rueckert (b61) 2020 Dalton, D., Lazarus, A., Rabbani, A., Gao, H., Husmeier, D., 2021. Graph Neural Network Emulation of Cardiac Mechanics. In: 3rd International Conference on Statistics: Theory and Applications. ICSTA’21, pp. 1–8. Lu, Bai, Rueckert, Noble (b50) 2021 Yang, Y., Feng, C., Shen, Y., Tian, D., Foldingnet: Interpretable unsupervised learning on 3D point clouds arXiv preprint Corral Acero, Schuster, Zacur, Lange, Stiermaier, Backhaus, Thiele, Bueno-Orovio, Lamata, Eitel (b29) 2022; 15 Meister, Passerini, Audigier, Lluch, Mihalef, Ashikaga, Maier, Halperin, Mansi (b54) 2020 Rodero, Strocchi, Marciniak, Longobardi, Whitaker, O’Neill, Gillette, Augustin, Plank, Vigmond (b64) 2021; 17 Beetz, Banerjee, Grau (b8) 2021 Beetz, Corral Acero, Banerjee, Eitel, Zacur, Lange, Stiermaier, Evertz, Backhaus, Thiele (b17) 2023 Beetz, Banerjee, Grau (b12) 2023 Pedregosa, Varoquaux, Gramfort, Michel, Thirion, Grisel, Blondel, Prettenhofer, Weiss, Dubourg (b57) 2011; 12 Chang, Jung (b27) 2020; 418 Lu, Bai, Rueckert, Noble (b49) 2020 Zakeri, Hokmabadi, Ravikumar, Frangi, Gooya (b79) 2022; 75 Khened, Alex, Krishnamurthi (b43) 2018 Kingma, D.P., Ba, J., 2015. Adam: A method for stochastic optimization. In: International Conference on Learning Representations. Seale, Beetz, Rodriguez, Grau, Banerjee (b66) 2024 Smith, H.J., Banerjee, A., Choudhury, R.P., Grau, V., 2022. Automated Torso Contour Extraction from Clinical Cardiac MR Slices for 3D Torso Reconstruction. In: 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. EMBC, pp. 3809–3813. Yuan, Khot, Held, Mertz, Hebert (b78) 2018 Si (b67) 2015; 41 Qi, Yi, Su, Guibas (b63) 2017 Xiong, Stiles, Yao, Shi, Nalar, Hawson, Lee, Zhao (b73) 2022; 13 Beetz (10.1016/j.compmedimag.2025.102587_b13) 2023 Bai (10.1016/j.compmedimag.2025.102587_b5) 2018; 20 10.1016/j.compmedimag.2025.102587_b15 Petersen (10.1016/j.compmedimag.2025.102587_b58) 2013; 15 Kong (10.1016/j.compmedimag.2025.102587_b46) 2021; 74 Corral Acero (10.1016/j.compmedimag.2025.102587_b29) 2022; 15 Engwirda (10.1016/j.compmedimag.2025.102587_b34) 2014 Isensee (10.1016/j.compmedimag.2025.102587_b42) 2018 Ardekani (10.1016/j.compmedimag.2025.102587_b2) 2016; 29 Lu (10.1016/j.compmedimag.2025.102587_b51) 2021 Mauger (10.1016/j.compmedimag.2025.102587_b53) 2021; 23 Beetz (10.1016/j.compmedimag.2025.102587_b10) 2022 Farrar (10.1016/j.compmedimag.2025.102587_b35) 2016; 43 Seale (10.1016/j.compmedimag.2025.102587_b66) 2024 Beetz (10.1016/j.compmedimag.2025.102587_b16) 2022 Bronstein (10.1016/j.compmedimag.2025.102587_b22) 2017; 34 Zakeri (10.1016/j.compmedimag.2025.102587_b79) 2022; 75 Suk (10.1016/j.compmedimag.2025.102587_b71) 2021 Baessler (10.1016/j.compmedimag.2025.102587_b3) 2018; 286 Bowman (10.1016/j.compmedimag.2025.102587_b21) 2015 Beetz (10.1016/j.compmedimag.2025.102587_b19) 2021 10.1016/j.compmedimag.2025.102587_b68 Xiong (10.1016/j.compmedimag.2025.102587_b73) 2022; 13 Chang (10.1016/j.compmedimag.2025.102587_b27) 2020; 418 Lamata (10.1016/j.compmedimag.2025.102587_b47) 2014; 11 Li (10.1016/j.compmedimag.2025.102587_b48) 2023 Corral-Acero (10.1016/j.compmedimag.2025.102587_b28) 2020; 41 10.1016/j.compmedimag.2025.102587_b62 Banerjee (10.1016/j.compmedimag.2025.102587_b7) 2021; 379 Gretton (10.1016/j.compmedimag.2025.102587_b39) 2012; 13 Smith (10.1016/j.compmedimag.2025.102587_b69) 2024 Suinesiaputra (10.1016/j.compmedimag.2025.102587_b70) 2017; 22 Si (10.1016/j.compmedimag.2025.102587_b67) 2015; 41 Beetz (10.1016/j.compmedimag.2025.102587_b12) 2023 Mincholé (10.1016/j.compmedimag.2025.102587_b56) 2019 Ye (10.1016/j.compmedimag.2025.102587_b75) 2020 Young (10.1016/j.compmedimag.2025.102587_b76) 2009; 94 Wolterink (10.1016/j.compmedimag.2025.102587_b72) 2018 10.1016/j.compmedimag.2025.102587_b31 Camps (10.1016/j.compmedimag.2025.102587_b24) 2021; 73 Caldwell (10.1016/j.compmedimag.2025.102587_b23) 2009; 2 Meister (10.1016/j.compmedimag.2025.102587_b54) 2020 Petersen (10.1016/j.compmedimag.2025.102587_b59) 2015; 18 Beetz (10.1016/j.compmedimag.2025.102587_b11) 2022 Khened (10.1016/j.compmedimag.2025.102587_b43) 2018 Kingma (10.1016/j.compmedimag.2025.102587_b45) 2013 Mauger (10.1016/j.compmedimag.2025.102587_b52) 2019; 21 10.1016/j.compmedimag.2025.102587_b74 Bai (10.1016/j.compmedimag.2025.102587_b4) 2015; 26 Cox (10.1016/j.compmedimag.2025.102587_b30) 1972; 34 Beetz (10.1016/j.compmedimag.2025.102587_b8) 2021 Delaney (10.1016/j.compmedimag.2025.102587_b32) 2019 Lu (10.1016/j.compmedimag.2025.102587_b50) 2021 Beetz (10.1016/j.compmedimag.2025.102587_b18) 2023 Qi (10.1016/j.compmedimag.2025.102587_b63) 2017 Cetin (10.1016/j.compmedimag.2025.102587_b26) 2018 Cardone-Noott (10.1016/j.compmedimag.2025.102587_b25) 2016; 18 Fonseca (10.1016/j.compmedimag.2025.102587_b36) 2011; 27 10.1016/j.compmedimag.2025.102587_b44 Pedregosa (10.1016/j.compmedimag.2025.102587_b57) 2011; 12 Lu (10.1016/j.compmedimag.2025.102587_b49) 2020 Beetz (10.1016/j.compmedimag.2025.102587_b14) 2023; 90 Prakash (10.1016/j.compmedimag.2025.102587_b60) 1978; 40 Meng (10.1016/j.compmedimag.2025.102587_b55) 2022 Rodero (10.1016/j.compmedimag.2025.102587_b64) 2021; 17 Puyol-Antón (10.1016/j.compmedimag.2025.102587_b61) 2020 10.1016/j.compmedimag.2025.102587_b1 Gilbert (10.1016/j.compmedimag.2025.102587_b37) 2019; 9 10.1016/j.compmedimag.2025.102587_b41 Bernardini (10.1016/j.compmedimag.2025.102587_b20) 1999; 5 Bai (10.1016/j.compmedimag.2025.102587_b6) 2020; 26 Yuan (10.1016/j.compmedimag.2025.102587_b78) 2018 Harrell (10.1016/j.compmedimag.2025.102587_b40) 1982; 247 Gilbert (10.1016/j.compmedimag.2025.102587_b38) 2020; 7 Dou (10.1016/j.compmedimag.2025.102587_b33) 2022 Romero (10.1016/j.compmedimag.2025.102587_b65) 2021 Yu (10.1016/j.compmedimag.2025.102587_b77) 2021 Beetz (10.1016/j.compmedimag.2025.102587_b9) 2021 Beetz (10.1016/j.compmedimag.2025.102587_b17) 2023 |
| References_xml | – volume: 41 start-page: 4556 year: 2020 end-page: 4564 ident: b28 article-title: The ‘digital twin’ to enable the vision of precision cardiology publication-title: Eur. Heart J. – volume: 22 start-page: 503 year: 2017 end-page: 515 ident: b70 article-title: Statistical shape modeling of the left ventricle: myocardial infarct classification challenge publication-title: IEEE J. Biomed. Heal. Informatics – year: 2013 ident: b45 article-title: Auto-encoding variational Bayes – volume: 21 start-page: 1 year: 2019 end-page: 13 ident: b52 article-title: Right ventricular shape and function: cardiovascular magnetic resonance reference morphology and biventricular risk factor morphometrics in UK Biobank publication-title: J. Cardiovasc. Magn. Reson. – start-page: 1375 year: 2021 ident: b65 article-title: Clinically-driven virtual patient cohorts generation: An application to aorta publication-title: Front. Physiol. – volume: 12 start-page: 2825 year: 2011 end-page: 2830 ident: b57 article-title: Scikit-learn: Machine learning in python publication-title: J. Mach. Learn. Res. – volume: 18 start-page: iv4 year: 2016 end-page: iv15 ident: b25 article-title: Human ventricular activation sequence and the simulation of the electrocardiographic QRS complex and its variability in healthy and intraventricular block conditions publication-title: EP Eur. – year: 2020 ident: b75 article-title: PC-U Net: Learning to jointly reconstruct and segment the cardiac walls in 3D from CT data – volume: 18 start-page: 1 year: 2015 end-page: 7 ident: b59 article-title: UK Biobank’s cardiovascular magnetic resonance protocol publication-title: J. Cardiovasc. Magn. Reson. – start-page: 245 year: 2023 end-page: 257 ident: b17 article-title: Mesh U-Nets for 3D cardiac deformation modeling publication-title: Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers: 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers – start-page: 264 year: 2021 end-page: 272 ident: b51 article-title: Multiscale graph convolutional networks for cardiac motion analysis publication-title: International Conference on Functional Imaging and Modeling of the Heart – volume: 286 start-page: 103 year: 2018 end-page: 112 ident: b3 article-title: Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images publication-title: Radiol. – reference: Beetz, M., Banerjee, A., Sang, Y., Grau, V., 2022c. Combined generation of electrocardiogram and cardiac anatomy models using multi-modal variational autoencoders. In: 2022 IEEE 19th International Symposium on Biomedical Imaging. ISBI, pp. 1–4. – volume: 11 year: 2014 ident: b47 article-title: An automatic service for the personalization of ventricular cardiac meshes publication-title: J. R. Soc. Interface – year: 2014 ident: b34 article-title: Locally Optimal Delaunay-Refinement and Optimisation-Based Mesh Generation – volume: 247 start-page: 2543 year: 1982 end-page: 2546 ident: b40 article-title: Evaluating the yield of medical tests publication-title: JAMA – start-page: 219 year: 2021 end-page: 228 ident: b19 article-title: Predicting 3D cardiac deformations with point cloud autoencoders publication-title: International Workshop on Statistical Atlases and Computational Models of the Heart – volume: 9 start-page: 1 year: 2019 end-page: 9 ident: b37 article-title: Independent left ventricular morphometric atlases show consistent relationships with cardiovascular risk factors: a UK biobank study publication-title: Sci. Rep. – volume: 40 start-page: 1257 year: 1978 end-page: 1261 ident: b60 article-title: Determination of right ventricular wall thickness in systole and diastole. Echocardiographic and necropsy correlation in 32 patients. publication-title: Heart – start-page: 284 year: 2020 end-page: 293 ident: b61 article-title: Interpretable deep models for cardiac resynchronisation therapy response prediction publication-title: Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part I 23 – reference: Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al., 2016. Tensorflow: A system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation. pp. 265–283. – start-page: 101 year: 2018 end-page: 110 ident: b72 article-title: Automatic segmentation and disease classification using cardiac cine MR images publication-title: Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges: 8th International Workshop, STACOM 2017, Held in Conjunction with MICCAI 2017, Quebec City, Canada, September 10-14, 2017, Revised Selected Papers 8 – reference: 2 (3) 5. – start-page: 291 year: 2023 end-page: 301 ident: b18 article-title: Post-infarction risk prediction with mesh classification networks publication-title: Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers: 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers – volume: 7 start-page: 102 year: 2020 ident: b38 article-title: Artificial intelligence in cardiac imaging with statistical atlases of cardiac anatomy publication-title: Front. Cardiovasc. Med. – volume: 20 start-page: 1 year: 2018 end-page: 12 ident: b5 article-title: Automated cardiovascular magnetic resonance image analysis with fully convolutional networks publication-title: J. Cardiovasc. Magn. Reson. – volume: 43 start-page: 61 year: 2016 end-page: 69 ident: b35 article-title: Atlas-based ventricular shape analysis for understanding congenital heart disease publication-title: Prog. Pediatr. Cardiol. – volume: 73 year: 2021 ident: b24 article-title: Inference of ventricular activation properties from non-invasive electrocardiography publication-title: Med. Image Anal. – volume: 90 year: 2023 ident: b14 article-title: Multi-class point cloud completion networks for 3D cardiac anatomy reconstruction from cine magnetic resonance images publication-title: Med. Image Anal. – volume: 75 year: 2022 ident: b79 article-title: A probabilistic deep motion model for unsupervised cardiac shape anomaly assessment publication-title: Med. Image Anal. – start-page: 105 year: 2021 end-page: 109 ident: b8 article-title: Biventricular surface reconstruction from cine MRI contours using point completion networks publication-title: 2021 IEEE 18th International Symposium on Biomedical Imaging – volume: 26 start-page: 133 year: 2015 end-page: 145 ident: b4 article-title: A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion publication-title: Med. Image Anal. – reference: Yang, Y., Feng, C., Shen, Y., Tian, D., Foldingnet: Interpretable unsupervised learning on 3D point clouds arXiv preprint – start-page: 1103 year: 2019 ident: b56 article-title: MRI-based computational torso/biventricular multiscale models to investigate the impact of anatomical variability on the ECG QRS complex publication-title: Front. Physiol. – start-page: 3258 year: 2022 ident: b16 article-title: Interpretable cardiac anatomy modeling using variational mesh autoencoders publication-title: Front. Cardiovasc. Med. – reference: Smith, H.J., Banerjee, A., Choudhury, R.P., Grau, V., 2022. Automated Torso Contour Extraction from Clinical Cardiac MR Slices for 3D Torso Reconstruction. In: 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. EMBC, pp. 3809–3813. – volume: 94 start-page: 578 year: 2009 end-page: 596 ident: b76 article-title: Computational cardiac atlases: from patient to population and back publication-title: Exp. Physiol. – start-page: 3 year: 2022 end-page: 14 ident: b11 article-title: Reconstructing 3D cardiac anatomies from misaligned multi-view magnetic resonance images with mesh deformation U-Nets publication-title: Geometric Deep Learning in Medical Image Analysis – start-page: 991 year: 2022 ident: b10 article-title: Multi-domain variational autoencoders for combined modeling of MRI-based biventricular anatomy and ECG-based cardiac electrophysiology publication-title: Front. Physiol. – volume: 74 year: 2021 ident: b46 article-title: A deep-learning approach for direct whole-heart mesh reconstruction publication-title: Med. Image Anal. – reference: Qi, C.R., Su, H., Mo, K., Guibas, L.J., 2017a. Pointnet: Deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 652–660. – start-page: 140 year: 2018 end-page: 151 ident: b43 article-title: Densely connected fully convolutional network for short-axis cardiac cine MR image segmentation and heart diagnosis using random forest publication-title: Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges: 8th International Workshop, STACOM 2017, Held in Conjunction with MICCAI 2017, Quebec City, Canada, September 10-14, 2017, Revised Selected Papers 8 – start-page: 23 year: 2020 end-page: 34 ident: b54 article-title: Graph convolutional regression of cardiac depolarization from sparse endocardial maps publication-title: International Workshop on Statistical Atlases and Computational Models of the Heart – year: 2021 ident: b77 article-title: 3D medical point transformer: Introducing convolution to attention networks for medical point cloud analysis – volume: 13 start-page: 723 year: 2012 end-page: 773 ident: b39 article-title: A kernel two-sample test publication-title: J. Mach. Learn. Res. – volume: 379 year: 2021 ident: b7 article-title: A completely automated pipeline for 3D reconstruction of human heart from 2D cine magnetic resonance slices publication-title: Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci. – reference: Kingma, D.P., Ba, J., 2015. Adam: A method for stochastic optimization. In: International Conference on Learning Representations. – start-page: 75 year: 2021 end-page: 83 ident: b9 article-title: Generating subpopulation-specific biventricular anatomy models using conditional point cloud variational autoencoders publication-title: International Workshop on Statistical Atlases and Computational Models of the Heart – volume: 29 start-page: 12 year: 2016 end-page: 23 ident: b2 article-title: Shape analysis of hypertrophic and hypertensive heart disease using MRI-based 3D surface models of left ventricular geometry publication-title: Med. Image Anal. – year: 2022 ident: b33 article-title: A generative shape compositional framework: Towards representative populations of virtual heart chimaeras – volume: 23 start-page: 1 year: 2021 end-page: 14 ident: b53 article-title: Right-left ventricular shape variations in tetralogy of fallot: associations with pulmonary regurgitation publication-title: J. Cardiovasc. Magn. Reson. – start-page: 56 year: 2020 end-page: 65 ident: b49 article-title: Modelling cardiac motion via spatio-temporal graph convolutional networks to boost the diagnosis of heart conditions publication-title: International Workshop on Statistical Atlases and Computational Models of the Heart – start-page: 369 year: 2023 end-page: 380 ident: b48 article-title: Deep computational model for the inference of ventricular activation properties publication-title: Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers: 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers – year: 2019 ident: b32 article-title: Synthesis of realistic ECG using generative adversarial networks – volume: 5 start-page: 349 year: 1999 end-page: 359 ident: b20 article-title: The ball-pivoting algorithm for surface reconstruction publication-title: IEEE Trans. Vis. Comput. Graphics – start-page: 1 year: 2024 end-page: 5 ident: b66 article-title: Modelling multi-phase cardiac anatomy using point cloud variational autoencoders publication-title: 2024 IEEE International Symposium on Biomedical Imaging – year: 2024 ident: b69 article-title: Anatomical basis of human sex differences in ECG identified by automated torso-cardiac three-dimensional reconstruction – volume: 418 start-page: 270 year: 2020 end-page: 279 ident: b27 article-title: Automatic cardiac MRI segmentation and permutation-invariant pathology classification using deep neural networks and point clouds publication-title: Neurocomputing – volume: 34 start-page: 18 year: 2017 end-page: 42 ident: b22 article-title: Geometric deep learning: going beyond Euclidean data publication-title: IEEE Signal Process. Mag. – volume: 2 start-page: 433 year: 2009 end-page: 440 ident: b23 article-title: Three distinct directions of intramural activation reveal nonuniform side-to-side electrical coupling of ventricular myocytes publication-title: Circ.: Arrhythmia Electrophysiol. – volume: 34 start-page: 187 year: 1972 end-page: 202 ident: b30 article-title: Regression models and life-tables publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol. – volume: 17 year: 2021 ident: b64 article-title: Linking statistical shape models and simulated function in the healthy adult human heart publication-title: PLoS Comput. Biol. – reference: Dalton, D., Lazarus, A., Rabbani, A., Gao, H., Husmeier, D., 2021. Graph Neural Network Emulation of Cardiac Mechanics. In: 3rd International Conference on Statistics: Theory and Applications. ICSTA’21, pp. 1–8. – volume: 15 start-page: 1 year: 2013 end-page: 10 ident: b58 article-title: Imaging in population science: cardiovascular magnetic resonance in 100,000 participants of UK Biobank-rationale, challenges and approaches publication-title: J. Cardiovasc. Magn. Reson. – volume: 26 start-page: 1654 year: 2020 end-page: 1662 ident: b6 article-title: A population-based phenome-wide association study of cardiac and aortic structure and function publication-title: Nature Med. – year: 2015 ident: b21 article-title: Generating sentences from a continuous space – volume: 41 start-page: 11:1 year: 2015 end-page: 36 ident: b67 article-title: TetGen, a delaunay-based quality tetrahedral mesh generator publication-title: ACM Trans. Math. Software – start-page: 93 year: 2021 end-page: 102 ident: b71 article-title: Mesh convolutional neural networks for wall shear stress estimation in 3D artery models publication-title: International Workshop on Statistical Atlases and Computational Models of the Heart – volume: 13 year: 2022 ident: b73 article-title: Automatic 3D surface reconstruction of the left atrium from clinically mapped point clouds using convolutional neural networks. publication-title: Front. Physiol. – start-page: 248 year: 2022 end-page: 258 ident: b55 article-title: Mesh-based 3D motion tracking in cardiac MRI using deep learning publication-title: Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part VI – start-page: 280 year: 2023 end-page: 290 ident: b13 article-title: Point2Mesh-Net: Combining point cloud and mesh-based deep learning for cardiac shape reconstruction publication-title: Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers: 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers – start-page: 532 year: 2023 end-page: 542 ident: b12 article-title: Multi-objective point cloud autoencoders for explainable myocardial infarction prediction publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 728 year: 2018 end-page: 737 ident: b78 article-title: Pcn: Point completion network publication-title: 2018 International Conference on 3D Vision (3DV) – volume: 15 start-page: 1563 year: 2022 end-page: 1574 ident: b29 article-title: Understanding and improving risk assessment after myocardial infarction using automated left ventricular shape analysis publication-title: JACC: Cardiovasc. Imaging – start-page: 82 year: 2018 end-page: 90 ident: b26 article-title: A radiomics approach to computer-aided diagnosis with cardiac cine-MRI publication-title: Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges: 8th International Workshop, STACOM 2017, Held in Conjunction with MICCAI 2017, Quebec City, Canada, September 10-14, 2017, Revised Selected Papers 8 – volume: 27 start-page: 2288 year: 2011 end-page: 2295 ident: b36 article-title: The cardiac atlas project—an imaging database for computational modeling and statistical atlases of the heart publication-title: Bioinform. – reference: Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., Lerchner, A., 2017. beta-VAE: Learning basic visual concepts with a constrained variational framework. In: 5th International Conference on Learning Representations. ICLR, pp. 1–13. – start-page: 122 year: 2021 end-page: 125 ident: b50 article-title: Dynamic spatio-temporal graph convolutional networks for cardiac motion analysis publication-title: 2021 IEEE 18th International Symposium on Biomedical Imaging – start-page: 5099 year: 2017 end-page: 5108 ident: b63 article-title: Pointnet++: Deep hierarchical feature learning on point sets in a metric space publication-title: Advances in Neural Information Processing Systems – start-page: 120 year: 2018 end-page: 129 ident: b42 article-title: Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features publication-title: Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges: 8th International Workshop, STACOM 2017, Held in Conjunction with MICCAI 2017, Quebec City, Canada, September 10-14, 2017, Revised Selected Papers 8 – start-page: 56 year: 2020 ident: 10.1016/j.compmedimag.2025.102587_b49 article-title: Modelling cardiac motion via spatio-temporal graph convolutional networks to boost the diagnosis of heart conditions – start-page: 284 year: 2020 ident: 10.1016/j.compmedimag.2025.102587_b61 article-title: Interpretable deep models for cardiac resynchronisation therapy response prediction – volume: 94 start-page: 578 issue: 5 year: 2009 ident: 10.1016/j.compmedimag.2025.102587_b76 article-title: Computational cardiac atlases: from patient to population and back publication-title: Exp. Physiol. doi: 10.1113/expphysiol.2008.044081 – start-page: 82 year: 2018 ident: 10.1016/j.compmedimag.2025.102587_b26 article-title: A radiomics approach to computer-aided diagnosis with cardiac cine-MRI – volume: 73 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b24 article-title: Inference of ventricular activation properties from non-invasive electrocardiography publication-title: Med. Image Anal. doi: 10.1016/j.media.2021.102143 – year: 2015 ident: 10.1016/j.compmedimag.2025.102587_b21 – volume: 15 start-page: 1563 issue: 9 year: 2022 ident: 10.1016/j.compmedimag.2025.102587_b29 article-title: Understanding and improving risk assessment after myocardial infarction using automated left ventricular shape analysis publication-title: JACC: Cardiovasc. Imaging – volume: 5 start-page: 349 issue: 4 year: 1999 ident: 10.1016/j.compmedimag.2025.102587_b20 article-title: The ball-pivoting algorithm for surface reconstruction publication-title: IEEE Trans. Vis. Comput. Graphics doi: 10.1109/2945.817351 – start-page: 101 year: 2018 ident: 10.1016/j.compmedimag.2025.102587_b72 article-title: Automatic segmentation and disease classification using cardiac cine MR images – start-page: 219 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b19 article-title: Predicting 3D cardiac deformations with point cloud autoencoders – ident: 10.1016/j.compmedimag.2025.102587_b68 doi: 10.1109/EMBC48229.2022.9871643 – volume: 7 start-page: 102 year: 2020 ident: 10.1016/j.compmedimag.2025.102587_b38 article-title: Artificial intelligence in cardiac imaging with statistical atlases of cardiac anatomy publication-title: Front. Cardiovasc. Med. doi: 10.3389/fcvm.2020.00102 – volume: 23 start-page: 1 issue: 1 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b53 article-title: Right-left ventricular shape variations in tetralogy of fallot: associations with pulmonary regurgitation publication-title: J. Cardiovasc. Magn. Reson. doi: 10.1186/s12968-021-00780-x – start-page: 105 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b8 article-title: Biventricular surface reconstruction from cine MRI contours using point completion networks – start-page: 245 year: 2023 ident: 10.1016/j.compmedimag.2025.102587_b17 article-title: Mesh U-Nets for 3D cardiac deformation modeling – volume: 74 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b46 article-title: A deep-learning approach for direct whole-heart mesh reconstruction publication-title: Med. Image Anal. doi: 10.1016/j.media.2021.102222 – start-page: 120 year: 2018 ident: 10.1016/j.compmedimag.2025.102587_b42 article-title: Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features – year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b77 – start-page: 280 year: 2023 ident: 10.1016/j.compmedimag.2025.102587_b13 article-title: Point2Mesh-Net: Combining point cloud and mesh-based deep learning for cardiac shape reconstruction – start-page: 248 year: 2022 ident: 10.1016/j.compmedimag.2025.102587_b55 article-title: Mesh-based 3D motion tracking in cardiac MRI using deep learning – volume: 90 year: 2023 ident: 10.1016/j.compmedimag.2025.102587_b14 article-title: Multi-class point cloud completion networks for 3D cardiac anatomy reconstruction from cine magnetic resonance images publication-title: Med. Image Anal. doi: 10.1016/j.media.2023.102975 – volume: 11 issue: 91 year: 2014 ident: 10.1016/j.compmedimag.2025.102587_b47 article-title: An automatic service for the personalization of ventricular cardiac meshes publication-title: J. R. Soc. Interface doi: 10.1098/rsif.2013.1023 – year: 2014 ident: 10.1016/j.compmedimag.2025.102587_b34 – ident: 10.1016/j.compmedimag.2025.102587_b41 – ident: 10.1016/j.compmedimag.2025.102587_b1 – start-page: 728 year: 2018 ident: 10.1016/j.compmedimag.2025.102587_b78 article-title: Pcn: Point completion network – ident: 10.1016/j.compmedimag.2025.102587_b62 – start-page: 369 year: 2023 ident: 10.1016/j.compmedimag.2025.102587_b48 article-title: Deep computational model for the inference of ventricular activation properties – volume: 41 start-page: 11:1 issue: 2 year: 2015 ident: 10.1016/j.compmedimag.2025.102587_b67 article-title: TetGen, a delaunay-based quality tetrahedral mesh generator publication-title: ACM Trans. Math. Software doi: 10.1145/2629697 – start-page: 1 year: 2024 ident: 10.1016/j.compmedimag.2025.102587_b66 article-title: Modelling multi-phase cardiac anatomy using point cloud variational autoencoders – ident: 10.1016/j.compmedimag.2025.102587_b31 doi: 10.11159/icsta21.127 – volume: 15 start-page: 1 issue: 1 year: 2013 ident: 10.1016/j.compmedimag.2025.102587_b58 article-title: Imaging in population science: cardiovascular magnetic resonance in 100,000 participants of UK Biobank-rationale, challenges and approaches publication-title: J. Cardiovasc. Magn. Reson. doi: 10.1186/1532-429X-15-46 – volume: 34 start-page: 18 issue: 4 year: 2017 ident: 10.1016/j.compmedimag.2025.102587_b22 article-title: Geometric deep learning: going beyond Euclidean data publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2017.2693418 – start-page: 264 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b51 article-title: Multiscale graph convolutional networks for cardiac motion analysis – volume: 20 start-page: 1 issue: 65 year: 2018 ident: 10.1016/j.compmedimag.2025.102587_b5 article-title: Automated cardiovascular magnetic resonance image analysis with fully convolutional networks publication-title: J. Cardiovasc. Magn. Reson. – start-page: 3258 year: 2022 ident: 10.1016/j.compmedimag.2025.102587_b16 article-title: Interpretable cardiac anatomy modeling using variational mesh autoencoders publication-title: Front. Cardiovasc. Med. – year: 2024 ident: 10.1016/j.compmedimag.2025.102587_b69 – volume: 2 start-page: 433 issue: 4 year: 2009 ident: 10.1016/j.compmedimag.2025.102587_b23 article-title: Three distinct directions of intramural activation reveal nonuniform side-to-side electrical coupling of ventricular myocytes publication-title: Circ.: Arrhythmia Electrophysiol. – start-page: 122 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b50 article-title: Dynamic spatio-temporal graph convolutional networks for cardiac motion analysis – ident: 10.1016/j.compmedimag.2025.102587_b44 – volume: 40 start-page: 1257 issue: 11 year: 1978 ident: 10.1016/j.compmedimag.2025.102587_b60 article-title: Determination of right ventricular wall thickness in systole and diastole. Echocardiographic and necropsy correlation in 32 patients. publication-title: Heart doi: 10.1136/hrt.40.11.1257 – volume: 12 start-page: 2825 year: 2011 ident: 10.1016/j.compmedimag.2025.102587_b57 article-title: Scikit-learn: Machine learning in python publication-title: J. Mach. Learn. Res. – volume: 17 issue: 4 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b64 article-title: Linking statistical shape models and simulated function in the healthy adult human heart publication-title: PLoS Comput. Biol. doi: 10.1371/journal.pcbi.1008851 – start-page: 1375 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b65 article-title: Clinically-driven virtual patient cohorts generation: An application to aorta publication-title: Front. Physiol. – start-page: 93 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b71 article-title: Mesh convolutional neural networks for wall shear stress estimation in 3D artery models – volume: 379 issue: 2212 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b7 article-title: A completely automated pipeline for 3D reconstruction of human heart from 2D cine magnetic resonance slices publication-title: Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci. doi: 10.1098/rsta.2020.0257 – volume: 26 start-page: 133 issue: 1 year: 2015 ident: 10.1016/j.compmedimag.2025.102587_b4 article-title: A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion publication-title: Med. Image Anal. doi: 10.1016/j.media.2015.08.009 – start-page: 3 year: 2022 ident: 10.1016/j.compmedimag.2025.102587_b11 article-title: Reconstructing 3D cardiac anatomies from misaligned multi-view magnetic resonance images with mesh deformation U-Nets – volume: 27 start-page: 2288 issue: 16 year: 2011 ident: 10.1016/j.compmedimag.2025.102587_b36 article-title: The cardiac atlas project—an imaging database for computational modeling and statistical atlases of the heart publication-title: Bioinform. doi: 10.1093/bioinformatics/btr360 – volume: 418 start-page: 270 year: 2020 ident: 10.1016/j.compmedimag.2025.102587_b27 article-title: Automatic cardiac MRI segmentation and permutation-invariant pathology classification using deep neural networks and point clouds publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.08.030 – volume: 22 start-page: 503 issue: 2 year: 2017 ident: 10.1016/j.compmedimag.2025.102587_b70 article-title: Statistical shape modeling of the left ventricle: myocardial infarct classification challenge publication-title: IEEE J. Biomed. Heal. Informatics doi: 10.1109/JBHI.2017.2652449 – volume: 41 start-page: 4556 issue: 48 year: 2020 ident: 10.1016/j.compmedimag.2025.102587_b28 article-title: The ‘digital twin’ to enable the vision of precision cardiology publication-title: Eur. Heart J. doi: 10.1093/eurheartj/ehaa159 – year: 2022 ident: 10.1016/j.compmedimag.2025.102587_b33 – volume: 18 start-page: 1 issue: 8 year: 2015 ident: 10.1016/j.compmedimag.2025.102587_b59 article-title: UK Biobank’s cardiovascular magnetic resonance protocol publication-title: J. Cardiovasc. Magn. Reson. – volume: 9 start-page: 1 issue: 1 year: 2019 ident: 10.1016/j.compmedimag.2025.102587_b37 article-title: Independent left ventricular morphometric atlases show consistent relationships with cardiovascular risk factors: a UK biobank study publication-title: Sci. Rep. doi: 10.1038/s41598-018-37916-6 – start-page: 1103 year: 2019 ident: 10.1016/j.compmedimag.2025.102587_b56 article-title: MRI-based computational torso/biventricular multiscale models to investigate the impact of anatomical variability on the ECG QRS complex publication-title: Front. Physiol. doi: 10.3389/fphys.2019.01103 – volume: 26 start-page: 1654 issue: 10 year: 2020 ident: 10.1016/j.compmedimag.2025.102587_b6 article-title: A population-based phenome-wide association study of cardiac and aortic structure and function publication-title: Nature Med. doi: 10.1038/s41591-020-1009-y – volume: 286 start-page: 103 issue: 1 year: 2018 ident: 10.1016/j.compmedimag.2025.102587_b3 article-title: Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images publication-title: Radiol. doi: 10.1148/radiol.2017170213 – start-page: 75 year: 2021 ident: 10.1016/j.compmedimag.2025.102587_b9 article-title: Generating subpopulation-specific biventricular anatomy models using conditional point cloud variational autoencoders – start-page: 991 year: 2022 ident: 10.1016/j.compmedimag.2025.102587_b10 article-title: Multi-domain variational autoencoders for combined modeling of MRI-based biventricular anatomy and ECG-based cardiac electrophysiology publication-title: Front. Physiol. – volume: 29 start-page: 12 year: 2016 ident: 10.1016/j.compmedimag.2025.102587_b2 article-title: Shape analysis of hypertrophic and hypertensive heart disease using MRI-based 3D surface models of left ventricular geometry publication-title: Med. Image Anal. doi: 10.1016/j.media.2015.11.004 – volume: 13 start-page: 723 issue: 1 year: 2012 ident: 10.1016/j.compmedimag.2025.102587_b39 article-title: A kernel two-sample test publication-title: J. Mach. Learn. Res. – volume: 13 year: 2022 ident: 10.1016/j.compmedimag.2025.102587_b73 article-title: Automatic 3D surface reconstruction of the left atrium from clinically mapped point clouds using convolutional neural networks. publication-title: Front. Physiol. doi: 10.3389/fphys.2022.880260 – volume: 75 year: 2022 ident: 10.1016/j.compmedimag.2025.102587_b79 article-title: A probabilistic deep motion model for unsupervised cardiac shape anomaly assessment publication-title: Med. Image Anal. doi: 10.1016/j.media.2021.102276 – start-page: 291 year: 2023 ident: 10.1016/j.compmedimag.2025.102587_b18 article-title: Post-infarction risk prediction with mesh classification networks – volume: 43 start-page: 61 year: 2016 ident: 10.1016/j.compmedimag.2025.102587_b35 article-title: Atlas-based ventricular shape analysis for understanding congenital heart disease publication-title: Prog. Pediatr. Cardiol. doi: 10.1016/j.ppedcard.2016.07.010 – start-page: 532 year: 2023 ident: 10.1016/j.compmedimag.2025.102587_b12 article-title: Multi-objective point cloud autoencoders for explainable myocardial infarction prediction – volume: 18 start-page: iv4 issue: suppl_4 year: 2016 ident: 10.1016/j.compmedimag.2025.102587_b25 article-title: Human ventricular activation sequence and the simulation of the electrocardiographic QRS complex and its variability in healthy and intraventricular block conditions publication-title: EP Eur. – volume: 21 start-page: 1 issue: 1 year: 2019 ident: 10.1016/j.compmedimag.2025.102587_b52 article-title: Right ventricular shape and function: cardiovascular magnetic resonance reference morphology and biventricular risk factor morphometrics in UK Biobank publication-title: J. Cardiovasc. Magn. Reson. doi: 10.1186/s12968-019-0551-6 – year: 2020 ident: 10.1016/j.compmedimag.2025.102587_b75 – volume: 247 start-page: 2543 issue: 18 year: 1982 ident: 10.1016/j.compmedimag.2025.102587_b40 article-title: Evaluating the yield of medical tests publication-title: JAMA doi: 10.1001/jama.1982.03320430047030 – ident: 10.1016/j.compmedimag.2025.102587_b15 doi: 10.1109/ISBI52829.2022.9761590 – year: 2019 ident: 10.1016/j.compmedimag.2025.102587_b32 – start-page: 140 year: 2018 ident: 10.1016/j.compmedimag.2025.102587_b43 article-title: Densely connected fully convolutional network for short-axis cardiac cine MR image segmentation and heart diagnosis using random forest – start-page: 23 year: 2020 ident: 10.1016/j.compmedimag.2025.102587_b54 article-title: Graph convolutional regression of cardiac depolarization from sparse endocardial maps – start-page: 5099 year: 2017 ident: 10.1016/j.compmedimag.2025.102587_b63 article-title: Pointnet++: Deep hierarchical feature learning on point sets in a metric space – ident: 10.1016/j.compmedimag.2025.102587_b74 – volume: 34 start-page: 187 issue: 2 year: 1972 ident: 10.1016/j.compmedimag.2025.102587_b30 article-title: Regression models and life-tables publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol. doi: 10.1111/j.2517-6161.1972.tb00899.x – year: 2013 ident: 10.1016/j.compmedimag.2025.102587_b45 |
| SSID | ssj0002071 |
| Score | 2.412169 |
| Snippet | Cardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for both... AbstractCardiac anatomy and physiology vary considerably across the human population. Understanding and taking into account this variability is crucial for... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 102587 |
| SubjectTerms | 3D anatomy modeling Autoencoder Cardiac electrophysiology simulation Deep Learning Geometric deep learning Heart - anatomy & histology Heart - diagnostic imaging Humans Imaging, Three-Dimensional - methods Internal Medicine Myocardial Infarction - diagnostic imaging Myocardial infarction prediction Other Point cloud VAE Virtual population generation |
| Title | 3D cardiac shape analysis with variational point cloud autoencoders for myocardial infarction prediction and virtual heart synthesis |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S0895611125000965 https://www.clinicalkey.es/playcontent/1-s2.0-S0895611125000965 https://dx.doi.org/10.1016/j.compmedimag.2025.102587 https://www.ncbi.nlm.nih.gov/pubmed/40582300 https://www.proquest.com/docview/3225869069 |
| Volume | 124 |
| WOSCitedRecordID | wos001525914800001&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-0771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002071 issn: 0895-6111 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLZ2QRMviOsol8mTEC9VqjRpmgTx0rFNgEZBopP6Zjm2o2Xa0tCk1eCZ38Tv4xw7ToNYpfLAS1S5spP4fLHP8bl8hLySfcFlIF0kd_GcgegPnCRJIgedbAKptxMv1WQT4XgcTafxl62tXzYXZnkV5nl0cxMX_1XU0AbCxtTZfxB3Myg0wG8QOlxB7HDdSPD-MZabBrGLbnnBC3QP1HVH9JnrEoxjewBYzLK86oqr2UJ2-aKaYVFLDGzWsYfX32dmHKzKkcIkaaQUc_TsVDaIeZnNdQIK8mJXWP4A9MkyK9sqr-WNyH6Abntd-4Wya8OOhGPomtmtoPsjpTTJLOYRCdVEgBzxXM0vTdzQKLnI5vWZGUYTmRRvlbU9KqVN_-btkw0vaEK37GIchZhgZShaeuqWNruCe4PWGgwqU2A28b-2B3NScYnSLfCF4V17eOfeqs-fJbnHn9np-dkZm5xMJ6-Lbw6ylaFXv6Zu2Sa7XhjEsJrujj6cTD82OoDnGlPfPu0eOVxFFq65-zrNaJ3lozWgyX1yrzZd6MhA7gHZUvlDsvepDs54RH76x7RGHtXIoxZ5FJFHW8ijGnlUI4-2kUcBeXSFPLpCHl0hD8aVtEYe1cijDfIek_PTk8m7905N8uEIsJUrRw6l7yYilZyHUvI0iqUPWqkaBqngQiaxpwIZDPnAj3jAU5W6Qsh4KD0Ff4Bu7T8hO_ksV08J9UXguXzQ74cqGAjQ_PtoQERplCbQkPgd4tkJZoWp5cJskOMla0mFoVSYkUqHvLGiYDZZGbZXBpDapHN4W2dV1utFyfqs9JjLvroRZpiD8aMJSoZBh7xteta6sNFxN73xoUUNg_0CnYDwkc4WJcMNHFnohnGH7Bs4NZMBxhv63d1nG_R-Tu6uvtkXZKeaL9RLckcsq6ycH5DtcBod1F_Fb9de9c8 |
| linkProvider | Elsevier |
| 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=3D+cardiac+shape+analysis+with+variational+point+cloud+autoencoders+for+myocardial+infarction+prediction+and+virtual+heart+synthesis&rft.jtitle=Computerized+medical+imaging+and+graphics&rft.au=Beetz%2C+Marcel&rft.au=Banerjee%2C+Abhirup&rft.au=Li%2C+Lei&rft.au=Camps%2C+Julia&rft.date=2025-09-01&rft.issn=1879-0771&rft.eissn=1879-0771&rft.volume=124&rft.spage=102587&rft_id=info:doi/10.1016%2Fj.compmedimag.2025.102587&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_m | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F08956111%2FS0895611125X00057%2Fcov150h.gif |