Discriminative Hamiltonian variational autoencoder for accurate tumor segmentation in data-scarce regimes
Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data augmentation techniques have been proposed. However, the majority...
Saved in:
| Published in: | Neurocomputing (Amsterdam) Vol. 606; p. 128360 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
14.11.2024
Elsevier |
| Subjects: | |
| ISSN: | 0925-2312 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data augmentation techniques have been proposed. However, the majority of these approaches primarily focus on image generation. For segmentation tasks, providing both images and their corresponding target masks is crucial, and the generation of diverse and realistic samples remains a complex task, especially when working with limited training datasets. To this end, we propose a new end-to-end hybrid architecture based on Hamiltonian Variational Autoencoders (HVAE) and a discriminative regularization to improve the quality of generated images. Our method provides an accurate estimation of the joint distribution of the images and masks, resulting in the generation of realistic medical images with reduced artifacts and off-distribution instances. As generating 3D volumes requires substantial time and memory, our architecture operates on a slice-by-slice basis to segment 3D volumes, capitalizing on the richly augmented dataset. Experiments conducted on two public datasets, BRATS (MRI modality) and HECKTOR (PET modality), demonstrate the efficacy of our proposed method on different medical imaging modalities with limited data. |
|---|---|
| AbstractList | Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data augmentation techniques have been proposed. However, the majority of these approaches primarily focus on image generation. For segmentation tasks, providing both images and their corresponding target masks is crucial, and the generation of diverse and realistic samples remains a complex task, especially when working with limited training datasets. To this end, we propose a new end-to-end hybrid architecture based on Hamiltonian Variational Autoencoders (HVAE) and a discriminative regularization to improve the quality of generated images. Our method provides an accurate estimation of the joint distribution of the images and masks, resulting in the generation of realistic medical images with reduced artifacts and off-distribution instances. As generating 3D volumes requires substantial time and memory, our architecture operates on a sliceby-slice basis to segment 3D volumes, capitalizing on the richly augmented dataset. Experiments conducted on two public datasets, BRATS (MRI modality) and HECKTOR (PET modality), demonstrate the efficacy of our proposed method on different medical imaging modalities with limited data. Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data augmentation techniques have been proposed. However, the majority of these approaches primarily focus on image generation. For segmentation tasks, providing both images and their corresponding target masks is crucial, and the generation of diverse and realistic samples remains a complex task, especially when working with limited training datasets. To this end, we propose a new end-to-end hybrid architecture based on Hamiltonian Variational Autoencoders (HVAE) and a discriminative regularization to improve the quality of generated images. Our method provides an accurate estimation of the joint distribution of the images and masks, resulting in the generation of realistic medical images with reduced artifacts and off-distribution instances. As generating 3D volumes requires substantial time and memory, our architecture operates on a slice-by-slice basis to segment 3D volumes, capitalizing on the richly augmented dataset. Experiments conducted on two public datasets, BRATS (MRI modality) and HECKTOR (PET modality), demonstrate the efficacy of our proposed method on different medical imaging modalities with limited data. |
| ArticleNumber | 128360 |
| Author | Vera, Pierre Ruan, Su Lapuyade-Lahorgue, Jérôme Kebaili, Aghiles |
| Author_xml | – sequence: 1 givenname: Aghiles orcidid: 0009-0000-6114-7733 surname: Kebaili fullname: Kebaili, Aghiles organization: LITIS UR 4108, University of Rouen-Normandy, Rouen, 76000, Normandy, France – sequence: 2 givenname: Jérôme surname: Lapuyade-Lahorgue fullname: Lapuyade-Lahorgue, Jérôme organization: LITIS UR 4108, University of Rouen-Normandy, Rouen, 76000, Normandy, France – sequence: 3 givenname: Pierre surname: Vera fullname: Vera, Pierre organization: LITIS UR 4108, University of Rouen-Normandy, Rouen, 76000, Normandy, France – sequence: 4 givenname: Su orcidid: 0000-0001-8785-6917 surname: Ruan fullname: Ruan, Su email: su.ruan@univ-rouen.fr organization: LITIS UR 4108, University of Rouen-Normandy, Rouen, 76000, Normandy, France |
| BackLink | https://hal.science/hal-04782076$$DView record in HAL |
| BookMark | eNqFkDtPAzEQhF2AxPMfULiluGD7nqZAisIjSJFooLY2vg1sdGcj2zmJf8-Fg4YCqtWuZmY13wk7cN4hYxdSzKSQ1dV25nBnfT9TQhUzqZq8EgfsWGhVZiqX6oidxLgVQtZS6WNGtxRtoJ4cJBqQL6GnLnlH4PgAgcard9Bx2CWPzvoWA9_4wMHaXYCEPO36cY342qNLX2pOjreQIIsWgkUe8JV6jGfscANdxPPvecpe7u-eF8ts9fTwuJivMpsXImUNQLPGsrEbAbKVNeo616iqRtdlAU1e4lrLVksJUlTQrttS6LyyaPO1rsfO-Sm7nHLfoDPvYzUIH8YDmeV8ZfY3UdSNEnU1yFF7PWlt8DEG3BhLU4kUgDojhdlDNVszQTV7qGaCOpqLX-afb__YbiYbjhAGwmCipREtthTQJtN6-jvgEyhZmUI |
| CitedBy_id | crossref_primary_10_1038_s41467_025_61754_6 crossref_primary_10_1049_cit2_70053 crossref_primary_10_1016_j_saa_2025_126611 |
| Cites_doi | 10.1016/j.ijar.2022.06.007 10.1145/3065386 10.3390/jimaging9040081 10.1109/TMI.2019.2914656 10.1109/CVPR.2015.7298594 10.1364/BOE.449796 10.1016/j.zemedi.2018.11.002 10.1016/j.neucom.2023.02.047 10.1117/1.JMI.6.1.014001 10.1186/s40708-020-00104-2 10.1016/j.neucom.2023.126282 10.1038/s41467-024-44824-z 10.1093/bib/bbab569 10.1109/TCBB.2021.3065361 10.1016/j.neucom.2022.04.065 10.1109/CVPR.2018.00068 10.1109/CVPR52688.2022.01042 10.1109/WACV51458.2022.00181 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier B.V. licence_http://creativecommons.org/publicdomain/zero |
| Copyright_xml | – notice: 2024 Elsevier B.V. – notice: licence_http://creativecommons.org/publicdomain/zero |
| DBID | AAYXX CITATION 1XC |
| DOI | 10.1016/j.neucom.2024.128360 |
| DatabaseName | CrossRef Hyper Article en Ligne (HAL) |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | oai:HAL:hal-04782076v1 10_1016_j_neucom_2024_128360 S0925231224011317 |
| GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAXKI AAXLA AAXUO AAYFN ABBOA ABCQJ ABFNM ABJNI ABMAC ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RIG ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSN SSV SSZ T5K ZMT ~G- 29N 9DU AAQXK AATTM AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EFLBG EJD FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC WUQ XPP ~HD 1XC |
| ID | FETCH-LOGICAL-c340t-8aa8be58cf0a1d17e9739e2689754a835eb91d911a106adbd50936cec3b972023 |
| ISICitedReferencesCount | 4 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001302503200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0925-2312 |
| IngestDate | Tue Nov 18 06:20:40 EST 2025 Tue Nov 18 20:57:22 EST 2025 Sat Nov 29 06:34:00 EST 2025 Sat Sep 07 15:50:51 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Generative modeling Hamiltonian Variational Autoencoder MRI Variational Autoencoder Data augmentation Tumor segmentation PET Deep learning Data augmentation Tumor segmentation Generative modeling Variational Autoencoder MRI PET Hamiltonian Variational Autoencoder |
| Language | English |
| License | licence_http://creativecommons.org/publicdomain/zero/: http://creativecommons.org/publicdomain/zero |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c340t-8aa8be58cf0a1d17e9739e2689754a835eb91d911a106adbd50936cec3b972023 |
| ORCID | 0009-0000-6114-7733 0000-0001-8785-6917 |
| ParticipantIDs | hal_primary_oai_HAL_hal_04782076v1 crossref_citationtrail_10_1016_j_neucom_2024_128360 crossref_primary_10_1016_j_neucom_2024_128360 elsevier_sciencedirect_doi_10_1016_j_neucom_2024_128360 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-11-14 |
| PublicationDateYYYYMMDD | 2024-11-14 |
| PublicationDate_xml | – month: 11 year: 2024 text: 2024-11-14 day: 14 |
| PublicationDecade | 2020 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2024 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684–10695. Xudong Mao, Qing Li, Haoran Xie, Raymond YK Lau, Zhen Wang, Stephen Paul Smolley, Least squares generative adversarial networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2794–2802. Liang, Chen (b38) 2021 Huang, Ruan, Decazes, Denœux (b4) 2022; 149 Song, Zheng, Li, Zhang, Zhang, Huang, Chen, Wang, Zhao, Chong (b5) 2021; 18 Kebaili, Lapuyade-Lahorgue, Ruan (b8) 2023; 9 Chen, Wang, Shan (b34) 2023 Andrearczyk, Oreiller, Boughdad, Rest, Elhalawani, Jreige, Prior, Vallières, Visvikis, Hatt (b53) 2021 Kebaili, Lapuyade-Lahorgue, Vera, Ruan (b20) 2023 Ho, Jain, Abbeel (b29) 2020; 33 Heusel, Ramsauer, Unterthiner, Nessler, Hochreiter (b54) 2017; 30 Trullo, Petitjean, Dubray, Ruan (b6) 2019; 6 Huo, Vakharia, Wu, Sharan, Ko, Ourselin, Sparks (b44) 2022 Stojanovski, Hermida, Lamata, Beqiri, Gomez (b32) 2023 Dorjsembe, Pao, Odonchimed, Xiao (b31) 2023 Biffi, Oktay, Tarroni, Bai, Marvao, Doumou, Rajchl, Bedair, Prasad, Cook (b42) 2018 Razavi, Van den Oord, Vinyals (b22) 2019; 32 Zhuang, Schwing, Koyejo (b41) 2019 Krizhevsky, Sutskever, Hinton (b57) 2012; 25 Isensee, Petersen, Klein, Zimmerer, Jaeger, Kohl, Wasserthal, Koehler, Norajitra, Wirkert (b64) 2018 Kazerouni, Aghdam, Heidari, Azad, Fayyaz, Hacihaliloglu, Merhof (b30) 2022 Xiao, Kreis, Vahdat (b17) 2021 Caterini, Doucet, Sejdinovic (b45) 2018; 31 Gan, Wang (b37) 2022; 13 Volokitin, Erdil, Karani, Tezcan, Chen, Gool, Konukoglu (b43) 2020 Huang, Ruan, Denœux (b2) 2023; 535 Li, Xia, Zhang, Wang, Li (b14) 2022 Wang, Xie, Huang, Lyu, Zheng, Zheng, Jin (b10) 2023; 546 Hatamizadeh, Nath, Tang, Yang, Roth, Xu (b62) 2021 Kingma, Salimans, Jozefowicz, Chen, Sutskever, Welling (b25) 2016; 29 Rezende, Mohamed (b26) 2015 Chadebec, Thibeau-Sutre, Burgos, Allassonnière (b27) 2022 Pesteie, Abolmaesumi, Rohling (b40) 2019; 38 Kingma, Salimans, Jozefowicz, Chen, Sutskever, Welling (b21) 2016; 29 Simonyan, Zisserman (b48) 2014 Bond-Taylor, Leach, Long, Willcocks (b13) 2021 Kingma, Welling (b16) 2013 Chadebec, Allassonnière (b18) 2021 Oktay, Schlemper, Folgoc, Lee, Heinrich, Misawa, Mori, McDonagh, Hammerla, Kainz (b63) 2018 Ronneberger, Fischer, Brox (b59) 2015 Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, Going deeper with convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1–9. Davidson, Falorsi, De Cao, Kipf, Tomczak (b28) 2018 Islam, Zhang (b3) 2020; 7 Han, Xiong, You, Khosravi, Sun, Yan, Duncan, Xie (b35) 2023 Mescheder, Geiger, Nowozin (b12) 2018 Krizhevsky, Sutskever, Hinton (b7) 2017; 60 Stahlschmidt, Ulfenborg, Synnergren (b46) 2022; 23 Lundervold, Lundervold (b1) 2019; 29 Shrivastava, Fletcher (b33) 2023 Johnson, Alahi, Fei-Fei (b47) 2016 Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, Oliver Wang, The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 586–595. Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (b9) 2014 Chen, Yang, Wei, Heidari, Zheng, Li, Chen, Hu, Zhou, Guan (b11) 2022 Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Zhai, Unterthiner, Dehghani, Minderer, Heigold, Gelly (b60) 2020 Ali Hatamizadeh, Yucheng Tang, Vishwesh Nath, Dong Yang, Andriy Myronenko, Bennett Landman, Holger R Roth, Daguang Xu, Unetr: Transformers for 3d medical image segmentation, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 574–584. Ma, He, Li, Han, You, Wang (b51) 2024; 15 Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b49) 2017; 30 Tomczak, Welling (b24) 2018 Odena (b15) 2016 Dai, Liu, Chen, Liu, Shi, Liu, Zhou (b19) 2023; 161 Niyas, Pawan, Kumar, Rajan (b39) 2022; 493 Baid, Ghodasara, Mohan, Bilello, Calabrese, Colak, Farahani, Kalpathy-Cramer, Kitamura, Pati (b52) 2021 Isola, Zhu, Zhou, Efros (b50) 2016 Dilokthanakul, Mediano, Garnelo, Lee, Salimbeni, Arulkumaran, Shanahan (b23) 2016 Davidson (10.1016/j.neucom.2024.128360_b28) 2018 Ho (10.1016/j.neucom.2024.128360_b29) 2020; 33 Islam (10.1016/j.neucom.2024.128360_b3) 2020; 7 10.1016/j.neucom.2024.128360_b56 10.1016/j.neucom.2024.128360_b55 10.1016/j.neucom.2024.128360_b58 Kazerouni (10.1016/j.neucom.2024.128360_b30) 2022 Dorjsembe (10.1016/j.neucom.2024.128360_b31) 2023 Huang (10.1016/j.neucom.2024.128360_b2) 2023; 535 Kingma (10.1016/j.neucom.2024.128360_b16) 2013 Krizhevsky (10.1016/j.neucom.2024.128360_b57) 2012; 25 Krizhevsky (10.1016/j.neucom.2024.128360_b7) 2017; 60 Niyas (10.1016/j.neucom.2024.128360_b39) 2022; 493 Simonyan (10.1016/j.neucom.2024.128360_b48) 2014 Pesteie (10.1016/j.neucom.2024.128360_b40) 2019; 38 Lundervold (10.1016/j.neucom.2024.128360_b1) 2019; 29 Rezende (10.1016/j.neucom.2024.128360_b26) 2015 Chadebec (10.1016/j.neucom.2024.128360_b18) 2021 Huang (10.1016/j.neucom.2024.128360_b4) 2022; 149 Dai (10.1016/j.neucom.2024.128360_b19) 2023; 161 Kebaili (10.1016/j.neucom.2024.128360_b20) 2023 Johnson (10.1016/j.neucom.2024.128360_b47) 2016 Stahlschmidt (10.1016/j.neucom.2024.128360_b46) 2022; 23 Biffi (10.1016/j.neucom.2024.128360_b42) 2018 Ronneberger (10.1016/j.neucom.2024.128360_b59) 2015 Trullo (10.1016/j.neucom.2024.128360_b6) 2019; 6 Odena (10.1016/j.neucom.2024.128360_b15) 2016 Kingma (10.1016/j.neucom.2024.128360_b21) 2016; 29 10.1016/j.neucom.2024.128360_b61 Zhuang (10.1016/j.neucom.2024.128360_b41) 2019 Razavi (10.1016/j.neucom.2024.128360_b22) 2019; 32 Vaswani (10.1016/j.neucom.2024.128360_b49) 2017; 30 Dosovitskiy (10.1016/j.neucom.2024.128360_b60) 2020 Li (10.1016/j.neucom.2024.128360_b14) 2022 Mescheder (10.1016/j.neucom.2024.128360_b12) 2018 Xiao (10.1016/j.neucom.2024.128360_b17) 2021 Heusel (10.1016/j.neucom.2024.128360_b54) 2017; 30 Oktay (10.1016/j.neucom.2024.128360_b63) 2018 Goodfellow (10.1016/j.neucom.2024.128360_b9) 2014 Wang (10.1016/j.neucom.2024.128360_b10) 2023; 546 Chen (10.1016/j.neucom.2024.128360_b34) 2023 Gan (10.1016/j.neucom.2024.128360_b37) 2022; 13 Tomczak (10.1016/j.neucom.2024.128360_b24) 2018 Kebaili (10.1016/j.neucom.2024.128360_b8) 2023; 9 Shrivastava (10.1016/j.neucom.2024.128360_b33) 2023 10.1016/j.neucom.2024.128360_b36 Dilokthanakul (10.1016/j.neucom.2024.128360_b23) 2016 Huo (10.1016/j.neucom.2024.128360_b44) 2022 Bond-Taylor (10.1016/j.neucom.2024.128360_b13) 2021 Ma (10.1016/j.neucom.2024.128360_b51) 2024; 15 Caterini (10.1016/j.neucom.2024.128360_b45) 2018; 31 Chen (10.1016/j.neucom.2024.128360_b11) 2022 Baid (10.1016/j.neucom.2024.128360_b52) 2021 Kingma (10.1016/j.neucom.2024.128360_b25) 2016; 29 Isensee (10.1016/j.neucom.2024.128360_b64) 2018 Isola (10.1016/j.neucom.2024.128360_b50) 2016 Han (10.1016/j.neucom.2024.128360_b35) 2023 Song (10.1016/j.neucom.2024.128360_b5) 2021; 18 Andrearczyk (10.1016/j.neucom.2024.128360_b53) 2021 Liang (10.1016/j.neucom.2024.128360_b38) 2021 Hatamizadeh (10.1016/j.neucom.2024.128360_b62) 2021 Stojanovski (10.1016/j.neucom.2024.128360_b32) 2023 Volokitin (10.1016/j.neucom.2024.128360_b43) 2020 Chadebec (10.1016/j.neucom.2024.128360_b27) 2022 |
| References_xml | – volume: 149 start-page: 39 year: 2022 end-page: 60 ident: b4 article-title: Lymphoma segmentation from 3D PET-CT images using a deep evidential network publication-title: Internat. J. Approx. Reason. – year: 2021 ident: b17 article-title: Tackling the generative learning trilemma with denoising diffusion gans – volume: 493 start-page: 397 year: 2022 end-page: 413 ident: b39 article-title: Medical image segmentation with 3D convolutional neural networks: A survey publication-title: Neurocomputing – year: 2022 ident: b30 article-title: Diffusion models for medical image analysis: A comprehensive survey – volume: 161 year: 2023 ident: b19 article-title: Swin MAE: Masked autoencoders for small datasets publication-title: Comput. Biol. Med. – volume: 31 year: 2018 ident: b45 article-title: Hamiltonian variational auto-encoder publication-title: Adv. Neural Inf. Process. Syst. – year: 2023 ident: b31 article-title: Conditional diffusion models for semantic 3D medical image synthesis – volume: 13 start-page: 1188 year: 2022 end-page: 1201 ident: b37 article-title: Esophageal optical coherence tomography image synthesis using an adversarially learned variational autoencoder publication-title: Biomed. Opt. Express – volume: 25 year: 2012 ident: b57 article-title: Imagenet classification with deep convolutional neural networks publication-title: Adv. Neural Inf. Process. Syst. – start-page: 34 year: 2023 end-page: 43 ident: b32 article-title: Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation publication-title: International Workshop on Advances in Simplifying Medical Ultrasound – volume: 18 start-page: 2775 year: 2021 end-page: 2780 ident: b5 article-title: Deep learning enables accurate diagnosis of novel coronavirus (COVID-19) with CT images publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform. – reference: Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684–10695. – volume: 7 start-page: 1 year: 2020 end-page: 12 ident: b3 article-title: GAN-based synthetic brain PET image generation publication-title: Brain Inform. – start-page: 759 year: 2023 end-page: 769 ident: b35 article-title: Medgen3d: A deep generative framework for paired 3d image and mask generation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 1214 year: 2018 end-page: 1223 ident: b24 article-title: VAE with a VampPrior publication-title: International Conference on Artificial Intelligence and Statistics – volume: 30 year: 2017 ident: b54 article-title: Gans trained by a two time-scale update rule converge to a local nash equilibrium publication-title: Adv. Neural Inf. Process. Syst. – year: 2014 ident: b48 article-title: Very deep convolutional networks for large-scale image recognition – reference: Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, Oliver Wang, The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 586–595. – volume: 9 start-page: 81 year: 2023 ident: b8 article-title: Deep learning approaches for data augmentation in medical imaging: A review publication-title: J. Imaging – year: 2023 ident: b33 article-title: NASDM: Nuclei-aware semantic histopathology image generation using diffusion models – start-page: 1 year: 2021 end-page: 4 ident: b38 article-title: Data augmentation of thyroid ultrasound images using generative adversarial network publication-title: 2021 IEEE International Ultrasonics Symposium – volume: 30 year: 2017 ident: b49 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – volume: 15 start-page: 654 year: 2024 ident: b51 article-title: Segment anything in medical images publication-title: Nature Commun. – year: 2018 ident: b63 article-title: Attention u-net: Learning where to look for the pancreas – year: 2014 ident: b9 article-title: Generative adversarial networks – start-page: 1530 year: 2015 end-page: 1538 ident: b26 article-title: Variational inference with normalizing flows publication-title: International Conference on Machine Learning – start-page: 1 year: 2021 end-page: 37 ident: b53 article-title: Overview of the HECKTOR challenge at MICCAI 2021: automatic head and neck tumor segmentation and outcome prediction in PET/CT images publication-title: 3D Head and Neck Tumor Segmentation in PET/CT Challenge – year: 2020 ident: b60 article-title: An image is worth 16x16 words: Transformers for image recognition at scale – start-page: 3481 year: 2018 end-page: 3490 ident: b12 article-title: Which training methods for GANs do actually converge? publication-title: International Conference on Machine Learning – start-page: 657 year: 2020 end-page: 666 ident: b43 article-title: Modelling the distribution of 3D brain MRI using a 2D slice VAE publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – year: 2016 ident: b50 article-title: Image-to-image translation with conditional adversarial networks – year: 2021 ident: b52 article-title: The rsna-asnr-miccai brats 2021 benchmark on brain tumor segmentation and radiogenomic classification – reference: Ali Hatamizadeh, Yucheng Tang, Vishwesh Nath, Dong Yang, Andriy Myronenko, Bennett Landman, Holger R Roth, Daguang Xu, Unetr: Transformers for 3d medical image segmentation, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 574–584. – volume: 60 start-page: 84 year: 2017 end-page: 90 ident: b7 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM – year: 2022 ident: b27 article-title: Data augmentation in high dimensional low sample size setting using a geometry-based variational autoencoder publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2023 ident: b34 article-title: BerDiff: Conditional Bernoulli diffusion model for medical image segmentation – start-page: 272 year: 2021 end-page: 284 ident: b62 article-title: Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images publication-title: International MICCAI Brainlesion Workshop – year: 2016 ident: b23 article-title: Deep unsupervised clustering with gaussian mixture variational autoencoders – volume: 29 year: 2016 ident: b25 article-title: Improved variational inference with inverse autoregressive flow publication-title: Adv. Neural Inf. Process. Syst. – start-page: 1783 year: 2019 end-page: 1787 ident: b41 article-title: Fmri data augmentation via synthesis publication-title: 2019 IEEE 16th International Symposium on Biomedical Imaging – volume: 535 start-page: 40 year: 2023 end-page: 52 ident: b2 article-title: Semi-supervised multiple evidence fusion for brain tumor segmentation publication-title: Neurocomputing – volume: 38 start-page: 2807 year: 2019 end-page: 2820 ident: b40 article-title: Adaptive augmentation of medical data using independently conditional variational auto-encoders publication-title: IEEE Trans. Med. Imaging – start-page: 464 year: 2018 end-page: 471 ident: b42 article-title: Learning interpretable anatomical features through deep generative models: Application to cardiac remodeling publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – year: 2023 ident: b20 article-title: End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks – volume: 23 start-page: bbab569 year: 2022 ident: b46 article-title: Multimodal deep learning for biomedical data fusion: a review publication-title: Brief. Bioinform. – year: 2013 ident: b16 article-title: Auto-encoding variational bayes – start-page: 694 year: 2016 end-page: 711 ident: b47 article-title: Perceptual losses for real-time style transfer and super-resolution publication-title: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part II 14 – reference: Xudong Mao, Qing Li, Haoran Xie, Raymond YK Lau, Zhen Wang, Stephen Paul Smolley, Least squares generative adversarial networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2794–2802. – year: 2022 ident: b14 article-title: A comprehensive survey on data-efficient GANs in image generation – volume: 546 year: 2023 ident: b10 article-title: FedMed-GAN: Federated domain translation on unsupervised cross-modality brain image synthesis publication-title: Neurocomputing – reference: Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, Going deeper with convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1–9. – volume: 33 start-page: 6840 year: 2020 end-page: 6851 ident: b29 article-title: Denoising diffusion probabilistic models publication-title: Adv. Neural Inf. Process. Syst. – year: 2016 ident: b15 article-title: Semi-supervised learning with generative adversarial networks – volume: 29 start-page: 102 year: 2019 end-page: 127 ident: b1 article-title: An overview of deep learning in medical imaging focusing on MRI publication-title: Z. Med. Phys. – volume: 32 year: 2019 ident: b22 article-title: Generating diverse high-fidelity images with vq-vae-2 publication-title: Adv. Neural Inf. Process. Syst. – year: 2021 ident: b13 article-title: Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2018 ident: b64 article-title: nnu-net: Self-adapting framework for u-net-based medical image segmentation – year: 2022 ident: b11 article-title: Generative adversarial networks in medical image augmentation: a review publication-title: Comput. Biol. Med. – volume: 6 year: 2019 ident: b6 article-title: Multiorgan segmentation using distance-aware adversarial networks publication-title: J. Med. Imaging – year: 2018 ident: b28 article-title: Hyperspherical variational auto-encoders – start-page: 234 year: 2015 end-page: 241 ident: b59 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 184 year: 2021 end-page: 192 ident: b18 article-title: Data augmentation with variational autoencoders and manifold sampling publication-title: Deep Generative Models, and Data Augmentation, Labelling, and Imperfections – volume: 29 year: 2016 ident: b21 article-title: Improved variational inference with inverse autoregressive flow publication-title: Adv. Neural Inf. Process. Syst. – start-page: 101 year: 2022 end-page: 111 ident: b44 article-title: Brain lesion synthesis via progressive adversarial variational auto-encoder publication-title: International Workshop on Simulation and Synthesis in Medical Imaging – year: 2014 ident: 10.1016/j.neucom.2024.128360_b9 – year: 2021 ident: 10.1016/j.neucom.2024.128360_b13 article-title: Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 32 year: 2019 ident: 10.1016/j.neucom.2024.128360_b22 article-title: Generating diverse high-fidelity images with vq-vae-2 publication-title: Adv. Neural Inf. Process. Syst. – start-page: 272 year: 2021 ident: 10.1016/j.neucom.2024.128360_b62 article-title: Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images – start-page: 694 year: 2016 ident: 10.1016/j.neucom.2024.128360_b47 article-title: Perceptual losses for real-time style transfer and super-resolution – volume: 149 start-page: 39 year: 2022 ident: 10.1016/j.neucom.2024.128360_b4 article-title: Lymphoma segmentation from 3D PET-CT images using a deep evidential network publication-title: Internat. J. Approx. Reason. doi: 10.1016/j.ijar.2022.06.007 – year: 2021 ident: 10.1016/j.neucom.2024.128360_b52 – volume: 60 start-page: 84 issue: 6 year: 2017 ident: 10.1016/j.neucom.2024.128360_b7 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM doi: 10.1145/3065386 – year: 2021 ident: 10.1016/j.neucom.2024.128360_b17 – volume: 9 start-page: 81 issue: 4 year: 2023 ident: 10.1016/j.neucom.2024.128360_b8 article-title: Deep learning approaches for data augmentation in medical imaging: A review publication-title: J. Imaging doi: 10.3390/jimaging9040081 – year: 2013 ident: 10.1016/j.neucom.2024.128360_b16 – volume: 30 year: 2017 ident: 10.1016/j.neucom.2024.128360_b49 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – volume: 30 year: 2017 ident: 10.1016/j.neucom.2024.128360_b54 article-title: Gans trained by a two time-scale update rule converge to a local nash equilibrium publication-title: Adv. Neural Inf. Process. Syst. – start-page: 34 year: 2023 ident: 10.1016/j.neucom.2024.128360_b32 article-title: Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation – volume: 38 start-page: 2807 issue: 12 year: 2019 ident: 10.1016/j.neucom.2024.128360_b40 article-title: Adaptive augmentation of medical data using independently conditional variational auto-encoders publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2019.2914656 – start-page: 101 year: 2022 ident: 10.1016/j.neucom.2024.128360_b44 article-title: Brain lesion synthesis via progressive adversarial variational auto-encoder – volume: 29 year: 2016 ident: 10.1016/j.neucom.2024.128360_b21 article-title: Improved variational inference with inverse autoregressive flow publication-title: Adv. Neural Inf. Process. Syst. – year: 2016 ident: 10.1016/j.neucom.2024.128360_b23 – year: 2023 ident: 10.1016/j.neucom.2024.128360_b34 – start-page: 464 year: 2018 ident: 10.1016/j.neucom.2024.128360_b42 article-title: Learning interpretable anatomical features through deep generative models: Application to cardiac remodeling – ident: 10.1016/j.neucom.2024.128360_b55 doi: 10.1109/CVPR.2015.7298594 – start-page: 1214 year: 2018 ident: 10.1016/j.neucom.2024.128360_b24 article-title: VAE with a VampPrior – start-page: 1 year: 2021 ident: 10.1016/j.neucom.2024.128360_b38 article-title: Data augmentation of thyroid ultrasound images using generative adversarial network – year: 2014 ident: 10.1016/j.neucom.2024.128360_b48 – volume: 13 start-page: 1188 issue: 3 year: 2022 ident: 10.1016/j.neucom.2024.128360_b37 article-title: Esophageal optical coherence tomography image synthesis using an adversarially learned variational autoencoder publication-title: Biomed. Opt. Express doi: 10.1364/BOE.449796 – year: 2020 ident: 10.1016/j.neucom.2024.128360_b60 – volume: 33 start-page: 6840 year: 2020 ident: 10.1016/j.neucom.2024.128360_b29 article-title: Denoising diffusion probabilistic models publication-title: Adv. Neural Inf. Process. Syst. – volume: 29 start-page: 102 issue: 2 year: 2019 ident: 10.1016/j.neucom.2024.128360_b1 article-title: An overview of deep learning in medical imaging focusing on MRI publication-title: Z. Med. Phys. doi: 10.1016/j.zemedi.2018.11.002 – volume: 25 year: 2012 ident: 10.1016/j.neucom.2024.128360_b57 article-title: Imagenet classification with deep convolutional neural networks publication-title: Adv. Neural Inf. Process. Syst. – year: 2018 ident: 10.1016/j.neucom.2024.128360_b63 – start-page: 1530 year: 2015 ident: 10.1016/j.neucom.2024.128360_b26 article-title: Variational inference with normalizing flows – start-page: 759 year: 2023 ident: 10.1016/j.neucom.2024.128360_b35 article-title: Medgen3d: A deep generative framework for paired 3d image and mask generation – volume: 535 start-page: 40 year: 2023 ident: 10.1016/j.neucom.2024.128360_b2 article-title: Semi-supervised multiple evidence fusion for brain tumor segmentation publication-title: Neurocomputing doi: 10.1016/j.neucom.2023.02.047 – year: 2023 ident: 10.1016/j.neucom.2024.128360_b33 – year: 2018 ident: 10.1016/j.neucom.2024.128360_b28 – start-page: 1 year: 2021 ident: 10.1016/j.neucom.2024.128360_b53 article-title: Overview of the HECKTOR challenge at MICCAI 2021: automatic head and neck tumor segmentation and outcome prediction in PET/CT images – volume: 29 year: 2016 ident: 10.1016/j.neucom.2024.128360_b25 article-title: Improved variational inference with inverse autoregressive flow publication-title: Adv. Neural Inf. Process. Syst. – year: 2022 ident: 10.1016/j.neucom.2024.128360_b27 article-title: Data augmentation in high dimensional low sample size setting using a geometry-based variational autoencoder publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 234 year: 2015 ident: 10.1016/j.neucom.2024.128360_b59 article-title: U-net: Convolutional networks for biomedical image segmentation – year: 2022 ident: 10.1016/j.neucom.2024.128360_b14 – year: 2023 ident: 10.1016/j.neucom.2024.128360_b20 – start-page: 3481 year: 2018 ident: 10.1016/j.neucom.2024.128360_b12 article-title: Which training methods for GANs do actually converge? – volume: 6 issue: 1 year: 2019 ident: 10.1016/j.neucom.2024.128360_b6 article-title: Multiorgan segmentation using distance-aware adversarial networks publication-title: J. Med. Imaging doi: 10.1117/1.JMI.6.1.014001 – ident: 10.1016/j.neucom.2024.128360_b58 – year: 2016 ident: 10.1016/j.neucom.2024.128360_b50 – volume: 7 start-page: 1 issue: 1 year: 2020 ident: 10.1016/j.neucom.2024.128360_b3 article-title: GAN-based synthetic brain PET image generation publication-title: Brain Inform. doi: 10.1186/s40708-020-00104-2 – volume: 546 year: 2023 ident: 10.1016/j.neucom.2024.128360_b10 article-title: FedMed-GAN: Federated domain translation on unsupervised cross-modality brain image synthesis publication-title: Neurocomputing doi: 10.1016/j.neucom.2023.126282 – volume: 15 start-page: 654 issue: 1 year: 2024 ident: 10.1016/j.neucom.2024.128360_b51 article-title: Segment anything in medical images publication-title: Nature Commun. doi: 10.1038/s41467-024-44824-z – year: 2016 ident: 10.1016/j.neucom.2024.128360_b15 – volume: 23 start-page: bbab569 issue: 2 year: 2022 ident: 10.1016/j.neucom.2024.128360_b46 article-title: Multimodal deep learning for biomedical data fusion: a review publication-title: Brief. Bioinform. doi: 10.1093/bib/bbab569 – volume: 161 year: 2023 ident: 10.1016/j.neucom.2024.128360_b19 article-title: Swin MAE: Masked autoencoders for small datasets publication-title: Comput. Biol. Med. – volume: 18 start-page: 2775 issue: 6 year: 2021 ident: 10.1016/j.neucom.2024.128360_b5 article-title: Deep learning enables accurate diagnosis of novel coronavirus (COVID-19) with CT images publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform. doi: 10.1109/TCBB.2021.3065361 – start-page: 184 year: 2021 ident: 10.1016/j.neucom.2024.128360_b18 article-title: Data augmentation with variational autoencoders and manifold sampling – volume: 31 year: 2018 ident: 10.1016/j.neucom.2024.128360_b45 article-title: Hamiltonian variational auto-encoder publication-title: Adv. Neural Inf. Process. Syst. – year: 2022 ident: 10.1016/j.neucom.2024.128360_b30 – start-page: 1783 year: 2019 ident: 10.1016/j.neucom.2024.128360_b41 article-title: Fmri data augmentation via synthesis – volume: 493 start-page: 397 year: 2022 ident: 10.1016/j.neucom.2024.128360_b39 article-title: Medical image segmentation with 3D convolutional neural networks: A survey publication-title: Neurocomputing doi: 10.1016/j.neucom.2022.04.065 – year: 2022 ident: 10.1016/j.neucom.2024.128360_b11 article-title: Generative adversarial networks in medical image augmentation: a review publication-title: Comput. Biol. Med. – year: 2023 ident: 10.1016/j.neucom.2024.128360_b31 – ident: 10.1016/j.neucom.2024.128360_b56 doi: 10.1109/CVPR.2018.00068 – ident: 10.1016/j.neucom.2024.128360_b36 doi: 10.1109/CVPR52688.2022.01042 – start-page: 657 year: 2020 ident: 10.1016/j.neucom.2024.128360_b43 article-title: Modelling the distribution of 3D brain MRI using a 2D slice VAE – ident: 10.1016/j.neucom.2024.128360_b61 doi: 10.1109/WACV51458.2022.00181 – year: 2018 ident: 10.1016/j.neucom.2024.128360_b64 |
| SSID | ssj0017129 |
| Score | 2.4559722 |
| Snippet | Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge... |
| SourceID | hal crossref elsevier |
| SourceType | Open Access Repository Enrichment Source Index Database Publisher |
| StartPage | 128360 |
| SubjectTerms | Data augmentation Deep learning Generative modeling Hamiltonian Variational Autoencoder Life Sciences MRI PET Tumor segmentation Variational Autoencoder |
| Title | Discriminative Hamiltonian variational autoencoder for accurate tumor segmentation in data-scarce regimes |
| URI | https://dx.doi.org/10.1016/j.neucom.2024.128360 https://hal.science/hal-04782076 |
| Volume | 606 |
| WOSCitedRecordID | wos001302503200001&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 issn: 0925-2312 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0017129 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6lLQcuvFHLSyvELXLl966PAYoCiqoKFZSbtV6vW0eNEyVxVP4Ov5QZ767tUEHpgYuVWPba8nyeHc9-8w0h7-LcC3NcZC1cN3dCGQsnKzLlFEwVihdceIVsmk2w01M-nSZng8FPWwuzvWJVxa-vk-V_NTXsA2Nj6ewdzN0OCjvgNxgdtmB22P6T4T-W6AmQ4dKwgsaYwYAAD1_kLXwY2-SfqDcLFLFELYmGSSlljbIRw009h79rdTE3ZUkNFxKZpM5aYmXkEJs52MKRmVV_qmEmbDpEmNzDaI4SDDnireNzq0yUuh57hELaHX9xIpb1D5ErZyIuF6uLWmf29Sp-s5j_Ppy3EPyumuZIwzOY0jvu7tfa5HLrfibDD7GkT1eQ2pSkHzkQb-5459jt-1eYTQPdf-CG69dZiNlxpWrkAeEFjrvDd5W2f5sBW16ipbzNUj1KiqOkepQ9cuCzKAHPeTD6fDL90q5VMc_Xio7m7m2BZsMivHk3fwqA9i5tKr8Jbc4fkQfmm4SONJYek4GqnpCHtt8HNe7_KSl3oUV70KI9aNEetChAi1po0QZatA8tWla0By1qoPWMfPt0cv5h7JhWHY4MQnfjcCF4piIuC1d4ucdUwoJE-TFPWBQKiPJVlng5TKzCc2ORZznEqUEslQyyhMHDCZ6T_WpRqUNCmYQYmmeCRYKHfsgyGSQuy90EHEcQ8fiIBPb5pdLo2GM7lav0b9Y7Ik571lLruNxyPLOmSU0sqmPMFPB2y5lvwZLtRVC-fTyapLgPlbB8l8Vb78Udb-clud-9Ma_I_mZVq9fkntxuyvXqjUHkL9dcu9A |
| 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=Discriminative+Hamiltonian+variational+autoencoder+for+accurate+tumor+segmentation+in+data-scarce+regimes&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Kebaili%2C+Aghiles&rft.au=Lapuyade-Lahorgue%2C+J%C3%A9r%C3%B4me&rft.au=Vera%2C+Pierre&rft.au=Ruan%2C+Su&rft.date=2024-11-14&rft.issn=0925-2312&rft.volume=606&rft.spage=128360&rft_id=info:doi/10.1016%2Fj.neucom.2024.128360&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neucom_2024_128360 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |