Learning Deep Representations of Cardiac Structures for 4D Cine MRI Image Segmentation through Semi-Supervised Learning
Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model—namely, combine-all in semi...
Uloženo v:
| Vydáno v: | Applied sciences Ročník 12; číslo 23; s. 12163 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Switzerland
MDPI AG
01.12.2022
|
| Témata: | |
| ISSN: | 2076-3417, 2076-3417 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model—namely, combine-all in semi-supervised learning (CqSL)—to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured L2 similarity (SL2SIM) loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (CqSL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly. |
|---|---|
| AbstractList | Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model—namely, combine-all in semi-supervised learning (CqSL)—to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured L2 similarity (SL2SIM) loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (CqSL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly. Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model-namely, combine-all in semi-supervised learning (CqSL)-to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured L 2 similarity ( S L 2 SIM ) loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (CqSL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly.Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model-namely, combine-all in semi-supervised learning (CqSL)-to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured L 2 similarity ( S L 2 SIM ) loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (CqSL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly. Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model-namely, combine-all in semi-supervised learning (C SL)-to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured similarity loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (C SL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly. Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model—namely, combine-all in semi-supervised learning (CqSL)—to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured L2 similarity (S L2 SIM) loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (CqSL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly. |
| Author | Hasan, S. M. Kamrul Linte, Cristian A. |
| AuthorAffiliation | 1 Center for Imaging Science, Rochester Institute of Technology, Rochester, NY 14623, USA 2 Department of Biomedical Engineering, Rochester Institute of Technology, Rochester, NY 14623, USA |
| AuthorAffiliation_xml | – name: 2 Department of Biomedical Engineering, Rochester Institute of Technology, Rochester, NY 14623, USA – name: 1 Center for Imaging Science, Rochester Institute of Technology, Rochester, NY 14623, USA |
| Author_xml | – sequence: 1 givenname: S. M. Kamrul surname: Hasan fullname: Hasan, S. M. Kamrul – sequence: 2 givenname: Cristian A. surname: Linte fullname: Linte, Cristian A. |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37125242$$D View this record in MEDLINE/PubMed |
| BookMark | eNptkk1v1DAQhi1UREvpjTOyxIUDAX8lsU8IbflYaRFSF86WY0-yXiVxsJMi_j2G7aJthS-2Zt55_NozT9HZGEZA6DklbzhX5K2ZJsoYp4xW_BG6YKSuCi5ofXZyPkdXKe1JXopySckTdM5rykom2AX6uQETRz92-BpgwjcwRUgwzmb2YUw4tHhlovPG4u0cFzsvOY3bELG4xis_Av5ys8brwXSAt9ANx0o872JYul0ODr7YLhPEW5_A4eN1z9Dj1vQJru72S_T944dvq8_F5uun9er9prCiVnPBm7qpbWOpIJZXRpFW8co6wtqaUqekbEruWOMA2kqB5KQqlZG1BOpK46Tll2h94Lpg9nqKfjDxlw7G67-BEDtt4uxtD9oZBSCt5EJWQrZUiUoxZWXdAlWVoJn17sCalmYAZ_Njo-nvQe9nRr_TXbjVlFAuFCWZ8OqOEMOPBdKsB58s9L0ZISxJM0kkoyVXKktfPpDuwxLH_Fea1UKWueklz6oXp5b-eTk2OAvYQWBjSClCq60_tCg79H22pv8Mkj4dpFz0-kHRkftf-W9R1skA |
| CitedBy_id | crossref_primary_10_3390_app13020984 |
| Cites_doi | 10.1007/978-3-030-00889-5_1 10.1109/TPAMI.2013.50 10.1007/978-3-319-68127-6_1 10.1109/CVPR.2016.265 10.1609/aaai.v32i1.11671 10.1016/j.media.2019.101535 10.1007/978-3-319-66179-7_47 10.1145/3236386.3241340 10.1109/CVPR.2017.632 10.1109/CVPR.2017.316 10.1109/CVPR42600.2020.01070 10.1109/WACV51458.2022.00130 10.1007/978-3-319-24574-4_28 10.1162/neco_a_01458 10.1109/ICCV.2017.606 10.1145/3523055 10.1109/BIBM55620.2022.9995040 10.1109/ICCV.2017.167 10.1007/978-3-319-66185-8_29 10.1109/CVPR52688.2022.01565 10.1109/CVPR.2017.437 10.1109/JBHI.2021.3094311 10.1109/CVPR.2019.00244 10.1109/ICCV.2017.304 10.1109/42.906421 10.1007/978-3-030-01219-9_11 10.1007/978-3-031-12053-4_28 10.1007/978-3-030-00919-9_17 10.18653/v1/2020.emnlp-main.101 10.1109/ICCV.2017.244 10.1109/TMI.2018.2837502 10.1109/CVPR42600.2020.00500 |
| ContentType | Journal Article |
| Copyright | 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | AAYXX CITATION NPM ABUWG AFKRA AZQEC BENPR CCPQU DWQXO PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA |
| DOI | 10.3390/app122312163 |
| DatabaseName | CrossRef PubMed ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One ProQuest Central ProQuest Central Premium ProQuest One Academic Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central China ProQuest Central ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic Publicly Available Content Database CrossRef PubMed |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Sciences (General) |
| EISSN | 2076-3417 |
| ExternalDocumentID | oai_doaj_org_article_da9ee8c8348648f1946929c87fe19641 PMC10134910 37125242 10_3390_app122312163 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: NIGMS NIH HHS grantid: R35 GM128877 |
| GroupedDBID | .4S 2XV 5VS 7XC 8CJ 8FE 8FG 8FH AADQD AAFWJ AAYXX ADBBV ADMLS AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS APEBS ARCSS BCNDV BENPR CCPQU CITATION CZ9 D1I D1J D1K GROUPED_DOAJ IAO IGS ITC K6- K6V KC. KQ8 L6V LK5 LK8 M7R MODMG M~E OK1 P62 PHGZM PHGZT PIMPY PROAC TUS ABJCF ARAPS ATCPS BBNVY BHPHI BKSAR HCIFZ K7- KB. M0K M7P M7S N95 NPM PATMY PCBAR PDBOC PYCSY ABUWG AZQEC DWQXO PKEHL PQEST PQQKQ PQUKI PRINS 7X8 PUEGO 5PM |
| ID | FETCH-LOGICAL-c479t-3b7b7cbc140c36a90f936cd02f711d988b53d2bdeef69e830659a878e1d5ad8c3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 2 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000895998300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2076-3417 |
| IngestDate | Fri Oct 03 12:42:48 EDT 2025 Tue Nov 04 02:07:09 EST 2025 Fri Sep 05 06:37:14 EDT 2025 Mon Jun 30 11:31:32 EDT 2025 Wed Feb 19 02:24:02 EST 2025 Sat Nov 29 07:12:27 EST 2025 Tue Nov 18 21:41:32 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 23 |
| Keywords | generative adversarial network image quality disentangled representation cardiac segmentation reconstruction domain invariant features mutual information augmentation variational autoencoder |
| Language | English |
| License | This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c479t-3b7b7cbc140c36a90f936cd02f711d988b53d2bdeef69e830659a878e1d5ad8c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Author Contributions: Conceptualization, S.M.K.H. and C.A.L.; methodology, S.M.K.H.; software, S.M.K.H.; validation, S.M.K.H.; formal analysis, S.M.K.H. and C.A.L.; resources, S.M.K.H. and C.A.L.; writing—original draft preparation, S.M.K.H.; writing—review and editing, S.M.K.H. and C.A.L.; visualization, S.M.K.H.; supervision, C.A.L.; funding acquisition, C.A.L. All authors have read and agreed to the published version of the manuscript. |
| OpenAccessLink | https://doaj.org/article/da9ee8c8348648f1946929c87fe19641 |
| PMID | 37125242 |
| PQID | 2748523153 |
| PQPubID | 2032433 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_da9ee8c8348648f1946929c87fe19641 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10134910 proquest_miscellaneous_2808215399 proquest_journals_2748523153 pubmed_primary_37125242 crossref_citationtrail_10_3390_app122312163 crossref_primary_10_3390_app122312163 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-12-01 |
| PublicationDateYYYYMMDD | 2022-12-01 |
| PublicationDate_xml | – month: 12 year: 2022 text: 2022-12-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Basel |
| PublicationTitle | Applied sciences |
| PublicationTitleAlternate | Appl Sci (Basel) |
| PublicationYear | 2022 |
| Publisher | MDPI AG |
| Publisher_xml | – name: MDPI AG |
| References | ref_50 Elakkiya (ref_6) 2021; 26 ref_14 ref_12 ref_56 ref_11 ref_55 ref_10 ref_53 ref_52 ref_51 ref_19 ref_18 ref_17 ref_16 ref_15 Bengio (ref_25) 2013; 35 Lipton (ref_26) 2018; 16 Chartsias (ref_49) 2019; 58 ref_24 ref_23 ref_22 ref_21 ref_20 ref_29 ref_28 ref_27 Frangi (ref_54) 2001; 20 ref_36 ref_35 ref_34 Marino (ref_40) 2022; 34 ref_33 ref_32 ref_31 ref_30 ref_39 ref_38 ref_37 Gomes (ref_13) 2022; 55 ref_47 ref_46 ref_45 ref_44 ref_43 ref_42 ref_41 Bernard (ref_48) 2018; 37 ref_1 ref_3 ref_2 ref_9 ref_8 ref_5 ref_4 ref_7 |
| References_xml | – ident: ref_5 – ident: ref_51 – ident: ref_42 doi: 10.1007/978-3-030-00889-5_1 – volume: 35 start-page: 1798 year: 2013 ident: ref_25 article-title: Representation learning: A review and new perspectives publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2013.50 – ident: ref_20 doi: 10.1007/978-3-319-68127-6_1 – ident: ref_32 doi: 10.1109/CVPR.2016.265 – ident: ref_38 doi: 10.1609/aaai.v32i1.11671 – ident: ref_23 – volume: 58 start-page: 101535 year: 2019 ident: ref_49 article-title: Disentangled representation learning in cardiac image analysis publication-title: Med. Image Anal. doi: 10.1016/j.media.2019.101535 – ident: ref_8 – ident: ref_4 – ident: ref_31 – ident: ref_56 – ident: ref_19 doi: 10.1007/978-3-319-66179-7_47 – ident: ref_27 – ident: ref_52 – volume: 16 start-page: 31 year: 2018 ident: ref_26 article-title: The mythos of model interpretability publication-title: Queue doi: 10.1145/3236386.3241340 – ident: ref_41 – ident: ref_28 doi: 10.1109/CVPR.2017.632 – ident: ref_34 doi: 10.1109/CVPR.2017.316 – ident: ref_45 – ident: ref_9 doi: 10.1109/CVPR42600.2020.01070 – ident: ref_22 doi: 10.1109/WACV51458.2022.00130 – ident: ref_53 – ident: ref_55 doi: 10.1007/978-3-319-24574-4_28 – ident: ref_24 – volume: 34 start-page: 1 year: 2022 ident: ref_40 article-title: Predictive coding, variational autoencoders, and biological connections publication-title: Neural Comput. doi: 10.1162/neco_a_01458 – ident: ref_47 – ident: ref_16 doi: 10.1109/ICCV.2017.606 – ident: ref_11 – volume: 55 start-page: 1 year: 2022 ident: ref_13 article-title: A survey on semi-supervised learning for delayed partially labelled data streams publication-title: ACM Comput. Surv. (CSUR) doi: 10.1145/3523055 – ident: ref_3 doi: 10.1109/BIBM55620.2022.9995040 – ident: ref_37 doi: 10.1109/ICCV.2017.167 – ident: ref_10 doi: 10.1007/978-3-319-66185-8_29 – ident: ref_15 doi: 10.1109/CVPR52688.2022.01565 – ident: ref_35 doi: 10.1109/CVPR.2017.437 – volume: 26 start-page: 1464 year: 2021 ident: ref_6 article-title: Cervical cancer diagnostics healthcare system using hybrid object detection adversarial networks publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2021.3094311 – ident: ref_14 – ident: ref_18 – ident: ref_44 – ident: ref_21 – ident: ref_39 doi: 10.1109/CVPR.2019.00244 – ident: ref_46 doi: 10.1109/ICCV.2017.304 – volume: 20 start-page: 2 year: 2001 ident: ref_54 article-title: Three-dimensional modeling for functional analysis of cardiac images, a review publication-title: IEEE Trans. Med. Imaging doi: 10.1109/42.906421 – ident: ref_30 doi: 10.1007/978-3-030-01219-9_11 – ident: ref_7 doi: 10.1007/978-3-031-12053-4_28 – ident: ref_17 doi: 10.1007/978-3-030-00919-9_17 – ident: ref_50 – ident: ref_33 – ident: ref_2 – ident: ref_12 – ident: ref_43 doi: 10.18653/v1/2020.emnlp-main.101 – ident: ref_29 doi: 10.1109/ICCV.2017.244 – volume: 37 start-page: 2514 year: 2018 ident: ref_48 article-title: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved? publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2018.2837502 – ident: ref_36 – ident: ref_1 doi: 10.1109/CVPR42600.2020.00500 |
| SSID | ssj0000913810 |
| Score | 2.2457538 |
| Snippet | Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 12163 |
| SubjectTerms | Annotations augmentation cardiac segmentation disentangled representation domain invariant features generative adversarial network image quality Medical imaging Methods Semantics |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fb9MwED7BxgN7ADZgBAYyEkggFBHHbmw_IdZtYg9UUwvS3iLHP0olmpRlhX-fc-qUFgEvvMaXxJK_O9_5zt8BvGC8yr3JfMqF0CkfVD7VPmTZM29Ypg2CynbNJsRoJC8v1UU8cGtjWWVvEztDbRsTzsjfYvQkMWhCBX23-JaGrlEhuxpbaNyE3cBUhjjfPT4dXYzXpyyB9VLSbFXxzjC-D3lhilsizWnBtvaijrL_T37m7-WSG_vP2d3_nfk9uBM9T_J-BZV9uOHqA9jb4CM8gP2o6S15FemoX9-HH5GCdUpOnFuQcVc6G28s1S1pPBl2KDNk0nHRLnGYoCtM-AkZ4rfJx_E5OZ-j3SITN533b5LYIQgfzmfpZLkIRqt1lvS_ewCfz04_DT-ksV1DarhQ1ymrRCVMZTBkM6zQKvOKFcZmuReUWiVlNWA2r6xzvlBOhpb1SkshHbUDbaVhD2Gnbmr3CAhavlxxVulMC264k8XA6pyxXGWaVTJL4E2_cKWJXOahpcbXEmOasMzl5jIn8HItvVhxePxF7jhgYC0TmLe7B83VtIyKXFqtnJNGMi4LLj1VvEAP00jhXeA2owkc9Sgoozloy18QSOD5ehgVOWRndO2aJcpI9MZoIApO4HAFuPVMmEA_FJ2pBOQWFLemuj1Sz750ZOFochlHn_Dxv-f1BG7n4WJHV6hzBDsIGPcUbpnv17P26llUq5_c6y2h priority: 102 providerName: ProQuest |
| Title | Learning Deep Representations of Cardiac Structures for 4D Cine MRI Image Segmentation through Semi-Supervised Learning |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/37125242 https://www.proquest.com/docview/2748523153 https://www.proquest.com/docview/2808215399 https://pubmed.ncbi.nlm.nih.gov/PMC10134910 https://doaj.org/article/da9ee8c8348648f1946929c87fe19641 |
| Volume | 12 |
| WOSCitedRecordID | wos000895998300001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Nb9MwFH-CwYEdEBtfgVEZCSQQipbEbmwfWbeJHlZVLUjlFDn-GJVoWq0r_Ps8O26VIhAXjolfEsf--X3Iz78H8IayunA6cynjXKWsX7tUOb_LnjlNM6URVCYUm-CjkZjN5LhT6svnhLX0wO3AnRolrRVaUCZKJhzG3CVadC24s55LKgQ-GZedYCroYJl76qo2051iXO_3g3M0hXmRl3TPBgWq_j_5l7-nSXbszuUjeBgdRvKx7egR3LHNMRx2aASP4Sgu0DV5F1mk3z-Gn5E59ZqcW7sik5DxGg8aNWuydGQQwKHJNFDIbrCZoAdL2DkZ4LvJ1WRIhgtUN2RqrxfbJ0ks7IM3F_N0ull5XbO2hmw_9wS-XF58HnxKY5WFVDMub1Na85rrWmOkpWmpZOYkLbXJCsfz3Egh6j41RW2sdaW0wleal0pwYXPTV0Zo-hQOmmVjnwNBhVVIRmuVKc40s6LsG1VQWshM0VpkCXzYjnulIwW5r4TxvcJQxM9S1Z2lBN7upFct9cZf5M78FO5kPGF2uIEwqiKMqn_BKIGTLQCquIrXFUbsAgN1NAoJvN414_rzmyqqscsNygh0onLP75vAsxYvu55Qju4j-kAJiD0k7XV1v6WZfwsc36gpKUNX7sX_-LmX8KDwpzZCFs4JHCCs7Cu4r3_cztc3PbjLZ6IH984uRuNJL6wjvBoPr8ZffwHmQSHI |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3fb9MwED6NDgl4ADZ-BQYYiUkgFJHEbmI_IAQt06qtVbVu0ngKjmOXSjQpy8rEP8XfyDl1SouAtz3wGjuJlXz3-c4-fwfwnLIsMiowPksS6bN2Znxp7C57YBQNpEJQ5XWxiWQw4KenYrgBP5qzMDatsuHEmqjzUtk18tcYPXEMmtBA386--rZqlN1dbUpoLGBxoL9fYMhWvel18f_uRtHeh-POvu-qCviKJeLcp1mSJSpTGFkoGksRGEFjlQeRScIwF5xnbZpHWa61iYXmtrK6kDzhOszbMueK4nOvwCazYG_B5rDXH35crupYlU0eBosMe0pFYPehQ5yCwyiM6drcV5cI-JNf-3t65sp8t3frf_tSt-Gm86zJu4UpbMGGLrbhxore4jZsOSaryAsnt_3yDlw4idkx6Wo9I0d1arA7kVVUpDSkU1uRIqNaa3eOzQRdfcK6pIPPJv2jHulNkZfJSI-nzZ3EVUDCi9OJP5rPLClXOifN6-7CyaV8jnvQKspCPwCCzB4JRjMZyIQppnnczmVEaSQCSTMeePCqAUqqnFa7LRnyJcWYzcIqXYWVB7vL3rOFRslf-r23mFv2scri9YXybJw6okpzKbTmilPGY8ZNKFiMHrTiidFWuy30YKdBXerorkp_Qc6DZ8tmJCq7-yQLXc6xD0dvM7RCyB7cXwB8ORKaoJ-NzqIHfA36a0Ndbykmn2sxdJxSKEOf9-G_x_UUru0f9w_Tw97g4BFcj-whljopaQdaCB79GK6qb-eT6uyJM2kCny7bNn4CEuuL2A |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3fb9MwED6NDiF4ADZ-BQYYiUkgFC2J3dh-QAhaKqqxqtqYNJ6C49ilEk3LsjLxr_HXcU6d0iLgbQ-8xk5iJd99vrPP3wE8pSxPrI5syDhXIWvnNlTW7bJHVtNIaQRVUReb4IOBODmRww340ZyFcWmVDSfWRF1MtVsj38PoSWDQhAa6Z31axLDbezX7GroKUm6ntSmnsYDIvvl-juFb9bLfxX-9myS9tx8670JfYSDUjMuzkOY85zrXGGVomioZWUlTXUSJ5XFcSCHyNi2SvDDGptIIV2VdKsGFiYu2KoSm-NxLsIkuOUtasDnsHww_Lld4nOKmiKNFtj2lMnJ70jFOx3ESp3RtHqzLBfzJx_09VXNl7uvd-J-_2k247j1u8nphIluwYcptuLaiw7gNW57hKvLMy3A_vwXnXnp2RLrGzMhhnTLsT2qVFZla0qmtS5OjWoN3js0EQwDCuqSDzyYHh33SnyBfkyMzmjR3El8ZCS9OxuHRfObIujIFaV53G44v5HPcgVY5Lc09IMj4iWQ0V5HiTDMj0nahEkoTGSmaiyiAFw1oMu013F0pkS8ZxnIOYtkqxALYXfaeLbRL_tLvjcPfso9THK8vTE9HmSewrFDSGKEFZSJlwsaSpehZa8GtcZpucQA7DQIzT4NV9gt-ATxZNiOBuV0pVZrpHPsI9EJjJ5AcwN0F2JcjoRz9b3QiAxBrZrA21PWWcvy5FknHqYYy9IXv_3tcj-EKGkT2vj_YfwBXE3e2pc5V2oEWYsc8hMv629m4On3krZvAp4s2jZ-9pJSY |
| 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=Learning+Deep+Representations+of+Cardiac+Structures+for+4D+Cine+MRI+Image+Segmentation+through+Semi-Supervised+Learning&rft.jtitle=Applied+sciences&rft.au=S.+M.+Kamrul+Hasan&rft.au=Cristian+A.+Linte&rft.date=2022-12-01&rft.pub=MDPI+AG&rft.eissn=2076-3417&rft.volume=12&rft.issue=23&rft.spage=12163&rft_id=info:doi/10.3390%2Fapp122312163&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_da9ee8c8348648f1946929c87fe19641 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2076-3417&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2076-3417&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2076-3417&client=summon |