Entropy‐guided contrastive learning for semi‐supervised medical image segmentation
Accurately segmenting medical images is a critical step in clinical diagnosis and developing patient‐specific treatment plans. While supervised learning algorithms have achieved excellent performance in this area, they require a large amount of annotated data, which is often time‐consuming and diffi...
Uloženo v:
| Vydáno v: | IET image processing Ročník 18; číslo 2; s. 312 - 326 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Wiley
01.02.2024
|
| Témata: | |
| ISSN: | 1751-9659, 1751-9667 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Accurately segmenting medical images is a critical step in clinical diagnosis and developing patient‐specific treatment plans. While supervised learning algorithms have achieved excellent performance in this area, they require a large amount of annotated data, which is often time‐consuming and difficult to obtain. As a result, semi‐supervised learning (SSL) has gained attention as it has the potential to alleviate this challenge by using not only limited labelled data but also a large amount of unlabelled data. A common approach in SSL is to filter out high‐entropy features and use the low‐entropy part to compute unsupervised loss. However, it is believed that the high‐entropy part is also beneficial for model training, and discarding it can lead to information loss. To address this issue, a simple yet efficient contrastive learning approach is proposed in this work for semi‐supervised medical image segmentation, called Entropy‐Guided Contrastive Learning Segmentation Network (EGCL‐Net). The proposed method separates the low‐entropy and high‐entropy features via the average of predictions, using contrastive loss to pull the intra‐class entropy representation distance close and push the inter‐class entropy representation distance away. Extensive experiments on the automated cardiac diagnosis challenge dataset, COVID‐19, and BraTS2019 datasets showed that: (1) EGCL‐Net can significantly improve performance by utilizing high‐entropy representation, and (2) the authors’ EGCL‐Net outperforms recent state‐of‐the‐art semi‐supervised methods in both qualitative and quantitative evaluations.
The authors proposed a simple yet efficient contrastive learning approach to make sufficient use of unlabelled data for semi‐supervised medical image segmentation. The contrastive loss is employed to pull the intra‐class entropy representation distance close and push the inter‐class entropy representation distance away. Extensive experiments on the automated cardiac diagnosis challenge dataset, COVID‐19, and BraTS2019 datasets demonstrate the effectiveness of the proposed method. |
|---|---|
| AbstractList | Accurately segmenting medical images is a critical step in clinical diagnosis and developing patient‐specific treatment plans. While supervised learning algorithms have achieved excellent performance in this area, they require a large amount of annotated data, which is often time‐consuming and difficult to obtain. As a result, semi‐supervised learning (SSL) has gained attention as it has the potential to alleviate this challenge by using not only limited labelled data but also a large amount of unlabelled data. A common approach in SSL is to filter out high‐entropy features and use the low‐entropy part to compute unsupervised loss. However, it is believed that the high‐entropy part is also beneficial for model training, and discarding it can lead to information loss. To address this issue, a simple yet efficient contrastive learning approach is proposed in this work for semi‐supervised medical image segmentation, called Entropy‐Guided Contrastive Learning Segmentation Network (EGCL‐Net). The proposed method separates the low‐entropy and high‐entropy features via the average of predictions, using contrastive loss to pull the intra‐class entropy representation distance close and push the inter‐class entropy representation distance away. Extensive experiments on the automated cardiac diagnosis challenge dataset, COVID‐19, and BraTS2019 datasets showed that: (1) EGCL‐Net can significantly improve performance by utilizing high‐entropy representation, and (2) the authors’ EGCL‐Net outperforms recent state‐of‐the‐art semi‐supervised methods in both qualitative and quantitative evaluations. Abstract Accurately segmenting medical images is a critical step in clinical diagnosis and developing patient‐specific treatment plans. While supervised learning algorithms have achieved excellent performance in this area, they require a large amount of annotated data, which is often time‐consuming and difficult to obtain. As a result, semi‐supervised learning (SSL) has gained attention as it has the potential to alleviate this challenge by using not only limited labelled data but also a large amount of unlabelled data. A common approach in SSL is to filter out high‐entropy features and use the low‐entropy part to compute unsupervised loss. However, it is believed that the high‐entropy part is also beneficial for model training, and discarding it can lead to information loss. To address this issue, a simple yet efficient contrastive learning approach is proposed in this work for semi‐supervised medical image segmentation, called Entropy‐Guided Contrastive Learning Segmentation Network (EGCL‐Net). The proposed method separates the low‐entropy and high‐entropy features via the average of predictions, using contrastive loss to pull the intra‐class entropy representation distance close and push the inter‐class entropy representation distance away. Extensive experiments on the automated cardiac diagnosis challenge dataset, COVID‐19, and BraTS2019 datasets showed that: (1) EGCL‐Net can significantly improve performance by utilizing high‐entropy representation, and (2) the authors’ EGCL‐Net outperforms recent state‐of‐the‐art semi‐supervised methods in both qualitative and quantitative evaluations. Accurately segmenting medical images is a critical step in clinical diagnosis and developing patient‐specific treatment plans. While supervised learning algorithms have achieved excellent performance in this area, they require a large amount of annotated data, which is often time‐consuming and difficult to obtain. As a result, semi‐supervised learning (SSL) has gained attention as it has the potential to alleviate this challenge by using not only limited labelled data but also a large amount of unlabelled data. A common approach in SSL is to filter out high‐entropy features and use the low‐entropy part to compute unsupervised loss. However, it is believed that the high‐entropy part is also beneficial for model training, and discarding it can lead to information loss. To address this issue, a simple yet efficient contrastive learning approach is proposed in this work for semi‐supervised medical image segmentation, called Entropy‐Guided Contrastive Learning Segmentation Network (EGCL‐Net). The proposed method separates the low‐entropy and high‐entropy features via the average of predictions, using contrastive loss to pull the intra‐class entropy representation distance close and push the inter‐class entropy representation distance away. Extensive experiments on the automated cardiac diagnosis challenge dataset, COVID‐19, and BraTS2019 datasets showed that: (1) EGCL‐Net can significantly improve performance by utilizing high‐entropy representation, and (2) the authors’ EGCL‐Net outperforms recent state‐of‐the‐art semi‐supervised methods in both qualitative and quantitative evaluations. The authors proposed a simple yet efficient contrastive learning approach to make sufficient use of unlabelled data for semi‐supervised medical image segmentation. The contrastive loss is employed to pull the intra‐class entropy representation distance close and push the inter‐class entropy representation distance away. Extensive experiments on the automated cardiac diagnosis challenge dataset, COVID‐19, and BraTS2019 datasets demonstrate the effectiveness of the proposed method. |
| Author | Xie, Junsong Wu, Qian Zhu, Renju |
| Author_xml | – sequence: 1 givenname: Junsong orcidid: 0000-0002-6845-0441 surname: Xie fullname: Xie, Junsong organization: Anhui Medical University – sequence: 2 givenname: Qian surname: Wu fullname: Wu, Qian email: ayd_wuqian@126.com organization: Anhui Medical University – sequence: 3 givenname: Renju surname: Zhu fullname: Zhu, Renju organization: Hefei BOE Hospital |
| BookMark | eNp9kM1KAzEUhYNUsP5sfIJZC603yUxmspTiT0FQRN2GTH6GlOmkJFOlOx_BZ_RJTDvqQsTVvdx853ByDtGo851B6BTDFEPOz90qkCkmvIA9NMZlgSecsXL0sxf8AB3GuAAoOFTFGD1fdn3wq83H23uzdtroTPl0kbF3LyZrjQyd65rM-pBFs3QJi-uVCS8uJnRptFOyzdxSNia9N0vT9bJ3vjtG-1a20Zx8zSP0dHX5OLuZ3N5dz2cXtxOV5wQmVgKwmuNc1zkjNKd1XVqtckZpJaXUpVUpqFUciAGMC4Yp2IqVAIRaSjA9QvPBV3u5EKuQkoSN8NKJ3cGHRsjQO9UaAUVVUixVaas6NxbXFeEVY5ppDhrXdfKCwUsFH2MwVig3_Cb14VqBQWw7FtuOxa7jJDn7JfmO8CeMB_jVtWbzDynm9w9k0HwC1K2RXA |
| CitedBy_id | crossref_primary_10_1177_08953996241301685 crossref_primary_10_1007_s00521_024_10934_4 |
| Cites_doi | 10.1109/TMI.2018.2837502 10.1016/j.media.2022.102447 10.1007/978-3-319-24574-4_28 10.1109/ICCV48922.2021.00042 10.1016/j.media.2022.102517 10.1109/TIP.2020.3011269 10.1049/ipr2.12419 10.1109/TCBB.2022.3144428 10.1101/2020.04.22.20074948 10.1109/ITME.2018.00080 10.1609/aaai.v36i3.20146 10.1016/j.media.2023.102792 10.1038/s41592-020-01008-z 10.1007/978-3-319-66185-8_29 10.1109/TNNLS.2020.2995319 10.2139/ssrn.4081789 10.1109/CVPR52729.2023.01895 10.1109/TMI.2014.2377694 10.1049/iet‐ipr.2017.1061 10.1109/CVPR52688.2022.00421 10.1109/3DV.2016.79 10.1016/j.knosys.2021.108021 10.1007/978-3-030-59861-7_4 10.1109/CVPR46437.2021.00264 10.1609/aaai.v35i10.17066 10.1007/s11263-020-01395-y 10.1049/sil2.12114 10.1016/j.neunet.2019.08.025 10.1016/j.compmedimag.2022.102092 10.1109/ISBI52829.2022.9761710 10.1109/CVPR.2019.00262 10.1109/CVPR.2017.243 10.1142/S0129065722500162 10.1609/aaai.v31i1.11231 10.1109/ICASSP40776.2020.9053405 10.7557/18.6798 10.1016/j.compbiomed.2022.106051 |
| ContentType | Journal Article |
| Copyright | 2023 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology. |
| Copyright_xml | – notice: 2023 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology. |
| DBID | 24P AAYXX CITATION DOA |
| DOI | 10.1049/ipr2.12950 |
| DatabaseName | Wiley Online Library Open Access CrossRef Directory of Open Access Journals (DOAJ) |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: 24P name: Wiley Online Library Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher – sequence: 2 dbid: DOA name: View article at DOAJ url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISSN | 1751-9667 |
| EndPage | 326 |
| ExternalDocumentID | oai_doaj_org_article_058731ac7f8b4ef1b829866d6d90d1bb 10_1049_ipr2_12950 IPR212950 |
| Genre | article |
| GrantInformation_xml | – fundername: Nature Science Foundation of the Anhui Provincial Higher Education Institutions of China funderid: 2022AH050660; KJ2021A0265 |
| GroupedDBID | .DC 0R~ 1OC 24P 29I 5GY 6IK 8VB AAHHS AAHJG AAJGR ABQXS ACCFJ ACCMX ACESK ACGFS ACIWK ACXQS ADZOD AEEZP AENEX AEQDE AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN AVUZU CS3 DU5 EBS ESX GROUPED_DOAJ HZ~ IAO IFIPE IPLJI ITC JAVBF LAI MCNEO MS~ O9- OCL OK1 P2P QWB RIE RNS ROL RUI ZL0 4.4 8FE 8FG AAMMB AAYXX ABJCF AEFGJ AFFHD AFKRA AGXDD AIDQK AIDYY ARAPS BENPR BGLVJ CCPQU CITATION EJD HCIFZ IDLOA K1G L6V M43 M7S P62 PHGZM PHGZT PQGLB PTHSS S0W WIN |
| ID | FETCH-LOGICAL-c4420-fa006b914db462343bb7fdc46338aaad7fc059fc902e01156130f8670023f3213 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001075788700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1751-9659 |
| IngestDate | Fri Oct 03 12:38:13 EDT 2025 Wed Nov 05 20:21:30 EST 2025 Tue Nov 18 22:12:25 EST 2025 Wed Jan 22 16:14:57 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Language | English |
| License | Attribution-NonCommercial-NoDerivs |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4420-fa006b914db462343bb7fdc46338aaad7fc059fc902e01156130f8670023f3213 |
| ORCID | 0000-0002-6845-0441 |
| OpenAccessLink | https://doaj.org/article/058731ac7f8b4ef1b829866d6d90d1bb |
| PageCount | 15 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_058731ac7f8b4ef1b829866d6d90d1bb crossref_citationtrail_10_1049_ipr2_12950 crossref_primary_10_1049_ipr2_12950 wiley_primary_10_1049_ipr2_12950_IPR212950 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-02-01 |
| PublicationDateYYYYMMDD | 2024-02-01 |
| PublicationDate_xml | – month: 02 year: 2024 text: 2024-02-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | IET image processing |
| PublicationYear | 2024 |
| Publisher | Wiley |
| Publisher_xml | – name: Wiley |
| References | 2015; 34 2017; 3 2022; 16(140) 2020; 121 2020; 12436 2021; 129 2021b 2022; 20 2022; 239 2015; 9351 2023; 87 2017; 31 2023 2022 2020; 32(2) 2021 2020 2021; 18 2022; 80 2020; 12261 2022; 79 2019 2018 2022; 36 2017 2016 2022; 32 2022; 99 2018; 12 2022; 16 2018; 37 2020; 29 e_1_2_10_23_1 e_1_2_10_46_1 e_1_2_10_21_1 e_1_2_10_44_1 e_1_2_10_42_1 e_1_2_10_40_1 e_1_2_10_2_1 e_1_2_10_4_1 e_1_2_10_18_1 e_1_2_10_16_1 e_1_2_10_39_1 e_1_2_10_8_1 e_1_2_10_14_1 e_1_2_10_37_1 e_1_2_10_13_1 e_1_2_10_11_1 e_1_2_10_30_1 e_1_2_10_51_1 Tarvainen A. (e_1_2_10_34_1) 2017 e_1_2_10_29_1 e_1_2_10_27_1 e_1_2_10_25_1 e_1_2_10_48_1 e_1_2_10_24_1 e_1_2_10_45_1 Zhou Z. (e_1_2_10_6_1) 2018 e_1_2_10_22_1 e_1_2_10_43_1 e_1_2_10_20_1 e_1_2_10_41_1 Li X. (e_1_2_10_33_1) 2020; 32 Zheng H. (e_1_2_10_17_1) 2020 Zhang Y. (e_1_2_10_32_1) 2017; 3 e_1_2_10_3_1 e_1_2_10_19_1 e_1_2_10_5_1 e_1_2_10_38_1 e_1_2_10_7_1 e_1_2_10_15_1 e_1_2_10_36_1 e_1_2_10_12_1 e_1_2_10_35_1 e_1_2_10_9_1 e_1_2_10_10_1 e_1_2_10_31_1 e_1_2_10_50_1 e_1_2_10_28_1 e_1_2_10_49_1 e_1_2_10_26_1 e_1_2_10_47_1 |
| References_xml | – year: 2017 article-title: Semi‐supervised learning for network‐based cardiac MR image segmentation – year: 2022 article-title: Efficient combination of CNN and transformer for dual‐teacher uncertainty‐aware guided semi‐supervised medical image segmentation publication-title: SSRN J. – start-page: 2613 year: 2021b end-page: 2622 article-title: Semi‐supervised semantic segmentation with cross pseudo supervision – year: 2023 article-title: Pseudo‐label guided contrastive learning for semi‐supervised medical image segmentation – volume: 12 start-page: 1079 year: 2018 end-page: 1085 article-title: Image segmentation fusion using weakly supervised trace‐norm multi‐task learning method publication-title: IET Image Proc. – volume: 129 start-page: 1106 year: 2021 end-page: 1120 article-title: Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation publication-title: Int. J. Comput. Vision – start-page: 1 year: 2022 end-page: 5 article-title: Cross‐level contrastive learning and consistency constraint for semi‐supervised medical image segmentation – volume: 3 start-page: 408 year: 2017 end-page: 416 article-title: Deep adversarial networks for biomedical image segmentation utilizing unannotated images publication-title: MICCAI – volume: 87 year: 2023 article-title: Local contrastive loss with pseudo‐label based self‐training for semi‐supervised medical image segmentation publication-title: Med. Image Anal. – year: 2020 article-title: Unet 3+: A full‐scale connected unet for medical image segmentation – year: 2021 – start-page: 1195 year: 2017 end-page: 1204 – volume: 239 year: 2022 article-title: Semi‐supervised NPC segmentation with uncertainty and attention guided consistency publication-title: Knowl. Based Syst. – volume: 18 start-page: 203 issue: 2 year: 2021 end-page: 211 article-title: nnU‐Net: A self‐configuring method fordeep learning‐based biomedical image segmentation publication-title: Nat. Methods – year: 2019 article-title: ADVENT: Adversarial entropy minimization for domain adaptation in semantic segmentation – start-page: 3 year: 2018 end-page: 11 – volume: 32 year: 2022 article-title: Uncertainty‐guided voxel‐level supervised contrastive learning for semi‐supervised medical image segmentation publication-title: Int. J. Neur. Syst. – year: 2018 – volume: 32(2) start-page: 523 year: 2020 end-page: 534 article-title: Transformation‐consistent self‐ensembling model for semisupervised medical image segmentation publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 20 start-page: 2457 issue: 4 year: 2022 end-page: 2467 article-title: Semi‐supervised 3D Medical image segmentation based on dual‐task consistent joint learning and task‐level regularization publication-title: IEEE/ACM Trans. Comput. Biol. Bioinf. – volume: 99 year: 2022 article-title: A contrastive consistency semi‐supervised left atrium segmentation model publication-title: Comput. Med. Imaging Graph – volume: 121 start-page: 74 year: 2020 end-page: 87 article-title: MultiResUNet : Rethinking the U‐Net architecture for multimodal biomedical image segmentation publication-title: Neural Netw. – volume: 12436 year: 2020 – start-page: 1597 year: 2020 end-page: 1607 article-title: A simple framework for contrastive learning of visual representations – volume: 9351 start-page: 234 year: 2015 end-page: 241 article-title: U‐net: Convolutional networks for biomedical image segmentation – volume: 80 year: 2022 article-title: Semi‐supervised medical image segmentation via uncertainty rectified pyramid consistency publication-title: Med. Image Anal. – volume: 12261 year: 2020 – start-page: 327 year: 2018 end-page: 331 article-title: Weighted res‐unet for high‐quality retina vessel segmentation – volume: 37 start-page: 2514 issue: 11 year: 2018 end-page: 2525 article-title: Deep learning techniques for automatic MRI cardiac multi‐structures segmentation and diagnosis: Is the problem solved? publication-title: IEEE Trans. Med. Imag. – volume: 79 year: 2022 article-title: Semi‐supervised medical image segmentation via a tripled‐uncertainty guided mean teacher model with contrastive learning publication-title: Med. Image Anal. – volume: 36 issue: 3 year: 2022 article-title: Separated contrastive learning for organ‐at‐risk and gross‐tumor‐volume segmentation with limited annotation – year: 2016 article-title: V‐Net: Fully convolutional neural networks for volumetric medical image segmentation – year: 2022 – year: 2020 – volume: 16(140) year: 2022 article-title: FFUNet: A novel feature fusion makes strong decoder for medical image segmentation publication-title: IET Signal Process – start-page: 4700 year: 2017 end-page: 4708 – volume: 31 year: 2017 – volume: 34 start-page: 1993 issue: 10 year: 2015 end-page: 2024 article-title: The multimodal brain tumor image segmentation benchmark (BRATS) publication-title: IEEE Trans. Med. Imag – volume: 29 start-page: 8055 year: 2020 end-page: 8068 article-title: Unsupervised learning of image segmentation based on differentiable feature clustering publication-title: IEEE Trans. Image Process. – volume: 16 start-page: 1243 year: 2022 end-page: 1267 article-title: Medical image segmentation using deep learning: A survey publication-title: IET Image Process – ident: e_1_2_10_44_1 – ident: e_1_2_10_42_1 doi: 10.1109/TMI.2018.2837502 – ident: e_1_2_10_37_1 doi: 10.1016/j.media.2022.102447 – ident: e_1_2_10_2_1 doi: 10.1007/978-3-319-24574-4_28 – ident: e_1_2_10_30_1 doi: 10.1109/ICCV48922.2021.00042 – ident: e_1_2_10_28_1 – volume: 3 start-page: 408 year: 2017 ident: e_1_2_10_32_1 article-title: Deep adversarial networks for biomedical image segmentation utilizing unannotated images publication-title: MICCAI – ident: e_1_2_10_36_1 – ident: e_1_2_10_22_1 doi: 10.1016/j.media.2022.102517 – ident: e_1_2_10_35_1 – ident: e_1_2_10_13_1 doi: 10.1109/TIP.2020.3011269 – ident: e_1_2_10_11_1 doi: 10.1049/ipr2.12419 – ident: e_1_2_10_9_1 doi: 10.1109/TCBB.2022.3144428 – ident: e_1_2_10_43_1 doi: 10.1101/2020.04.22.20074948 – ident: e_1_2_10_27_1 – ident: e_1_2_10_4_1 doi: 10.1109/ITME.2018.00080 – ident: e_1_2_10_19_1 – ident: e_1_2_10_20_1 doi: 10.1609/aaai.v36i3.20146 – ident: e_1_2_10_26_1 – ident: e_1_2_10_21_1 doi: 10.1016/j.media.2023.102792 – ident: e_1_2_10_29_1 – start-page: 1195 volume-title: Advances in Neural Information Processing Systems (NeurIPS) year: 2017 ident: e_1_2_10_34_1 – ident: e_1_2_10_3_1 doi: 10.1038/s41592-020-01008-z – ident: e_1_2_10_31_1 doi: 10.1007/978-3-319-66185-8_29 – volume: 32 start-page: 523 year: 2020 ident: e_1_2_10_33_1 article-title: Transformation‐consistent self‐ensembling model for semisupervised medical image segmentation publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2020.2995319 – ident: e_1_2_10_14_1 doi: 10.2139/ssrn.4081789 – ident: e_1_2_10_49_1 doi: 10.1109/CVPR52729.2023.01895 – ident: e_1_2_10_45_1 doi: 10.1109/TMI.2014.2377694 – ident: e_1_2_10_12_1 doi: 10.1049/iet‐ipr.2017.1061 – ident: e_1_2_10_48_1 – ident: e_1_2_10_40_1 doi: 10.1109/CVPR52688.2022.00421 – ident: e_1_2_10_23_1 doi: 10.1109/3DV.2016.79 – start-page: 3 volume-title: Unet++: A nestedu‐net architecture for medical image segmentation year: 2018 ident: e_1_2_10_6_1 – ident: e_1_2_10_18_1 doi: 10.1016/j.knosys.2021.108021 – ident: e_1_2_10_16_1 doi: 10.1007/978-3-030-59861-7_4 – ident: e_1_2_10_47_1 doi: 10.1109/CVPR46437.2021.00264 – ident: e_1_2_10_10_1 doi: 10.1609/aaai.v35i10.17066 – ident: e_1_2_10_41_1 doi: 10.1007/s11263-020-01395-y – ident: e_1_2_10_8_1 doi: 10.1049/sil2.12114 – ident: e_1_2_10_5_1 doi: 10.1016/j.neunet.2019.08.025 – ident: e_1_2_10_38_1 doi: 10.1016/j.compmedimag.2022.102092 – volume-title: Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 year: 2020 ident: e_1_2_10_17_1 – ident: e_1_2_10_50_1 doi: 10.1109/ISBI52829.2022.9761710 – ident: e_1_2_10_46_1 doi: 10.1109/CVPR.2019.00262 – ident: e_1_2_10_25_1 doi: 10.1109/CVPR.2017.243 – ident: e_1_2_10_15_1 doi: 10.1142/S0129065722500162 – ident: e_1_2_10_24_1 doi: 10.1609/aaai.v31i1.11231 – ident: e_1_2_10_7_1 doi: 10.1109/ICASSP40776.2020.9053405 – ident: e_1_2_10_51_1 doi: 10.7557/18.6798 – ident: e_1_2_10_39_1 doi: 10.1016/j.compbiomed.2022.106051 |
| SSID | ssj0059085 |
| Score | 2.3119612 |
| Snippet | Accurately segmenting medical images is a critical step in clinical diagnosis and developing patient‐specific treatment plans. While supervised learning... Abstract Accurately segmenting medical images is a critical step in clinical diagnosis and developing patient‐specific treatment plans. While supervised... |
| SourceID | doaj crossref wiley |
| SourceType | Open Website Enrichment Source Index Database Publisher |
| StartPage | 312 |
| SubjectTerms | contrastive learning Covid‐19 entropy‐guided medical image segmentation semi‐supervised learning |
| SummonAdditionalLinks | – databaseName: Wiley Online Library Open Access dbid: 24P link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEA6iHrz4FtcXBb0orG7StE3Ai4qil2URFW8lz6XgrsvWFbz5E_yN_hJn0u7KggjirSRTGmYyr2YyHyEHxlvDqceycqWanBrT1C5zkKoYKWTiwENUYBNZuy0eH2VnhpyO78JU_SEmP9xQM4K9RgVXukIhgaAWhFgMhuwYvBUm7HOUxgKBGxjvjO0wgnkn4TokAsmniRw3J-Xy5PvdKXcUuvZPR6nBzVwt_W-By2SxDi-js2o_rJAZ118lS3WoGdWKXK6Rh0usUB-8fb5_dEeFhblQs65KtH5RDSXRjSCijUrXK4CsHA3QrJRA2qsOd6KiB8YI5ru9-gJTf53cX13eXVw3a4iFpuEcEkevQOu0pNxqDoEQj7XOUHopZK5KKZt5A4z0RraYw-ARsw0v8GoPi33MaLxBZvvPfbdJItHSDAaoEpnj1FKhjbE6wXMdq4SmDXI45nRu6v7jCIPxlIdzcC5zZFgeGNYg-xPaQdV140eqcxTYhAI7ZYeB52E3rxUvbyUig0WZzAvNnadaMCnS1KZWtizVukGOghB_-U5-07ll4WnrL8TbZIFBBFSVeO-Q2ZfhyO2SefP6UpTDvbBXvwAWV-36 priority: 102 providerName: Wiley-Blackwell |
| Title | Entropy‐guided contrastive learning for semi‐supervised medical image segmentation |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fipr2.12950 https://doaj.org/article/058731ac7f8b4ef1b829866d6d90d1bb |
| Volume | 18 |
| WOSCitedRecordID | wos001075788700001&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: View article at DOAJ customDbUrl: eissn: 1751-9667 dateEnd: 20241231 omitProxy: false ssIdentifier: ssj0059085 issn: 1751-9659 databaseCode: DOA dateStart: 20210101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVWIB databaseName: Wiley Online Library Free Content customDbUrl: eissn: 1751-9667 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0059085 issn: 1751-9659 databaseCode: WIN dateStart: 20130101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Open Access customDbUrl: eissn: 1751-9667 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0059085 issn: 1751-9659 databaseCode: 24P dateStart: 20130101 isFulltext: true titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8NAEF5UPHjxLdZHCehFodrdbJLdo4piL6WIr1vYZwnYWhorePMn-Bv9Jc5sUlEQvXgJYXdgw0x25hvmRci-8dZw6jGtXKkWp8a0tMscuCpGCpk4sBDVsIms2xX397L3ZdQX5oRV7YErxh23E5HFVJnMC82dp1owKdLUpla2LdUatS-gnqkzVelgHOSdhFJIHCKfJnLamJTL42I0Zkdg5bDS_ospCh37vyPUYGIulslijQ2jk-qbVsiMG66SpRonRvUtLNfI7Tmml49e3l_f-pPCwl5IOFclqq6ongPRjwCORqUbFEBWTkaoE0ogHVSRmagYgCaB_f6grj4arpObi_Prs8tWPR-hZTgHr88ruDJaUm41BxTDY60zZH0KbqdSymbeACe8kW3mEPmhq-AF1uWw2MeMxhtkbvg4dJskEm3NYIEqkTlOLRXaGKsTDMpYJTRtkIMpq3JTNw_HGRYPeQhic5kjW_PA1gbZ-6QdVS0zfqQ6RY5_UmCb67AAws9r4ed_Cb9BDoO8fjkn7_SuWHjb-o8Tt8kCA1hT5W3vkLmn8cTtknnz_FSU4yaZZbzXDL8iPO863Q-y3eO4 |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1La9tAEF6CE2gvebWlTppE0FxScKuVV9LuMQk2MUmNCWmbm9inEdQPLDuQW35CfmN-SWdWa4dAKZTcxO4IidmdmW9250HIsXZGM-owrFzKFqNat5TNLbgqWnCRWrAQdbOJvN_nt7diEGJzMBemrg-xOnBDyfD6GgUcD6Rrh5NhkcxyOku-grlCj32dAdLAzg2_ev2lIsZu3qnPh8RO8lkqltVJmfj2_O4Le-TL9r-Eqd7OdLde-YfbZDMAzOi03hE7ZM2Od8lWAJtREOXqHfnZwRj16f3Tw-NwURqY81HrskL9F4VmEsMIMG1U2VEJZNViioqlAtJRfb0TlSNQRzA_HIUUpvF78qPbuTm_aIUmCy3NGLiOToLcKUGZUQygEGsrleP6ZeC7SilN7jRw0mkRJxbhI_objmNyT9J27YS2P5DGeDK2H0nEY5XAAJU8t4waypXWRqV4s2MkV7RJTpasLnSoQI6NMH4X_iaciQIZVniGNcnnFe20rrvxV6ozXLEVBdbK9gOT2bAIolfEKc_hp3TuuGLWUcUTwbPMZEbEhirVJF_8Kv7jO0VvcJ34p73_IT4iby5uvl8VV73-5T55mwAeqgO-P5HGfLawB2RD383LanboN-4f20ryUg |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSyQxEA6LLuJl3fWBs7q7DXpRGJ1k0t3JcR8OKyvDICremjyHBmdsph3Bmz9hf6O_xKp0ZkQQQbw1STUdKqlXp-orQnaNt4ZTj2nlSrU5NaatXe4gVDFSyNSBhWiaTeT9vri8lIOYm4O1MA0-xPyHG0pG0Nco4K6yvgk4OYJkltWEHYC5woh9kac5xUPN-GCmiLGbdxrqIbGTfJbKGTopl4dP7z6zRwG2_7mbGuxMb-WdK_xMPkUHM_nZnIgv5IMbr5KV6GwmUZTrNXJxhDnq1d3D_f_htLQwF7LWVY36L4nNJIYJ-LRJ7UYlkNXTChVLDaSj5nonKUegjmB-OIolTON1ct47Ovv9tx2bLLQN5xA6egVypyXlVnNwhXhX6xz3L4PYVSllc2-Ak97IDnPoPmK84QUW97Cu7zLa3SAL4-ux2ySJ6GgGA1SJ3HFqqdDGWJ3izY5VQtMW2ZuxujARgRwbYVwV4SacywIZVgSGtcjOnLZqcDdepPqFOzanQKzsMHA9GRZR9IpOKnJYlMm90Nx5qgWTIstsZmXHUq1bZD_s4ivfKY4Hpyw8fX0L8Q-yNPjTK06O-_-2yDIDd6jJ994mCzeTqftGPprbm7KefA_n9hECofFp |
| 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=Entropy%E2%80%90guided+contrastive+learning+for+semi%E2%80%90supervised+medical+image+segmentation&rft.jtitle=IET+image+processing&rft.au=Junsong+Xie&rft.au=Qian+Wu&rft.au=Renju+Zhu&rft.date=2024-02-01&rft.pub=Wiley&rft.issn=1751-9659&rft.eissn=1751-9667&rft.volume=18&rft.issue=2&rft.spage=312&rft.epage=326&rft_id=info:doi/10.1049%2Fipr2.12950&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_058731ac7f8b4ef1b829866d6d90d1bb |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-9659&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-9659&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-9659&client=summon |