{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:02:10Z","timestamp":1781712130474,"version":"3.54.5"},"reference-count":42,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T00:00:00Z","timestamp":1702857600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY22A010003"],"award-info":[{"award-number":["LY22A010003"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11801511"],"award-info":[{"award-number":["11801511"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Semi\u2010supervised learning has gained popularity in medical image segmentation due to its ability to reduce reliance on image annotation. A typical approach in semi\u2010supervised learning is to select reliable predictions as pseudo\u2010labels and eliminate unreliable predictions. Contrastive learning helps prevent the insufficient utilization of unreliable predictions, but neglecting the anatomical structure of medical images can lead to suboptimal optimization results.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>We propose a novel approach for semi\u2010supervised liver segmentation using contrastive learning, which leverages unlabeled data and enhances the suitability of contrastive learning for liver segmentation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method and materials<\/jats:title><jats:p>Contrastive learning helps prevent the inappropriate utilization of unreliable predictions, but neglecting the anatomical structure of medical images can lead to suboptimal optimization results. Therefore, we propose a semi\u2010supervised contrastive learning method with local regions self\u2010supervision (LRS<jats:sup>2<\/jats:sup>). On one side, we employ Shannon entropy to distinguish between reliable and unreliable predictions and reduce the dissimilarity between their representations within regional artificial units. Within each unit of the liver image, we strongly encourage unreliable predictions to acquire valuable information pertaining to the correct category by leveraging the representations of reliable predictions in their vicinity. On the other side, we introduce a dynamic reliability threshold based on the Shannon entropy of each prediction, gradually evaluating the confidence threshold of reliable predictions as predictive accuracy improves. After selecting reliable predictions, we sequentially apply erosion and dilation to refine them for better selection of qualified positive and negative samples. We evaluate our proposed method on abdominal CT images, including 131 images (train data: 77, validation data: 26, and testing data: 28) from 2017 ISBI Liver Tumors Segmentation Challenge.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our method obtains satisfactory performance in different proportion by exploiting the unreliable predictions. Compared with the result of VNet only under supervised settings (with 10, 30, 50, 70% and full labeled data), LRS<jats:sup>2<\/jats:sup>, respectively, brings an improvement of Dice coefficient by +6.11, +3.55, +4.43, and +2.25%, achieving Dice coefficients of 93.44, 93.31, 94.85, and 95.12%,\u00a0respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>In this study, we carefully select appropriate positive and negative samples from reliable regions, ensuring that anchor pixels within unreliable regions are correctly assigned to their respective categories. With a consideration of the anatomical structure present in CT images, we partition the image representations into regional units, enabling anchor pixels to capture more precise sample information. Extensive experiments confirm the effectiveness of our\u00a0method.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16886","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T09:55:21Z","timestamp":1702893321000},"page":"3455-3463","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Semi\u2010supervised liver segmentation based on local regions self\u2010supervision"],"prefix":"10.1002","volume":"51","author":[{"given":"Qiong","family":"Lou","sequence":"first","affiliation":[{"name":"School of Science Zhejiang University of Science and Technology Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingyi","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Science Zhejiang University of Science and Technology Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaguan","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Science Zhejiang University of Science and Technology Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Science Zhejiang University of Science and Technology Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,12,18]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek\u00d6 AbdulkadirA LienkampSS BroxT RonnebergerO.3D U\u2010Net: learning dense volumetric segmentation from sparse annotation. In:Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI. Lecture Notes in Computer Science. Vol9901.2016:424\u2010432.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"e_1_2_7_3_1","doi-asserted-by":"crossref","unstructured":"deOliveira JuniorLA MedeirosHR MacedoD ZanchettinC OliveiraALI LudermirTB.SegNetRes\u2010CRF: a deep convolutional encoder\u2010decoder architecture for semantic image segmentation. In:2018 International Joint Conference on Neural Networks IJCNN 2018.IEEE;2018:1\u20106.","DOI":"10.1109\/IJCNN.2018.8489376"},{"key":"e_1_2_7_4_1","first-page":"203","volume-title":"nnU\u2010Net: A Self\u2010configuring Method for Deep Learning\u2010based Biomedical Image Segmentation","author":"Isensee F","year":"2021"},{"key":"e_1_2_7_5_1","doi-asserted-by":"crossref","unstructured":"YuL WangS LiX FuC HengP.Uncertainty\u2010aware self\u2010ensembling model for semi\u2010supervised 3D left atrium segmentation. In:Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI. Lecture Notes in Computer Science. Vol11765.Springer;2019:605\u2010613.","DOI":"10.1007\/978-3-030-32245-8_67"},{"key":"e_1_2_7_6_1","unstructured":"LaineS AilaT.Temporal ensembling for semi\u2010supervised learning. In:5th International Conference on Learning Representations ICLR 2017.OpenReview.net;2017."},{"key":"e_1_2_7_7_1","unstructured":"SajjadiM JavanmardiM TasdizenT.Regularization with stochastic transformations and perturbations for deep semi\u2010supervised learning. In:Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016.2016:1163\u20101171."},{"key":"e_1_2_7_8_1","unstructured":"GrandvaletY BengioY.Semi\u2010supervised learning by entropy minimization. In:Proceedings of the 17th International Conference on Neural Information Processing Systems.NIPS'04.MIT Press;2004:529\u2010536."},{"key":"e_1_2_7_9_1","doi-asserted-by":"crossref","unstructured":"LiS ZhangC HeX.Shape\u2010aware semi\u2010supervised 3D semantic segmentation for medical images. In:Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI. Lecture Notes in Computer Science. Vol12261.Springer;2020:552\u2010561.","DOI":"10.1007\/978-3-030-59710-8_54"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107269"},{"key":"e_1_2_7_11_1","doi-asserted-by":"crossref","unstructured":"BaiW OktayO SinclairM et\u00a0al.Semi\u2010supervised learning for network\u2010based cardiac MR image segmentation. In:Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI. Lecture Notes in Computer Science. Vol10434.Springer;2017:253\u2010260.","DOI":"10.1007\/978-3-319-66185-8_29"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2772836"},{"key":"e_1_2_7_13_1","unstructured":"XuY ShangL YeJ et\u00a0al.Dash: semi\u2010supervised learning with dynamic thresholding. In:Proceedings of the 38th International Conference on Machine Learning ICML 2021. Proceedings of Machine Learning Research. PMLR. Vol139.2021:11525\u201011536."},{"key":"e_1_2_7_14_1","doi-asserted-by":"crossref","unstructured":"YangL ZhuoW QiL ShiY GaoY.ST++: make self\u2010training work better for semi\u2010supervised semantic segmentation. In:IEEE\/CVF Conference on Computer Vision and Pattern Recognition CVPR 2022.IEEE;2022:4258\u20104267.","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"e_1_2_7_15_1","doi-asserted-by":"crossref","unstructured":"ChenC LiuQ JinY DouQ HengP.Source\u2010free domain adaptive fundus image segmentation with denoised pseudo\u2010labeling. In:Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI. Lecture Notes in Computer Science. Vol12905.Springer;2021:225\u2010235.","DOI":"10.1007\/978-3-030-87240-3_22"},{"key":"e_1_2_7_16_1","doi-asserted-by":"crossref","unstructured":"GaoJ XuJ FeiH.A pseudo\u2010labeling approach to semi\u2010supervised organ segmentation. In:Fast and Low\u2010Resource Semi\u2010supervised Abdominal Organ Segmentation \u2010 MICCAI 2022 Challenge. Lecture Notes in Computer Science. Vol13816.Springer;2022:318\u2010326.","DOI":"10.1007\/978-3-031-23911-3_28"},{"key":"e_1_2_7_17_1","unstructured":"SohnK BerthelotD CarliniN et\u00a0al.FixMatch: simplifying semi\u2010supervised learning with consistency and confidence. In:Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020.2020."},{"key":"e_1_2_7_18_1","doi-asserted-by":"crossref","unstructured":"ArazoE OrtegoD AlbertP O'ConnorNE McGuinnessK.Pseudo\u2010labeling and confirmation bias in deep semi\u2010supervised learning. In:2020 International Joint Conference on Neural Networks IJCNN 2020.IEEE;2020:1\u20108.","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"e_1_2_7_19_1","unstructured":"HjelmRD FedorovA Lavoie\u2010MarchildonS et\u00a0al.Learning deep representations by mutual information estimation and maximization. In:7th International Conference on Learning Representations ICLR 2019.OpenReview.net;2019."},{"key":"e_1_2_7_20_1","doi-asserted-by":"crossref","unstructured":"MisraI van derMaatenL.Self\u2010supervised learning of pretext\u2010invariant representations. In:2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition CVPR 2020.Computer Vision Foundation\/IEEE;2020:6706\u20106716.","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"e_1_2_7_21_1","doi-asserted-by":"crossref","unstructured":"WuZ XiongY YuSX LinD.Unsupervised feature learning via non\u2010parametric instance discrimination. In:2018 IEEE Conference on Computer Vision and Pattern Recognition CVPR 2018.Computer Vision Foundation\/IEEE Computer Society;2018:3733\u20103742.","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_2_7_22_1","doi-asserted-by":"crossref","unstructured":"ChenX XieS HeK.An empirical study of training self\u2010supervised vision transformers. In:2021 IEEE\/CVF International Conference on Computer Vision ICCV 2021.IEEE;2021:9620\u20109629.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"e_1_2_7_23_1","doi-asserted-by":"crossref","unstructured":"HeK FanH WuY XieS GirshickRB.Momentum contrast for unsupervised visual representation learning. In:2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition CVPR 2020.Computer Vision Foundation\/IEEE;2020:9726\u20109735.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_2_7_24_1","unstructured":"LiuS ZhiS JohnsE DavisonAJ.Bootstrapping semantic segmentation with regional contrast. In:The Tenth International Conference on Learning Representations ICLR 2022.OpenReview.net;2022."},{"key":"e_1_2_7_25_1","doi-asserted-by":"crossref","unstructured":"WangY WangH ShenY et\u00a0al.Semi\u2010supervised semantic segmentation using unreliable pseudo\u2010labels. In:IEEE\/CVF Conference on Computer Vision and Pattern Recognition CVPR 2022.IEEE;2022:4238\u20104247.","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102134"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065722500162"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102680"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3153406"},{"key":"e_1_2_7_30_1","unstructured":"HussainZ GimenezF YiD RubinDL.Differential data augmentation techniques for medical imaging classification tasks. In:AMIA 2017 American Medical Informatics Association Annual Symposium Washington DC USA November 4\u20108 2017.AMIA;2017."},{"key":"e_1_2_7_31_1","doi-asserted-by":"crossref","unstructured":"BissotoA ValleE AvilaS.GAN\u2010based data augmentation and anonymization for skin\u2010lesion analysis: a critical review. In:IEEE Conference on Computer Vision and Pattern Recognition Workshops CVPR Workshops 2021.Computer Vision Foundation\/IEEE;2021:1847\u20101856.","DOI":"10.1109\/CVPRW53098.2021.00204"},{"key":"e_1_2_7_32_1","doi-asserted-by":"crossref","unstructured":"ZhaoA BalakrishnanG DurandF GuttagJV DalcaAV.Data augmentation using learned transformations for one\u2010shot medical image segmentation. In:IEEE Conference on Computer Vision and Pattern Recognition CVPR 2019.Computer Vision Foundation\/IEEE;2019:8543\u20108553.","DOI":"10.1109\/CVPR.2019.00874"},{"key":"e_1_2_7_33_1","unstructured":"TarvainenA ValpolaH.Mean teachers are better role models: weight\u2010averaged consistency targets improve semi\u2010supervised deep learning results. In:5th International Conference on Learning Representations ICLR 2017.OpenReview.net;2017."},{"key":"e_1_2_7_34_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiS.V\u2010Net: Fully convolutional neural networks for volumetric medical image segmentation. In:Fourth International Conference on 3D Vision 3DV 2016.IEEE Computer Society;2016:565\u2010571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_7_35_1","unstructured":"van denOordA LiY VinyalsO.Representation learning with contrastive predictive coding.2018. doi:10.48550\/arXiv.1807.03748"},{"key":"e_1_2_7_36_1","doi-asserted-by":"crossref","unstructured":"WangF LiuH.Understanding the behaviour of contrastive loss. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2021:2495\u20102504.","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"e_1_2_7_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40012-016-0092-1"},{"key":"e_1_2_7_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101832"},{"key":"e_1_2_7_39_1","doi-asserted-by":"crossref","unstructured":"ChenS BortsovaG Ju\u00e1rezAG vanTulderG deBruijneM.Multi\u2010task attention\u2010based semi\u2010supervised learning for medical image segmentation. In:Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI.Lecture Notes in Computer Science. Vol11766.Springer;2019:457\u2010465.","DOI":"10.1007\/978-3-030-32248-9_51"},{"key":"e_1_2_7_40_1","unstructured":"HungW TsaiY LiouY LinY YangM.Adversariallearning for semi\u2010supervised semantic segmentation. In:British Machine Vision Conference 2018 BMVC 2018.BMVA Press;2018:65."},{"key":"e_1_2_7_41_1","doi-asserted-by":"crossref","unstructured":"NieD GaoY WangL ShenD.ASDNet: attention based semi\u2010supervised deep networks for medical image segmentation. In:Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI.Lecture Notes in Computer Science. Vol11073.Springer;2018:370\u2010378.","DOI":"10.1007\/978-3-030-00937-3_43"},{"key":"e_1_2_7_42_1","doi-asserted-by":"crossref","unstructured":"OualiY HudelotC TamiM.Semi\u2010supervised semantic segmentation with cross\u2010consistency training. In:2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition CVPR 2020.Computer Vision Foundation\/IEEE;2020:12671\u201012681.","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"e_1_2_7_43_1","doi-asserted-by":"crossref","unstructured":"ZhengH LinL HuH et\u00a0al.Semi\u2010supervised segmentation of liver using adversarial learning with deep Atlas prior. In:Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI.Lecture Notes in Computer Science. Vol11769.Springer;2019:148\u2010156.","DOI":"10.1007\/978-3-030-32226-7_17"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:24:47Z","timestamp":1755876287000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,18]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["10.1002\/mp.16886"],"URL":"https:\/\/doi.org\/10.1002\/mp.16886","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,18]]},"assertion":[{"value":"2023-07-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}