{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T05:05:42Z","timestamp":1780031142908,"version":"3.53.1"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206195, 62163004, 61966001, 62276180"],"award-info":[{"award-number":["62206195, 62163004, 61966001, 62276180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:p>Semi-supervised learning (SSL) has garnered considerable attention in medical image segmentation due to its ability to leverage abundant unlabeled data, thereby significantly alleviating the dependency on expensive pixel-wise annotations. However, existing Mean-Teacher-based frameworks typically guide the student network using a teacher model in a unidirectional or loosely interactive manner, which fails to fully exploit the complementary relationships between different networks and often struggles with low-confidence predictions that degrade boundary accuracy. To address these limitations, we propose SDBS-Net, a novel semi-supervised dual-student self-distillation network for 3D medical image segmentation. The architecture comprises a shared encoder and two parallel decoders, forming two networks (Model I and Model II) that process both labeled and unlabeled volumes simultaneously. To enable effective bidirectional knowledge transfer, we introduce two synergistic training schemas: a prior knowledge learning (PKL) schema with hierarchical difference (HD) modules and a Self-Distillation Learning (SDL) schema. The PKL schema extracts and inject multi-scale discrepancy features from Model I into Model II, enhancing discriminative representation and boundary delineation, while the SDL schema employs multi-level soft-label and feature distillation losses to correct confirmation bias and refine overlooked regions in a mutually reinforcing manner. Extensive experiments on two challenging benchmarks such as the Left Atrium (LA) dataset and the Pancreas-CT dataset demonstrate the superiority of SDBS-Net. With only 10% and 20% labeled data, our method achieves Dice scores of 88.19% and 90.51% on the LA dataset, and 71.39% and 79.37% on the Pancreas-CT dataset, respectively, consistently outperforming state-of-the-art semi-supervised approaches while approaching fully supervised performance.<\/jats:p>","DOI":"10.3389\/fphys.2026.1755067","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T04:55:31Z","timestamp":1780030531000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-distillation double student network for semi-supervised medical image segmentation"],"prefix":"10.3389","volume":"17","author":[{"given":"Huaxiang","family":"Liu","sequence":"first","affiliation":[{"name":"Taizhou University Affiliated Taizhou Central Hospital, Taizhou University","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Taizhou University Affiliated Taizhou Central Hospital, Taizhou University","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Jin","sequence":"additional","affiliation":[{"name":"Taizhou University Affiliated Taizhou Central Hospital, Taizhou University","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Taizhou University Affiliated Taizhou Central Hospital, Taizhou University","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youyao","family":"Fu","sequence":"additional","affiliation":[{"name":"Artificial Intelligence School, Taizhou University","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangxiong","family":"Fang","sequence":"additional","affiliation":[{"name":"Taizhou University Affiliated Taizhou Central Hospital, Taizhou University","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Taizhou University Affiliated Taizhou Central Hospital, Taizhou University","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"B1","volume-title":"MixMatch: a holistic approach to semi-supervised learning (arXiv preprint arXiv:1905.02249)","author":"Berthelot","year":"2019"},{"key":"B2","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/978-3-031-25066-8_9","article-title":"Swin-Unet: unet-like pure transformer for medical image segmentation","volume-title":"Computer vision \u2013 ECCV 2022 workshops","author":"Cao","year":"2023"},{"key":"B3","doi-asserted-by":"publisher","first-page":"6912","DOI":"10.1609\/aaai.v35i8.16852","article-title":"Curriculum labeling: revisiting pseudo-labeling for semi-supervised learning","volume":"35","author":"Cascante-Bonilla","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"B4","volume-title":"TransUNet: transformers make strong encoders for medical image segmentation (arXiv preprint arXiv:2102.04306)","author":"Chen","year":"2021"},{"key":"B5","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1109\/TMI.2022.3213372","article-title":"Semi-supervised unpaired medical image segmentation through task-affinity consistency","volume":"42","author":"Chen","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1123410","article-title":"BAF-Net: bidirectional attention fusion network via CNN and transformers for the pepper leaf segmentation","volume":"14","author":"Fang","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1515105","article-title":"AMS-MLP: adaptive multi-scale MLP network with multi-scale context relation decoder for pepper leaf segmentation","volume":"16","author":"Fang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2026.109985","article-title":"Semi-supervised dual-teacher comparative learning with bidirectional balanced copy-paste for medical image segmentation","volume":"119","author":"Fang","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s44443-026-00662-1","article-title":"Spatial-spectral Fourier convolution fusion network with Taylor expansion attention-based transformer for jaw cyst segmentation","author":"Fang","year":"2026","journal-title":"J. King Saud Univ. Comput. Inf. Sci"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3397","DOI":"10.1109\/TMI.2025.3563500","article-title":"Optimal transport and central moment consistency regularization for semi-supervised medical image segmentation","volume":"44","author":"Guo","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B11","first-page":"1748","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1109\/TMI.2023.3347689","article-title":"Bilateral supervision network for semi-supervised medical image segmentation","volume":"43","author":"He","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B13","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1109\/TMI.2022.3225687","article-title":"Semi-supervised medical image segmentation using adversarial consistency learning and dynamic convolution network","volume":"42","author":"Lei","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B15","doi-asserted-by":"publisher","first-page":"4140","DOI":"10.1109\/JBHI.2021.3103646","article-title":"Self-ensembling co-training framework for semi-supervised COVID-19 CT segmentation","volume":"25","author":"Li","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"B16","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1007\/978-3-030-59710-8_54","article-title":"Shape-aware semi-supervised 3D semantic segmentation for medical images","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2020","author":"Li","year":"2020"},{"key":"B17","doi-asserted-by":"publisher","first-page":"3929","DOI":"10.1049\/ipr2.12604","article-title":"Active contour driven by adaptive\u2010scale local\u2010energy signed pressure force function based on bias correction for medical image segmentation","volume":"16","author":"Liu","year":"2022","journal-title":"IET Image Process."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106352","article-title":"GCHA-Net: global context and hybrid attention network for automatic liver segmentation","volume":"152","author":"Liu","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"104153","DOI":"10.1016\/j.inffus.2026.104153","article-title":"Lifting wavelet transform-guided network with histogram attention for liver segmentation in CT scans","volume":"131","author":"Liu","year":"2026","journal-title":"Inf. Fusion"},{"key":"B20","doi-asserted-by":"publisher","first-page":"045222","DOI":"10.1088\/2631-8695\/ae1103","article-title":"SquareNet: multi-scale progressive difference and scale-cross attention network for volumetric medical image segmentation","volume":"7","author":"Liu","year":"2025","journal-title":"Eng. Res. Express"},{"key":"B21","volume-title":"Semi-supervised medical image segmentation through dual-task consistency (arXiv preprint arXiv:2009.04448)","author":"Luo","year":"2023"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102517","article-title":"Semi-supervised medical image segmentation via uncertainty rectified pyramid consistency","volume":"80","author":"Luo","year":"2022","journal-title":"Med. Image Anal."},{"key":"B23","first-page":"565","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"B24","volume-title":"Attention U-Net: learning where to look for the pancreas (arXiv preprint arXiv:1804.03999)","author":"Oktay","year":"2018"},{"key":"B25","doi-asserted-by":"publisher","first-page":"3054","DOI":"10.1109\/TCSVT.2024.3508768","article-title":"Pseudo labeling methods for semi-supervised semantic segmentation: a review and future perspectives","volume":"35","author":"Ran","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"B26","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B27","volume-title":"Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results (arXiv preprint arXiv:1703.01780)","author":"Tarvainen","year":"2018"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.3233\/JIFS-18594","article-title":"Speech emotion recognition using a fuzzy approach","volume":"36","author":"Ton-That","year":"2019","journal-title":"J. Intell. Fuzzy Syst."},{"key":"B29","volume-title":"Attention is all you need (arXiv preprint arXiv:1706.03762)","author":"Vaswani","year":"2017"},{"key":"B30","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1007\/978-3-030-87196-3_41","article-title":"Neighbor matching for semi-supervised learning","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2021","author":"Wang","year":"2021"},{"key":"B31","first-page":"15651","article-title":"MCF: mutual correction framework for semi-supervised medical image segmentation","author":"Wang","year":"2023"},{"key":"B32","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1007\/978-3-031-16443-9_4","article-title":"Exploring smoothness and class-separation for semi-supervised medical image segmentation","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2022","author":"Wu","year":"2022"},{"key":"B33","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/978-3-030-87196-3_28","article-title":"Semi-supervised left atrium segmentation with mutual consistency training","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2021","author":"Wu","year":"2021"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2228","DOI":"10.1109\/TMI.2022.3161829","article-title":"SimCVD: simple contrastive voxel-wise representation distillation for semi-supervised medical image segmentation","volume":"41","author":"You","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B35","volume-title":"Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation (arXiv preprint arXiv:1907.07034)","author":"Yu","year":"2019"},{"key":"B36","doi-asserted-by":"publisher","first-page":"3296","DOI":"10.1007\/s11263-024-02328-9","article-title":"PICK: predict and mask for semi-supervised medical image segmentation","volume":"133","author":"Zeng","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"B37","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1109\/TMI.2025.3601359","article-title":"Harnessing text insights with visual alignment for medical image segmentation","volume":"45","author":"Zeng","year":"2026","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B38","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/978-3-032-04978-0_22","article-title":"Exploring text-enhanced mixture-of-experts for semi-supervised medical image segmentation with composite data","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2025","author":"Zeng","year":"2026"},{"key":"B39","doi-asserted-by":"publisher","first-page":"2948","DOI":"10.1109\/TMI.2025.3556310","article-title":"Segment together: a versatile paradigm for semi-supervised medical image segmentation","volume":"44","author":"Zeng","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B40","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/TMI.2024.3429340","article-title":"Consistency-guided differential decoding for enhancing semi-supervised medical image segmentation","volume":"44","author":"Zeng","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B41","first-page":"15671","article-title":"PEFAT: boosting semi-supervised medical image classification via pseudo-loss estimation and feature adversarial training","author":"Zeng","year":"2023"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","article-title":"UNet++: redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2020","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1755067\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T04:55:45Z","timestamp":1780030545000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1755067\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":42,"alternative-id":["10.3389\/fphys.2026.1755067"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1755067","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"article-number":"1755067"}}