{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:35:53Z","timestamp":1780497353682,"version":"3.54.1"},"reference-count":43,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T00:00:00Z","timestamp":1706227200000},"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":["LDT23F01015F01"],"award-info":[{"award-number":["LDT23F01015F01"]}],"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":["62201323"],"award-info":[{"award-number":["62201323"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20220266"],"award-info":[{"award-number":["BK20220266"]}],"id":[{"id":"10.13039\/501100004608","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":[[2024,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Segmentation of orbital tumors in CT images is of great significance for orbital tumor diagnosis, which is one of the most prevalent diseases of the eye. However, the large variety of tumor sizes and shapes makes the segmentation task very challenging, especially when the available annotation data is\u00a0limited.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To this end, in this paper, we propose a multi\u2010scale consistent self\u2010training network (MSCINet) for semi\u2010supervised orbital tumor segmentation. Specifically, we exploit the semantic\u2010invariance features by enforcing the consistency between the predictions of different scales of the same image to make the model more robust to size variation. Moreover, we incorporate a new self\u2010training strategy, which adopts iterative training with an uncertainty filtering mechanism to filter the pseudo\u2010labels generated by the model, to eliminate the accumulation of pseudo\u2010label error predictions and increase the generalization of the\u00a0model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>For evaluation, we have built two datasets, the orbital tumor binary segmentation dataset (Orbtum\u2010B) and the orbital multi\u2010organ segmentation dataset (Orbtum\u2010M). Experimental results on these two datasets show that our proposed method can both achieve state\u2010of\u2010the\u2010art performance. In our datasets, there are a total of 55 patients containing 602 2D\u00a0images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>In this paper, we develop a new semi\u2010supervised segmentation method for orbital tumors, which is designed for the characteristics of orbital tumors and exhibits excellent performance compared to previous semi\u2010supervised\u00a0algorithms.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16945","type":"journal-article","created":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T19:16:40Z","timestamp":1706296600000},"page":"4859-4871","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi\u2010scale consistent self\u2010training network for semi\u2010supervised orbital tumor segmentation"],"prefix":"10.1002","volume":"51","author":[{"given":"Keyi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Mechanical Electrical and Information Engineering at Shandong University Weihai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiming","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Automation Hangzhou Dianzi University Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xindi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Guan","sequence":"additional","affiliation":[{"name":"Department of Radiology, the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Radiology, the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Electrical and Information Engineering at Shandong University Weihai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Electrical and Information Engineering at Shandong University Weihai China"},{"name":"Suzhou Research Institute of Shandong University Suzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,1,26]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: Convolutional networks for biomedical image segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"e_1_2_11_4_1","doi-asserted-by":"crossref","unstructured":"JhaD RieglerMA JohansenD HalvorsenP JohansenHD.Doubleu\u2010net: a deep convolutional neural network for medical image segmentation. In:2020 IEEE 33rd International Symposium on Computer\u2010Based Medical Systems(CBMS).IEEE;2020:558\u2010564.","DOI":"10.1109\/CBMS49503.2020.00111"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_11_6_1","doi-asserted-by":"crossref","unstructured":"HuX ZengD XuX ShiY.Semi\u2010supervised contrastive learning for label\u2010efficient medical image segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:481\u2010490.","DOI":"10.1007\/978-3-030-87196-3_45"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2995319"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3117888"},{"key":"e_1_2_11_9_1","doi-asserted-by":"crossref","unstructured":"PapandreouG ChenL\u2010C MurphyKP YuilleAL.Weakly\u2010and semi\u2010supervised learning of a deep convolutional network for semantic image segmentation. In:Proceedings of the IEEE International Conference on Computer Vision.IEEE;2015:1742\u20101750.","DOI":"10.1109\/ICCV.2015.203"},{"key":"e_1_2_11_10_1","doi-asserted-by":"crossref","unstructured":"AhnJ ChoS KwakS.Weakly supervised learning of instance segmentation with inter\u2010pixel relations. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE;2019:2209\u20102218.","DOI":"10.1109\/CVPR.2019.00231"},{"key":"e_1_2_11_11_1","unstructured":"HeQ LiS HeX.Weakly supervised volumetric segmentation via self\u2010taught shape denoising model.Medical Imaging with Deep Learning.PMLR;2021:268\u2010285."},{"key":"e_1_2_11_12_1","doi-asserted-by":"crossref","unstructured":"LerousseauM VakalopoulouM ClasseM et\u00a0al.Weakly supervised multiple instance learning histopathological tumor segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2020:470\u2010479.","DOI":"10.1007\/978-3-030-59722-1_45"},{"key":"e_1_2_11_13_1","article-title":"Mean teachers are better role models: weight\u2010averaged consistency targets improve semi\u2010supervised deep learning results","volume":"30","author":"Tarvainen A","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_11_14_1","doi-asserted-by":"crossref","unstructured":"OualiY HudelotC TamiM.Semi\u2010supervised semantic segmentation with cross\u2010consistency training. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE;2020:12674\u201012684.","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"e_1_2_11_15_1","unstructured":"LeeD\u2010H.Pseudo\u2010label: the simple and efficient semi\u2010supervised learning method for deep neural networks. In:Workshop on challenges in representation learning. Vol.3. p.896.ICML;2013."},{"key":"e_1_2_11_16_1","doi-asserted-by":"crossref","unstructured":"ZhouB KhoslaA LapedrizaA OlivaA TorralbaA.Learning deep features for discriminative localization. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE;2016:2921\u20102929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_2_11_17_1","doi-asserted-by":"crossref","unstructured":"LongJ ShelhamerE DarrellT.Fully convolutional networks for semantic segmentation. In:Proceedings of the IEEE conference on computer vision and pattern recognition.IEEE;2015:3431\u20103440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","unstructured":"ZhuZ XuM BaiS HuangT BaiX.Asymmetric non\u2010local neural networks for semantic segmentation. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE;2019:593\u2010602.","DOI":"10.1109\/ICCV.2019.00068"},{"key":"e_1_2_11_19_1","doi-asserted-by":"crossref","unstructured":"ChenL\u2010C ZhuY PapandreouG SchroffF AdamH.Encoder\u2010decoder with atrous separable convolution for semantic image segmentation. In:Proceedings of the European Conference on Computer Vision.ECCV;2018:801\u2010818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_11_20_1","doi-asserted-by":"crossref","unstructured":"ZhangH DanaK ShiJ et\u00a0al.Context encoding for semantic segmentation. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE;2018:7151\u20107160.","DOI":"10.1109\/CVPR.2018.00747"},{"key":"e_1_2_11_21_1","doi-asserted-by":"crossref","unstructured":"HuangZ WangX HuangL HuangC WeiY LiuW.Ccnet: criss\u2010cross attention for semantic segmentation. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE;2019:603\u2010612.","DOI":"10.1109\/ICCV.2019.00069"},{"key":"e_1_2_11_22_1","doi-asserted-by":"crossref","unstructured":"YuanY ChenX WangJ.Object\u2010contextual representations for semantic segmentation. In:Computer Vision\u2013ECCV 2020: 16th European Conference Glasgow UK August 23\u201328 2020 Proceedings Part VI 16.Springer;2020:173\u2010190.","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2983721"},{"key":"e_1_2_11_24_1","doi-asserted-by":"crossref","unstructured":"TakikawaT AcunaD JampaniV FidlerS.Gated\u2010SCNN: gated shape CNNS for semantic segmentation. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE;2019:5229\u20105238.","DOI":"10.1109\/ICCV.2019.00533"},{"key":"e_1_2_11_25_1","doi-asserted-by":"crossref","unstructured":"ChaoP KaoC\u2010Y RuanY\u2010S HuangC\u2010H LinY\u2010L.Hardnet: a low memory traffic network. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE;2019:3552\u20103561.","DOI":"10.1109\/ICCV.2019.00365"},{"key":"e_1_2_11_26_1","unstructured":"HuangC\u2010H WuH\u2010Y LinY\u2010L.HarDNet\u2010MSEG: a simple encoder\u2010decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 FPS. arXiv preprint arXiv:2101.07172.2021."},{"key":"e_1_2_11_27_1","unstructured":"VaswaniA ShazeerN ParmarN et\u00a0al.Attention is all you need.Advances in Neural Information Processing Systems.2017:5998\u20106008."},{"key":"e_1_2_11_28_1","doi-asserted-by":"crossref","unstructured":"JiY ZhangR WangH et\u00a0al.Multi\u2010compound transformer for accurate biomedical image segmentation. In:Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference Strasbourg France September 27\u2013October 1 2021 Proceedings Part I 24.Springer;2021:326\u2010336.","DOI":"10.1007\/978-3-030-87193-2_31"},{"key":"e_1_2_11_29_1","doi-asserted-by":"crossref","unstructured":"ValanarasuJMJ OzaP HacihalilogluI PatelVM.Medical transformer: gated axial\u2010attention for medical image segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:36\u201046.","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"e_1_2_11_30_1","doi-asserted-by":"crossref","unstructured":"JiG\u2010P ChouY\u2010C FanD\u2010P et\u00a0al.Progressively normalized self\u2010attention network for video polyp segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:142\u2010152.","DOI":"10.1007\/978-3-030-87193-2_14"},{"key":"e_1_2_11_31_1","doi-asserted-by":"crossref","unstructured":"BaiW OktayO SinclairM et\u00a0al.Semi\u2010supervised learning for network\u2010based cardiac MR image segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2017:253\u2010260.","DOI":"10.1007\/978-3-319-66185-8_29"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_2_11_34_1","doi-asserted-by":"crossref","unstructured":"ChaitanyaK KaraniN BaumgartnerCF BeckerA DonatiO KonukogluE.Semi\u2010supervised and task\u2010driven data augmentation. In:International Conference on Information Processing in Medical Imaging.Springer;2019:29\u201041.","DOI":"10.1007\/978-3-030-20351-1_3"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2759102"},{"key":"e_1_2_11_36_1","doi-asserted-by":"crossref","unstructured":"Rei\u00dfS SeiboldC FreytagA RodnerE StiefelhagenR.Every annotation counts: multi\u2010label deep supervision for medical image segmentation. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE;2021:9532\u20109542.","DOI":"10.1109\/CVPR46437.2021.00941"},{"key":"e_1_2_11_37_1","doi-asserted-by":"crossref","unstructured":"YuL WangS LiX FuC\u2010W HengP\u2010A.Uncertainty\u2010aware self\u2010ensembling model for semi\u2010supervised 3D left atrium segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2019:605\u2010613.","DOI":"10.1007\/978-3-030-32245-8_67"},{"key":"e_1_2_11_38_1","doi-asserted-by":"crossref","unstructured":"LiY LuoL LinH ChenH HengP\u2010A.Dual\u2010consistency semi\u2010supervised learning with uncertainty quantification for COVID\u201019 lesion segmentation from CT images. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:199\u2010209.","DOI":"10.1007\/978-3-030-87196-3_19"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107764"},{"key":"e_1_2_11_40_1","doi-asserted-by":"crossref","unstructured":"TangY CaoZ ZhangY et\u00a0al.Leveraging large\u2010scale weakly labeled data for semi\u2010supervised mass detection in mammograms. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE;2021:3855\u20103864.","DOI":"10.1109\/CVPR46437.2021.00385"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20114"},{"key":"e_1_2_11_42_1","doi-asserted-by":"crossref","unstructured":"ChenX YuanY ZengG WangJ.Semi\u2010supervised semantic segmentation with cross pseudo supervision. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE;2021:2613\u20102622.","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"e_1_2_11_43_1","doi-asserted-by":"crossref","unstructured":"WuY XuM GeZ CaiJ ZhangL.Semi\u2010supervised left atrium segmentation with mutual consistency training. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:297\u2010306.","DOI":"10.1007\/978-3-030-87196-3_28"},{"key":"e_1_2_11_44_1","first-page":"8026","article-title":"PyTorch: an imperative style, high\u2010performance deep learning library","volume":"32","author":"Paszke A","year":"2019","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T15:57:59Z","timestamp":1720540679000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,26]]},"references-count":43,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10.1002\/mp.16945"],"URL":"https:\/\/doi.org\/10.1002\/mp.16945","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,26]]},"assertion":[{"value":"2022-10-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-10","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}