{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:18:23Z","timestamp":1778285903300,"version":"3.51.4"},"reference-count":60,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T00:00:00Z","timestamp":1750809600000},"content-version":"vor","delay-in-days":175,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Generally, there are two problems restrict the intracranial haemorrhage (ICH) segmentation task: scarcity of labelled data, and poor accuracy of ICH segmentation. To address these two issues, we propose a semi\u2010supervised ICH segmentation model and a dedicated ICH segmentation backbone network. Our approach aims at leveraging semi\u2010supervised modelling so as to alleviate the challenge of limited labelled data availability, while the dedicated ICH segmentation backbone network further enhances the segmentation precision. An augmented multiple perturbation dual mean teacher model is designed. Based on it, the prediction accuracy may be improved by a more stringent confidence\u2010weighted cross\u2010entropy (CW\u2010CE) loss, and the feature perturbation may be increased using adversarial feature perturbation for the purpose of improving the generalization ability and efficiency of consistent learning. In the ICH segmentation backbone network, we promote the segmentation accuracy by extracting both local and global features of ICH and fusing them in depth. We also fuse the features with rich details from the upper encoder during the up\u2010sampling process to reduce the loss of feature information. Experiments on our private dataset ICHDS, and the public dataset IN22SD demonstrate that our model outperforms current state\u2010of\u2010the\u2010art ICH segmentation models, achieving a maximum improvement of over 10% in Dice and exhibiting the best overall performance.<\/jats:p>","DOI":"10.1049\/ipr2.70102","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T23:39:21Z","timestamp":1750894761000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Augmented Multiple Perturbation Dual Mean Teacher Model for Semi\u2010Supervised Intracranial Haemorrhage Segmentation"],"prefix":"10.1049","volume":"19","author":[{"given":"Yan","family":"Dong","sequence":"first","affiliation":[{"name":"College of Electrical Engineering and Control Science Nanjing Tech University  Nanjing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangjun","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery Jinling Hospital Affiliated Hospital of Medical School Nanjing University  Nanjing Jiangsu China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7414-5390","authenticated-orcid":false,"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering and Control Science Nanjing Tech University  Nanjing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery Jinling Hospital Affiliated Hospital of Medical School Nanjing University  Nanjing Jiangsu China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenxing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery Jinling Hospital Affiliated Hospital of Medical School Nanjing University  Nanjing Jiangsu China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanling","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery Jinling Hospital Affiliated Hospital of Medical School Nanjing University  Nanjing Jiangsu China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurosh","family":"Madani","sequence":"additional","affiliation":[{"name":"Images Signals and Intelligent Systems Laboratory (LISSI\/EA 3956) Paris Est\/Paris 12\u2010Val de Marne University Senart\u2010FB Institute of Technology  Lieusaint France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhui","family":"Wan","sequence":"additional","affiliation":[{"name":"Department of Geriatrics Jinling Hospital Affiliated Hospital of Medical School Nanjing University  Nanjing Jiangsu China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000010660"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jns.2020.117020"},{"key":"e_1_2_11_4_1","first-page":"593","article-title":"Advances in the Management of Intracerebral Hemorrhage","volume":"6","author":"Adeoye O.","year":"2010","journal-title":"Nature Reviews Neuroscience"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3103850"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.113.003701"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1161\/01.STR.27.8.1304"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.120.032243"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-016-1720-z"},{"key":"e_1_2_11_10_1","doi-asserted-by":"crossref","unstructured":"M.Islam P.Sanghani A. A. Q.See M. L.James N. K. K.King andH.Ren \u201cICHNet: Intracerebral Hemorrhage (ich) Segmentation Using Deep Learning \u201d inProceedings of the International MICCAI Brainlesion Workshop(Springer 2018) 456\u2013463.","DOI":"10.1007\/978-3-030-11723-8_46"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12524-024-01994-z"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003469605-4"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781394186686.ch10"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxae130"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3317632"},{"key":"e_1_2_11_16_1","doi-asserted-by":"crossref","unstructured":"Z.Yang Y.Chen Z.Wang H.Shan Y.Chen andY.Zhang \u201cPatient\u2010Level Anatomy Meets Scanning\u2010Level Physics: Personalized Federated Low\u2010Dose CT Denoising Empowered by Large Language Model \u201d preprint arxiv:2503.00908 March 2 2025 https:\/\/doi.org\/10.48550\/arXiv.2503.00908.","DOI":"10.1109\/CVPR52734.2025.00486"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108004"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-54491-6"},{"key":"e_1_2_11_19_1","doi-asserted-by":"crossref","unstructured":"D.Kwon J.Ahn J.Kim et\u00a0al. \u201cSiamese U\u2010Net With Healthy Template for Accurate Segmentation of Intracranial Hemorrhage \u201d inProceedings of theInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention(Springer 2019) 848\u2013855.","DOI":"10.1007\/978-3-030-32248-9_94"},{"key":"e_1_2_11_20_1","doi-asserted-by":"crossref","unstructured":"D.Guo H.Wei P.Zhao et\u00a0al. \u201cSimultaneous Classification and Segmentation of Intracranial Hemorrhage Using a Fully Convolutional Neural Network \u201d inProceedings of the2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)(IEEE 2020) 118\u2013121.","DOI":"10.1109\/ISBI45749.2020.9098596"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-020-09493-5"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2021.101908"},{"key":"e_1_2_11_23_1","doi-asserted-by":"crossref","unstructured":"Q.Liu B. J.Macintosh T.Schellhorn K.Skogen K.Emblem andA.Bj\u00f8rnerud \u201cVoxels Intersecting Along Orthogonal Levels Attention U\u2010Net (Viola\u2010UNet) to Segment Intracerebral Haemorrhage Using Computed Tomography Head Scans \u201d preprint arXiv:2208.06313 August 12 2022 https:\/\/doi.org\/10.48550\/arXiv.2208.06313.","DOI":"10.1109\/ISBI53787.2023.10230843"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107840"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3154159"},{"key":"e_1_2_11_26_1","doi-asserted-by":"crossref","unstructured":"S.Li C.Zhang X.He andA. L.Martel \u201cShape\u2010Aware Semi\u2010Supervised 3D Semantic Segmentation for Medical Images \u201d inMedical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020(Springer 2020) 12261\u201312261.","DOI":"10.1007\/978-3-030-59710-8_54"},{"key":"e_1_2_11_27_1","doi-asserted-by":"crossref","unstructured":"Y.Wu M.Xu Z.Ge J.Cai andL.Zhang \u201cSemi\u2010Supervised Left Atrium Segmentation With Mutual Consistency Training \u201d in24th International Conference on Medical Image Computing and Computer Assisted Intervention\u2010MICCAI 2021(Springer International Publishing 2021) 297\u2013306.","DOI":"10.1007\/978-3-030-87196-3_28"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2995319"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969790"},{"key":"e_1_2_11_30_1","unstructured":"A.TarvainenandH.Valpola \u201cMean Teachers are Better Role Models: Weight\u2010Averaged Consistency Targets Improve Semi\u2010Supervised Deep Learning Results \u201d inProceedings of the 31st International Conference on Neural Information Processing Systems(Curran Associates Inc. 2017) 1195\u20131204."},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2892409"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"e_1_2_11_34_1","doi-asserted-by":"crossref","unstructured":"O.Ronneberger P.Fischer andT.Brox \u201cU\u2010Net: Convolutional Networks for Biomedical Image Segmentation \u201d inMedical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI 2015: 18th International Conference(Springer International Publishing 2015) 234\u2013241. .","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_11_36_1","doi-asserted-by":"crossref","unstructured":"X.Xiao S.Lian Z.Luo andS.Li \u201cWeighted Res\u2010unet for High\u2010Quality Retina Vessel Segmentation \u201d in2018 9th International Conference on Information Technology in Medicine And Education (ITME)(IEEE 2018) 327\u2013331.","DOI":"10.1109\/ITME.2018.00080"},{"key":"e_1_2_11_37_1","doi-asserted-by":"crossref","unstructured":"H.Huang L.Lin R.Tong et\u00a0al. \u201cUnet 3+: A Full\u2010scale Connected UNet for Medical Image Segmentation \u201d inICASSP\u20142020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)(IEEE 2020) 1055\u20131059.","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"e_1_2_11_38_1","doi-asserted-by":"crossref","unstructured":"Z.Li D.Li C.Xu et\u00a0al. \u201cTFCNS: A CNN\u2010Transformer Hybrid Network for Medical Image Segmentation \u201d inInternational Conference on Artificial Neural Networks(Springer Nature 2022) 781\u2013792.","DOI":"10.1007\/978-3-031-15937-4_65"},{"key":"e_1_2_11_39_1","doi-asserted-by":"crossref","unstructured":"Y.Xie J.Zhang C.Shen andY.Xia \u201cCOTR: Efficiently Bridging CNN and Transformer for 3d Medical Image Segmentation \u201d in24th International Conference on Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021 (Springer International Publishing 2021) 171\u2013180.","DOI":"10.1007\/978-3-030-87199-4_16"},{"key":"e_1_2_11_40_1","article-title":"Attention is All You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"e_1_2_11_41_1","unstructured":"J.Chen Y.Lu Q.Yu et\u00a0al. \u201cTransUNet: Transformers Make Strong Encoders for Medical Image Segmentation \u201d preprint arXiv:2102.04306 February 8 2021 https:\/\/doi.org\/10.48550\/arXiv.2102.04306."},{"key":"e_1_2_11_42_1","doi-asserted-by":"crossref","unstructured":"A.Hatamizadeh Y.Tang V.Nath et\u00a0al. \u201cUNetr: Transformers for 3d Medical Image Segmentation \u201d inProceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision(IEEE 2022) 574\u2013584.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"e_1_2_11_43_1","doi-asserted-by":"crossref","unstructured":"Y.Tang D.Yang W.Li et\u00a0al. \u201cSelf\u2010Supervised Pre\u2010training of Swin Transformers for 3D Medical Image Analysis \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2022) 20730\u201320740.","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"e_1_2_11_44_1","doi-asserted-by":"crossref","unstructured":"M. M.RahmanandR.Marculescu \u201cMulti\u2010Scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation \u201d preprint arXiv:2303.16892 March 29 2023 https:\/\/doi.org\/10.48550\/arXiv.2303.16892.","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A5742"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105546"},{"key":"e_1_2_11_47_1","doi-asserted-by":"crossref","unstructured":"D.Wang C.Wang L.Masters andM.Barnett \u201cMasked Multi\u2010Task Network for Case\u2010Level Intracranial Hemorrhage Classification in Brain CT Volumes \u201d inInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention(Springer 2020) 145\u2013154.","DOI":"10.1007\/978-3-030-59728-3_15"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102489"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.03.009"},{"key":"e_1_2_11_50_1","unstructured":"S.LaineandT.Aila \u201cTemporal Ensembling for Semi\u2010Supervised Learning \u201d preprint arXiv:1610.02242 October 7 2016 https:\/\/doi.org\/10.48550\/arXiv.1610.02242."},{"key":"e_1_2_11_51_1","doi-asserted-by":"crossref","unstructured":"G.French S.Laine T.Aila M.Mackiewicz andG.Finlayson \u201cSemi\u2010Supervised Semantic Segmen\u2010Tation Needs Strong Varied Perturbations \u201d preprint arXiv:1906.01916 June 5 2019 https:\/\/doi.org\/10.48550\/arXiv.1906.01916.","DOI":"10.5244\/C.34.154"},{"key":"e_1_2_11_52_1","doi-asserted-by":"crossref","unstructured":"Y.Ouali C.Hudelot andM.Tami \u201cSemi\u2010Supervised Semantic Segmentation With Cross\u2010Consistency Training \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2020) 12674\u201312684.","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"e_1_2_11_53_1","unstructured":"M.\u2010C.Xu Y.\u2010K.Zhou C.Jin et\u00a0al \u201cLearning Morphological Feature Perturbations for Calibrated Semi\u2010Supervised Segmentation \u201d preprint arXiv:2203.10196 March 19 2022 https:\/\/doi.org\/10.48550\/arXiv.2203.10196."},{"key":"e_1_2_11_54_1","doi-asserted-by":"crossref","unstructured":"K.Zheng J.Xu andJ.Wei \u201cDouble Noise Mean Teacher Self\u2010Ensembling Model for Semi\u2010Supervised Tumor Segmentation \u201d inICASSP 2022\u20102022 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)(IEEE 2022) 1446\u20131450.","DOI":"10.1109\/ICASSP43922.2022.9746957"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3139999"},{"key":"e_1_2_11_56_1","doi-asserted-by":"crossref","unstructured":"Z.Xie E.Tu H.Zheng Y.Gu andJ.Yang \u201cSemi\u2010Supervised Skin Lesion Segmentation With Learning Model Confidence \u201d inICASSP 2021\u20102021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)(IEEE 2021) 1135\u20131139.","DOI":"10.1109\/ICASSP39728.2021.9414297"},{"key":"e_1_2_11_57_1","doi-asserted-by":"crossref","unstructured":"Y.Bai D.Chen Q.Li W.Shen andY.Wang \u201cBidirectional Copy\u2010Paste for Semi\u2010Supervised Medical Image Segmentation \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2023) 11514\u201311524.","DOI":"10.1109\/CVPR52729.2023.01108"},{"key":"e_1_2_11_58_1","unstructured":"X.Zhao Z.Qi S.Wang et\u00a0al. \u201cRCPS: Rectified Contrastive Pseudo Supervision for Semi\u2010Supervised Medical Image Segmentation \u201d preprint arXiv:2301.05500 January 13 2023 https:\/\/doi.org\/10.48550\/arXiv.2301.05500."},{"key":"e_1_2_11_59_1","unstructured":"A.Dosovitskiy L.Beyer A.Kolesnikov et\u00a0al. \u201cAn Image is Worth 16\u00d716 Words: Transformers for Image Recognition at Scale \u201d preprint arXiv:2010.11929 October 22 2020 https:\/\/doi.org\/10.48550\/arXiv.2010.11929."},{"key":"e_1_2_11_60_1","doi-asserted-by":"crossref","unstructured":"Z.Liu Y.Lin Y.Cao et\u00a0al. \u201cSwin Transformer: Hierarchical Vision Transformer Using Shifted Windows \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision(IEEE 2021) 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_11_61_1","unstructured":"J.Ho N.Kalchbrenner D.Weissenborn andT.Salimans \u201cAxial Attention in Multidimensional Transformers \u201d preprint arXiv:1912.12180 December 20 2019 https:\/\/doi.org\/10.48550\/arXiv.1912.12180."}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70102","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70102","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:02:51Z","timestamp":1778284971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":60,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70102"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70102","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-09-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70102"}}