{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:57:00Z","timestamp":1781614620914,"version":"3.54.5"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The development and application of deep learning-based models have seen significant success in medical image segmentation, transforming diagnostic and treatment processes. However, these advancements often rely on large, fully annotated datasets, which are challenging to obtain due to the labour-intensive and costly nature of expert annotation. Therefore, we sought to explore the feasibility and efficacy of training 2D models under severe annotation constraints, aiming to optimise segmentation performance while minimising annotation costs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose an incremental 2D self-labelling framework for segmenting 3D medical volumes from a single annotated slice per volume. A 2D U-Net is first trained on these central slices. The model then iteratively generates and filters pseudo-labels for adjacent slices, progressively fine-tuning itself on an expanding dataset. This process is repeated until the entire training set is pseudo-labelled to produce the final model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On brain MRI and liver CECT datasets, our self-labelling approach improved segmentation performance compared to using only the sparse ground-truth data, increasing the Dice Similarity Coefficient and Intersection over Union by up to 15.95% and 26.75%, respectively. It also improved 3D continuity, reducing the 95th percentile Hausdorff Distance from 69.88\u2009mm to 36.46\u2009mm. Parameter analysis revealed that a gradual propagation of high-confidence pseudo-labels was most effective.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our framework demonstrates that a computationally efficient 2D model can be leveraged through self-labelling to achieve robust 3D segmentation performance and coherence from extremely sparse annotations, offering a viable solution to reduce the annotation burden in medical imaging.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12880-025-01991-9","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:24:56Z","timestamp":1762521896000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Incremental 2D self-labelling for effective 3D medical volume segmentation with minimal annotations"],"prefix":"10.1186","volume":"25","author":[{"given":"Matthew","family":"Anderson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maged","family":"Habib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David H.","family":"Steel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boguslaw","family":"Obara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"1991_CR1","first-page":"109","volume":"5","author":"GK Seerha","year":"2013","unstructured":"Seerha GK, Kaur R. Review on recent image segmentation techniques. Int J Surg Pathol on Comput Sci Eng. 2013;5:109.","journal-title":"Int J Surg Pathol On Comput Sci Eng"},{"key":"1991_CR2","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.jksuci.2018.06.002","volume":"33","author":"A Bhargava","year":"2021","unstructured":"Bhargava A, Bansal A. Fruits and vegetables quality evaluation using computer vision: a review. J Educ Chang King Saud Univ-Comput And Inf Sci. 2021;33:243\u201357.","journal-title":"J Educ Chang King Saud Univ-Comput And Inf Sci"},{"key":"1991_CR3","unstructured":"Jain A, Bolle R, Pankanti S. Biometrics: personal identification in networked society. 1999;479."},{"key":"1991_CR4","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.ijmedinf.2018.06.003","volume":"117","author":"MA Al-Antari","year":"2018","unstructured":"Al-Antari MA, Al-Masni MA, Choi M-T, Han S-M, Kim. T.-S. A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification. Int J Multiling Med Inf. 2018;117:44\u201354.","journal-title":"Int J Multiling Med Inf"},{"key":"1991_CR5","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.artmed.2015.04.006","volume":"64","author":"S Ghose","year":"2015","unstructured":"Ghose S, Holloway L, Lim K, Chan P, Veera J, Vinod SK, Liney G, Greer PB, Dowling J. A review of segmentation and deformable registration methods applied to adaptive cervical cancer radiation therapy treatment planning. Artif Intel Med. 2015;64:75\u201387.","journal-title":"Artif Intel Med"},{"key":"1991_CR6","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1111\/1754-9485.13286","volume":"65","author":"G Samarasinghe","year":"2021","unstructured":"Samarasinghe G, Jameson M, Vinod S, Field M, Dowling J, Sowmya A, Holloway L. Deep learning for segmentation in radiation therapy planning: a review. J Med Imag Radiat Oncol. 2021;65:578\u201395.","journal-title":"J Med Imag Radiat Oncol"},{"key":"1991_CR7","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1016\/j.procs.2015.09.027","volume":"65","author":"NM Zaitoun","year":"2015","unstructured":"Zaitoun NM, Aqel MJ. Survey on image segmentation techniques. Procedia Comput Sci. 2015;65:797\u2013806.","journal-title":"Procedia Comput Sci"},{"key":"1991_CR8","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Med Image Comput and Comput- Assist Intervent. 2015;234\u201341.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1991_CR9","doi-asserted-by":"crossref","unstructured":"Anderson M, Sadiq S, Nahaboo Solim M, Barker H, Steel DH, Habib M, Obara B, et al. Biomedical data annotation: an OCT imaging case study. J Ophthalmol. 2023;2023.","DOI":"10.1155\/2023\/5747010"},{"key":"1991_CR10","doi-asserted-by":"publisher","first-page":"119105","DOI":"10.1016\/j.eswa.2022.119105","volume":"214","author":"C Zhao","year":"2023","unstructured":"Zhao C, Xiang S, Wang Y, Cai Z, Shen J, Zhou S, Zhao D, Su W, Guo S, Li S. Context-aware network fusing transformer and V-Net for semisupervised segmentation of 3D left atrium. Expert Syst with Appl. 2023;214:119105.","journal-title":"Expert Syst With Appl"},{"key":"1991_CR11","doi-asserted-by":"crossref","unstructured":"Yang L, Qi L, Feng L, Zhang W, Shi Y. Revisiting weak-to-strong consistency in semi-supervised semantic segmentation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023, p. 7236\u201346.","DOI":"10.1109\/CVPR52729.2023.00699"},{"key":"1991_CR12","doi-asserted-by":"crossref","unstructured":"Kong L, Ren J, Pan L, Liu Z. Lasermix for semi-supervised lidar semantic segmentation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023, p. 21705\u201315.","DOI":"10.1109\/CVPR52729.2023.02079"},{"key":"1991_CR13","doi-asserted-by":"crossref","unstructured":"Ru L, Zheng H, Zhan Y, Du B. Token contrast for weakly-supervised semantic segmentation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023, p. 3093\u2013102.","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"1991_CR14","doi-asserted-by":"crossref","unstructured":"Cheng Z, Qiao P, Li K, Li S, Wei P, Ji X, Yuan L, Liu C, Chen J. Out-of-candidate rectification for weakly supervised semantic segmentation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023, p. 23673\u201384.","DOI":"10.1109\/CVPR52729.2023.02267"},{"key":"1991_CR15","unstructured":"Lee D-H, et al. Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. International Conference on Machine Learning. 2013, p. 896, vol. 3."},{"key":"1991_CR16","doi-asserted-by":"crossref","unstructured":"Xie Q, Luong M-T, Hovy E, Le QV. Self-training with noisy student improves imagenet classification. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020, p. 10687\u201398.","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"1991_CR17","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1038\/s42256-022-00568-3","volume":"4","author":"GM Ven","year":"2022","unstructured":"Ven GM, Tuytelaars T, Tolias AS. Three types of incremental learning. Nat Mach Intell. 2022;4:1185\u201397.","journal-title":"Nat Mach Intell"},{"key":"1991_CR18","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","volume":"113","author":"GI Parisi","year":"2019","unstructured":"Parisi GI, Kemker R, Part JL, Kanan C, Wermter S. Continual lifelong learning with neural networks: a review. Neural Netw. 2019;113:54\u201371.","journal-title":"Neural Netw"},{"key":"1991_CR19","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/S2589-7500(20)30102-3","volume":"2","author":"CS Lee","year":"2020","unstructured":"Lee CS, Lee AY. Clinical applications of continual learning machine learning. The Lancet Digit Health. 2020;2:279\u201381.","journal-title":"The Lancet Digit Health"},{"key":"1991_CR20","doi-asserted-by":"crossref","unstructured":"Shaheen K, Hanif MA, Hasan O, Shafique M. Continual learning for realworld autonomous systems: algorithms, challenges and frameworks. J Intell Robot Syst. 2022;105(9).","DOI":"10.1007\/s10846-022-01603-6"},{"key":"1991_CR21","unstructured":"Philps D, Weyde T, Garcez AD, Batchelor R. Continual learning augmented investment decisions. 2008; arXiv preprint arXiv:1812.02340."},{"key":"1991_CR22","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1109\/TTS.2023.3234203","volume":"4","author":"T Dhar","year":"2023","unstructured":"Dhar T, Dey N, Borra S, Sherratt RS. Challenges of deep learning in medical image analysis\u2014improving explainability and trust. IEEE Trans Technol Soc. 2023;4:68\u201375.","journal-title":"IEEE Trans Technol Soc"},{"key":"1991_CR23","doi-asserted-by":"crossref","unstructured":"Shi W, Gong Y, Ding C, Tao ZM, Zheng N. Transductive semi-supervised deep learning using min-max features. European Conference on Computer Vision. 2018, p. 299\u2013315.","DOI":"10.1007\/978-3-030-01228-1_19"},{"key":"1991_CR24","unstructured":"Laine S, Aila T. Temporal ensembling for semi-supervised learning. 2016; arXiv preprint arXiv:1610.02242."},{"key":"1991_CR25","unstructured":"Tarvainen A, Valpola H. Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. Adv Neural Inf Process Syst. 2017."},{"key":"1991_CR26","doi-asserted-by":"crossref","unstructured":"Arazo E, Ortego D, Albert P, O\u2019Connor NE, McGuinness K. Pseudolabeling and confirmation bias in deep semi-supervised learning. International Joint Conference on Neural Networks. 2020, p. 1\u20138.","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"1991_CR27","unstructured":"Xu Y, Shang L, Ye J, Qian Q, Li Y-F, Sun B, Li H, Jin R. Dash: semisupervised learning with dynamic thresholding. International Conference on Machine Learning. 2021, p. 11525\u201336."},{"key":"1991_CR28","unstructured":"Zou Y, Zhang Z, Zhang H, Li C-L, Bian X, Huang J-B, Pfister T. Pseudoseg: designing pseudo labels for semantic segmentation. 2020; arXiv preprint arXiv:2010.09713."},{"key":"1991_CR29","first-page":"396","volume-title":"Medical image computing and computer assisted intervention","author":"J Cai","year":"2018","unstructured":"Cai J, Tang Y, Lu L, Harrison AP, Yan K, Xiao J, Yang L, Summers, RM. Accurate weakly-supervised deep lesion segmentation using large-scale clinical annotations: slice-propagated 3D mask generation from 2D RECIST. In: Medical image computing and computer assisted intervention. Springer; 2018. p. 396\u2013404."},{"key":"1991_CR30","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1109\/JBHI.2020.3038847","volume":"25","author":"A Bitarafan","year":"2020","unstructured":"Bitarafan A, Nikdan M, Baghshah MS. 3D image segmentation with sparse annotation by self-training and internal registration. IEEE J Biomed and Health Inf. 2020;25:2665\u201372.","journal-title":"IEEE J Biomed And Health Inf"},{"issue":"1","key":"1991_CR31","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","volume":"13","author":"M Antonelli","year":"2022","unstructured":"Antonelli M, Reinke A, Bakas S, Farahani K, Kopp-Schneider A, Landman BA, Litjens G, Menze B, Ronneberger O, Summers RM, Ginneken B, Bilello M, Bilic P, Christ PF, Do RKG, Gollub MJ, Heckers SH, Huisman H, Jarnagin WR, McHugo MK, Napel S, Pernicka JSG, Rhode K, Tobon-Gomez C, Vorontsov E, Meakin JA, Ourselin S, Wiesenfarth M, Arbel\u00e1ez P, Bae B, Chen S, Daza L, Feng J, He B, Isensee F, Ji Y, Jia F, Kim I, Maier-Hein KMerhof D, et al. The medical segmentation decathlon. Nat Commun. 2022;13(1):4128.","journal-title":"Nat Commun"},{"key":"1991_CR32","doi-asserted-by":"publisher","first-page":"102680","DOI":"10.1016\/j.media.2022.102680","volume":"84","author":"P Bilic","year":"2023","unstructured":"Bilic P, Christ P, Li HB, Vorontsov E, Ben-Cohen A, Kaissis G, Szeskin A, Jacobs C, Mamani GEHChartrand G, et al. The liver tumor segmentation benchmark (lits). Med Image Anal. 2023;84:102680.","journal-title":"Med Image Anal"},{"key":"1991_CR33","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/TMI.2019.2930068","volume":"39","author":"D Karimi","year":"2019","unstructured":"Karimi D, Salcudean SE. Reducing the hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Trans Med Imag. 2019;39:499\u2013513.","journal-title":"IEEE Trans Med Imag"},{"key":"1991_CR34","unstructured":"Ouali Y, Hudelot C, Tami M. An overview of deep semi-supervised learning. arXiv preprint. 2020. arXiv:2006.05278."},{"key":"1991_CR35","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3390\/bioengineering10020181","volume":"10","author":"A Avesta","year":"2023","unstructured":"Avesta A, Hossain S, Lin M, Aboian M, Krumholz HM, Aneja S. Comparing 3d, 2.5 d, and 2d approaches to brain image auto-segmentation. Bioengineering. 2023;10:181.","journal-title":"Bioengineering"}],"updated-by":[{"DOI":"10.1186\/s12880-026-02270-x","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000}}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01991-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-025-01991-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01991-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:19:21Z","timestamp":1781612361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12880-025-01991-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1991"],"URL":"https:\/\/doi.org\/10.1186\/s12880-025-01991-9","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]},"assertion":[{"value":"9 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2026","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1186\/s12880-026-02270-x","URL":"https:\/\/doi.org\/10.1186\/s12880-026-02270-x","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"450"}}