{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T13:10:05Z","timestamp":1746537005389,"version":"3.40.5"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T00:00:00Z","timestamp":1739232000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T00:00:00Z","timestamp":1739232000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100020963","name":"Moonshot Research and Development Program","doi-asserted-by":"publisher","award":["JPMJMS2214"],"award-info":[{"award-number":["JPMJMS2214"]}],"id":[{"id":"10.13039\/501100020963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Purpose<\/jats:title>\n            <jats:p>Deep-learning-based supervised CT segmentation relies on fully and densely labeled data, the labeling process of which is time-consuming. In this study, our proposed method aims to improve segmentation performance on CT volumes with limited annotated data by considering category-wise difficulties and distribution.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>We propose a novel confidence-difficulty weight (CDifW) allocation method that considers confidence levels, balancing the training across different categories, influencing the loss function and volume-mixing process for pseudo-label generation. Additionally, we introduce a novel Double-Mix Pseudo-label Framework (DMPF), which strategically selects categories for image blending based on the distribution of voxel-counts per category and the weight of segmentation difficulty. DMPF is designed to enhance the segmentation performance of categories that are challenging to segment.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Result<\/jats:title>\n            <jats:p>Our approach was tested on two commonly used datasets: a Congenital Heart Disease (CHD) dataset and a Beyond-the-Cranial-Vault (BTCV) Abdomen dataset. Compared to the SOTA methods, our approach achieved an improvement of 5.1% and 7.0% in Dice score for the segmentation of difficult-to-segment categories on 5% of the labeled data in CHD and 40% of the labeled data in BTCV, respectively.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>Our method improves segmentation performance in difficult categories within CT volumes by category-wise weights and weight-based mixture augmentation. Our method was validated across multiple datasets and is significant for advancing semi-supervised segmentation tasks in health care. The code is available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/MoriLabNU\/Double-Mix\" ext-link-type=\"uri\">https:\/\/github.com\/MoriLabNU\/Double-Mix<\/jats:ext-link>.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s11548-024-03281-1","type":"journal-article","created":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T14:22:50Z","timestamp":1739283770000},"page":"991-1002","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Double-mix pseudo-label framework: enhancing semi-supervised segmentation on category-imbalanced CT volumes"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4427-5113","authenticated-orcid":false,"given":"Luyang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuichiro","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7714-422X","authenticated-orcid":false,"given":"Masahiro","family":"Oda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0100-4797","authenticated-orcid":false,"given":"Kensaku","family":"Mori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,11]]},"reference":[{"key":"3281_CR1","first-page":"34","volume":"13435","author":"Y Wu","year":"2022","unstructured":"Wu Y, Wu Z, Wu Q, Ge Z, Cai J (2022) Exploring smoothness and class-separation for semi-supervised medical image segmentation. MICCAI, LNCS 13435:34\u201343","journal-title":"MICCAI, LNCS"},{"key":"3281_CR2","first-page":"582","volume":"14222","author":"H Wang","year":"2022","unstructured":"Wang H, Li X (2022) DHC: Dual-debiased heterogeneous co-training framework for class-imbalanced semi-supervised medical image segmentation. MICCAI, LNCS 14222:582\u2013591","journal-title":"MICCAI, LNCS"},{"key":"3281_CR3","first-page":"109","volume":"13438","author":"Y Lin","year":"2022","unstructured":"Lin Y, Yao H, Li Z, Zheng G, Li X (2022) Calibrating label distribution for class-imbalanced barely-supervised knee segmentation. MICCAI, LNCS 13438:109\u2013118","journal-title":"MICCAI, LNCS"},{"key":"3281_CR4","unstructured":"French G, Laine S, Aila T, Mackiewicz M, Finlayson G (2020) Semi-supervised semantic segmentation needs strong, varied perturbations. In: BMVC"},{"key":"3281_CR5","doi-asserted-by":"crossref","unstructured":"Olsson V, Tranheden W, Pinto J, Svensson L (2021) Classmix: Segmentation-based data augmentation for semi-supervised learning. WACV 1369\u20131378","DOI":"10.1109\/WACV48630.2021.00141"},{"key":"3281_CR6","doi-asserted-by":"crossref","unstructured":"Chen X, Yuan Y, Zeng G, Wang J (2021) Semi-supervised semantic segmentation with cross pseudo supervision. CVPR 2613\u20132622","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"3281_CR7","first-page":"231","volume":"7","author":"A Krogh","year":"1994","unstructured":"Krogh A, Vedelsby J (1994) Neural network ensembles, cross validation, and active learning. NeurIPS 7:231\u2013238","journal-title":"NeurIPS"},{"issue":"3","key":"3281_CR8","first-page":"473","volume":"18","author":"J Qiu","year":"2023","unstructured":"Qiu J, Hayashi Y, Oda M, Kitasaka T, Mori K (2023) Class-wise confidence-aware active learning for laparoscopic images segmentation. Int J Comput Assist Radiol Surg 18(3):473\u2013482","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3281_CR9","unstructured":"Landman B, Xu Z, Igelsias J, Styner M, Langerak T, Klein A (2015) 2015 MICCAI Multi-Atlas Labeling Beyond Cranial Vault\u2013Workshop Challenge"},{"key":"3281_CR10","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi S-A (2016) V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In: 3DV, pp. 565\u2013571. IEEE","DOI":"10.1109\/3DV.2016.79"},{"key":"3281_CR11","volume-title":"Exponential Smoothing for Predicting Demand","author":"RG Brown","year":"1956","unstructured":"Brown RG (1956) Exponential Smoothing for Predicting Demand. Little, Brown and Company, Boston"},{"key":"3281_CR12","unstructured":"Yurdakul B (2018) Statistical properties of population stability index (psi). PhD thesis, Western Michigan University"},{"key":"3281_CR13","unstructured":"Gal Y, Islam R, Ghahramani Z (2017) Deep bayesian active learning with image data. In: ICML, pp. 1183\u20131192. PMLR"},{"key":"3281_CR14","doi-asserted-by":"crossref","unstructured":"Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2):203\u2013211","DOI":"10.1038\/s41592-020-01008-z"},{"key":"3281_CR15","doi-asserted-by":"crossref","unstructured":"Xu X, Wang T, Shi Y, Yuan H, Jia Q, Huang M, Zhuang J (2019) Whole heart and great vessel segmentation in congenital heart disease using deep neural networks and graph matching. MICCAI, Proceedings, Part II, LNIP 11765:477\u2013485 Springer","DOI":"10.1007\/978-3-030-32245-8_53"},{"key":"3281_CR16","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s00261-010-9623-7","volume":"36","author":"JR Long","year":"2011","unstructured":"Long JR, Frew MI, Brazaitis MP (2011) Virtual colonoscopy in the US army: current utilization at the Walter Reed Army Medical Center. Abdom Imaging 36:149\u2013152","journal-title":"Abdom Imaging"},{"key":"3281_CR17","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: ICCV, pp. 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"3281_CR18","first-page":"32424","volume":"35","author":"B Chen","year":"2022","unstructured":"Chen B, Jiang J, Wang X, Wan P, Wang J, Long M (2022) Debiased self-training for semi-supervised learning. NeurIPS 35:32424\u201332437","journal-title":"NeurIPS"},{"key":"3281_CR19","doi-asserted-by":"crossref","unstructured":"Wang X, Wu Z, Lian L, Yu SX (2022) Debiased learning from naturally imbalanced pseudo-labels. In: CVPR, pp. 14647\u201314657","DOI":"10.1109\/CVPR52688.2022.01424"},{"key":"3281_CR20","doi-asserted-by":"crossref","unstructured":"Wei C, Sohn K, Mellina C, Yuille A, Yang F (2021) CReST: A class-rebalancing self-training framework for imbalanced semi-supervised learning. In: CVPR, pp. 10857\u201310866","DOI":"10.1109\/CVPR46437.2021.01071"},{"key":"3281_CR21","unstructured":"Devries T, Taylor GW (2017) Improved regularization of convolutional neural networks with Cutout. CoRR arXiv:1708.04552"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03281-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-024-03281-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03281-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T12:51:35Z","timestamp":1746535895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-024-03281-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,11]]},"references-count":21,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["3281"],"URL":"https:\/\/doi.org\/10.1007\/s11548-024-03281-1","relation":{},"ISSN":["1861-6429"],"issn-type":[{"type":"electronic","value":"1861-6429"}],"subject":[],"published":{"date-parts":[[2025,2,11]]},"assertion":[{"value":"1 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All the datasets used in this study are publicly available for academic research.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}