{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T04:31:11Z","timestamp":1780806671660,"version":"3.54.1"},"reference-count":30,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Tomography"],"abstract":"<jats:p>Background\/Objectives: Automatic segmentation and identification of vertebrae in spinal CT are essential for assisting diagnosis of spinal disorders and for preoperative planning. The task is challenging due to the high structural similarity between adjacent vertebrae and the morphological variability of vertebrae. Most existing methods rely on fully supervised deep learning and, constrained by limited annotations, struggle to remain robust in complex scenarios. Methods: We propose a semi-supervised approach built on a dual-branch 3D U-Net. Mamba modules are inserted between the encoder and decoder to model long-range dependencies along the cranio\u2013caudal axis. The identification branch employs a 3D convolutional block attention module (3D-CBAM) to enhance class discriminability. A unified semi-supervised objective is formulated via teacher\u2013student consistency: for each unlabeled sample, weakly and strongly augmented views are generated, and cross-branch consistency is enforced, together with confidence-based filtering and class-frequency reweighting. In addition, a connected-component analysis is used to enforce anatomically plausible sequential continuity of vertebral indices in the outputs. Results: Experiments on VerSe 2019 and 2020 show that, on the public VerSe 2019 test set (with VerSe 2020 scans used as unlabeled training data), the supervised baseline achieved a Dice score of 89.8% and an identification accuracy of 92.3%. Incorporating unlabeled data improved performance to 91.6% Dice and 97.5% identification accuracy (relative gains of +1.8 and +5.2 percentage points). Compared with competing methods, the proposed semi-supervised model attains higher or comparable segmentation accuracy and the highest identification accuracy. Conclusions: Without additional annotation cost, the proposed method markedly improves the overall performance of vertebra segmentation and identification, offering more robust automated support for clinical workflows.<\/jats:p>","DOI":"10.3390\/tomography12030033","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:22:21Z","timestamp":1772551341000},"page":"33","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Semi-Supervised Vertebra Segmentation and Identification in CT Images"],"prefix":"10.3390","volume":"12","author":[{"given":"You","family":"Fu","sequence":"first","affiliation":[{"name":"School of Information Technology, Murdoch University, Murdoch 6150, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiasen","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Automation, University of Science and Technology Beijing, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanlin","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Biological Sciences and Medical Engineering, Southeast University, Nanjing 210096, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"key":"ref_1","first-page":"350","article-title":"Clinical examination of the spine","volume":"39","author":"Gordon","year":"2021","journal-title":"Surgery"},{"key":"ref_2","first-page":"370","article-title":"Imaging the spine","volume":"36","author":"Wong","year":"2018","journal-title":"Surgery"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.1001\/jama.2018.11100","article-title":"Deep learning\u2014A technology with the potential to transform health care","volume":"320","author":"Hinton","year":"2018","journal-title":"JAMA"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102166","DOI":"10.1016\/j.media.2021.102166","article-title":"VerSe: A vertebrae labelling and segmentation benchmark for multi-detector CT images","volume":"73","author":"Sekuboyina","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Payer, C., Stern, D., Bischof, H., and Urschler, M. (2020, January 27\u201329). Coarse to Fine Vertebrae Localization and Segmentation with SpatialConfiguration-Net and U-Net. Proceedings of the VISIGRAPP (5: VISAPP), Valletta, Malta.","DOI":"10.5220\/0008975201240133"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e190074","DOI":"10.1148\/ryai.2020190074","article-title":"Labeling vertebrae with two-dimensional reformations of multidetector CT images: An adversarial approach for incorporating prior knowledge of spine anatomy","volume":"2","author":"Sekuboyina","year":"2020","journal-title":"Radiol. Artif. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/j.media.2009.02.004","article-title":"Automated model-based vertebra detection, identification, and segmentation in CT images","volume":"13","author":"Klinder","year":"2009","journal-title":"Med. Image Anal."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1109\/TMI.2015.2389334","article-title":"A framework for automated spine and vertebrae interpolation-based detection and model-based segmentation","volume":"34","author":"Korez","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Glocker, B., Zikic, D., Konukoglu, E., Haynor, D.R., and Criminisi, A. (2013, January 22\u201326). Vertebrae localization in pathological spine CT via dense classification from sparse annotations. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Nagoya, Japan.","DOI":"10.1007\/978-3-642-40763-5_33"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., and Ahmadi, S.-A. (2016, January 25\u201328). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"ref_12","unstructured":"Lessmann, N., van Ginneken, B., and I\u0161gum, I. (2018, January 11\u201315). Iterative convolutional neural networks for automatic vertebra identification and segmentation in CT images. Proceedings of the Medical Imaging 2018: Image Processing, Houston, TX, USA."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.media.2019.02.005","article-title":"Iterative fully convolutional neural networks for automatic vertebra segmentation and identification","volume":"53","author":"Lessmann","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1266","DOI":"10.1109\/TMI.2018.2798293","article-title":"Joint vertebrae identification and localization in spinal CT images by combining short-and long-range contextual information","volume":"37","author":"Liao","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102235","DOI":"10.1016\/j.compmedimag.2023.102235","article-title":"Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle","volume":"107","author":"Meng","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"103380","DOI":"10.1016\/j.media.2024.103380","article-title":"Semantics and instance interactive learning for labeling and segmentation of vertebrae in CT images","volume":"99","author":"Mao","year":"2025","journal-title":"Med. Image Anal."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103285","DOI":"10.1016\/j.artmed.2025.103285","article-title":"SpineCLUE: Automatic Vertebrae Identification Using Contrastive Learning and Uncertainty Estimation","volume":"171","author":"Zhang","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref_18","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Perone, C.S., and Cohen-Adad, J. (2018, January 20). Deep semi-supervised segmentation with weight-averaged consistency targets. Proceedings of the International Workshop on Deep Learning in Medical Image Analysis, Granada, Spain.","DOI":"10.1007\/978-3-030-00889-5_2"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yu, L., Wang, S., Li, X., Fu, C.-W., and Heng, P.-A. (2019, January 13\u201317). Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.","DOI":"10.1007\/978-3-030-32245-8_67"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1109\/TNNLS.2020.2995319","article-title":"Transformation-consistent self-ensembling model for semisupervised medical image segmentation","volume":"32","author":"Li","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Luo, X., Chen, J., Song, T., and Wang, G. (2021, January 2\u20139). Semi-supervised medical image segmentation through dual-task consistency. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v35i10.17066"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3031","DOI":"10.1109\/TPAMI.2025.3528453","article-title":"Unimatch v2: Pushing the limit of semi-supervised semantic segmentation","volume":"47","author":"Yang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","unstructured":"Gu, A., and Dao, T. (2024, January 7\u20139). Mamba: Linear-Time Sequence Modeling with Selective State Spaces. Proceedings of the Conference on Language Modeling, Philadelphia, PA, USA."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2461","DOI":"10.1109\/TMI.2020.2972059","article-title":"Recalibrating 3D ConvNets With Project & Excite","volume":"39","author":"Rickmann","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., and Le, Q.V. (2020, January 14\u201319). Randaugment: Practical automated data augmentation with a reduced search space. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Virtual.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, X., Yuan, Y., Zeng, G., and Wang, J. (2021, January 20). Semi-supervised semantic segmentation with cross pseudo supervision. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Yang, L., Qi, L., Feng, L., Zhang, W., and Shi, Y. (2023, January 18\u201322). Revisiting weak-to-strong consistency in semi-supervised semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00699"},{"key":"ref_29","doi-asserted-by":"crossref","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":"ref_30","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Tomography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/3\/33\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:33:49Z","timestamp":1772555629000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/3\/33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":30,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["tomography12030033"],"URL":"https:\/\/doi.org\/10.3390\/tomography12030033","relation":{},"ISSN":["2379-139X"],"issn-type":[{"value":"2379-139X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,3]]}}}