{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:06:48Z","timestamp":1790698008027,"version":"4.1.0"},"reference-count":20,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"content-version":"vor","delay-in-days":3,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Accurate segmentation and classification of cervical spine fractures are essential for timely diagnosis and clinical decision\u2010making in trauma care. Existing deep learning approaches often require extensive manual annotations and struggle to maintain anatomical consistency across vertebral levels, limiting their reliability and generalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose a unified three\u2010stage framework that integrates self\u2010supervised representation learning, structure\u2010aware segmentation, and vertebra\u2010level classification. A bone\u2010window 3D masked autoencoder first pretrains the encoder to learn bone\u2010sensitive volumetric features from unlabeled CT scans. The pretrained encoder is then transferred to a structure\u2010aware 3D U\u2010Net that incorporates bone\u2010likelihood and edge priors with geometry\u2010consistency regularization for anatomically coherent vertebral segmentation. Finally, a vertebra\u2010level classification head performs fracture prediction using ROI features with positional embeddings to encode anatomical context.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Evaluated on the RSNA Cervical Spine Fracture Detection dataset, the proposed method achieved a Dice score of 89.23% for cervical vertebra segmentation. For vertebra\u2010level fracture classification, it achieved an AUC of 0.969 with sensitivity of 0.788 and specificity of 0.962 (macro\u2010averaged across C1\u2013C7), outperforming CNN\u2010 and transformer\u2010based baselines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed framework provides a robust, interpretable, and data\u2010efficient solution for automated cervical spine fracture detection and localization. By combining self\u2010supervised 3D pretraining with anatomy\u2010aware modeling, it offers a practical pathway toward clinically reliable AI\u2010assisted diagnosis in spinal imaging.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/acm2.70575","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T14:01:48Z","timestamp":1777903308000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SpineMAE: A bone\u2010window self\u2010supervised and structure\u2010aware framework for 3D cervical vertebra segmentation and fracture classification"],"prefix":"10.1002","volume":"27","author":[{"given":"Qing","family":"Liang","sequence":"first","affiliation":[{"name":"Hangzhou Medical College Hangzhou Zhejiang Province China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Health Science Center Ningbo University Ningbo China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Yang","sequence":"additional","affiliation":[{"name":"Ningbo No. 2 Hospital Wenzhou Medical University Ningbo China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Shi","sequence":"additional","affiliation":[{"name":"Ningbo No. 2 Hospital Wenzhou Medical University Ningbo China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Song","sequence":"additional","affiliation":[{"name":"College of Science and Technology Ningbo University Ningbo China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianjun","family":"Chen","sequence":"additional","affiliation":[{"name":"Ningbo No. 2 Hospital Wenzhou Medical University Ningbo China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zewen","family":"Shi","sequence":"additional","affiliation":[{"name":"Ningbo No. 2 Hospital Wenzhou Medical University Ningbo China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4218-3764","authenticated-orcid":false,"given":"Qingjiang","family":"Pang","sequence":"additional","affiliation":[{"name":"Hangzhou Medical College Hangzhou Zhejiang Province China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,5,4]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230034"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A8715"},{"key":"e_1_2_11_4_1","doi-asserted-by":"crossref","unstructured":"HungLQ TuanTD HieuNT HungPD.Cervical spine fracture detectionviacomputed tomography scan. InAsian Conference on Intelligent Information and Database Systems Cham Springer Nature Switzerland;2023.","DOI":"10.1007\/978-3-031-42430-4_38"},{"key":"e_1_2_11_5_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA TangY NathV et\u00a0al.Unetr: transformers for 3d medical image segmentation. InProceedings of the IEEE\/CVF winter conference on applications of computer vision;2022.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"e_1_2_11_6_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA NathV TangY YangD RothHR XuD.Swin unetr: swin transformers for semantic segmentation of brain tumors in mri images. InInternational MICCAI Brainlesion Workshop Cham Springer International Publishing;2021.","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"e_1_2_11_7_1","article-title":"nnu\u2010net: self\u2010adapting framework for u\u2010net\u2010based medical image segmentation","author":"Isensee F","year":"2018","journal-title":"arXiv"},{"key":"e_1_2_11_8_1","doi-asserted-by":"crossref","unstructured":"HeK ChenX XieS LiY DollarP GirshickR.Masked autoencoders are scalable vision learners. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;2022.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-024-09581-w"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293771"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17624"},{"key":"e_1_2_11_12_1","article-title":"Topology optimization in medical image segmentation with fast euler characteristic","author":"Li L","year":"2025","journal-title":"IEEE Trans Med Imaging"},{"key":"e_1_2_11_13_1","article-title":"Self pre\u2010training with topology\u2010and spatiality\u2010aware masked autoencoders for 3D medical image segmentation","author":"Gu P","year":"2024","journal-title":"arXiv"},{"key":"e_1_2_11_14_1","article-title":"Mim: mask in mask self\u2010supervised pre\u2010training for 3d medical image analysis","author":"Zhuang J","year":"2025","journal-title":"IEEE Trans Med Imaging"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3404273"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3546345"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","unstructured":"LiuJ DesrosiersC ZhouY.Semi\u2010supervised medical image segmentation using cross\u2010model pseudo\u2010supervision with shape awareness and local context constraints. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention Cham Springer Nature Switzerland;2022.","DOI":"10.1007\/978-3-031-16452-1_14"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2995319"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3359576"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108360"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70575","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acm2.70575","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T15:30:41Z","timestamp":1790695841000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.70575"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":20,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1002\/acm2.70575"],"URL":"https:\/\/doi.org\/10.1002\/acm2.70575","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"2025-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70575"}}