{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T07:45:58Z","timestamp":1791272758955,"version":"4.1.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:00:00Z","timestamp":1743120000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:00:00Z","timestamp":1743120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002551","name":"Seoul National University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Skeletal Radiol"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Objective<\/jats:title>\n            <jats:p>This study aims to establish a large degenerative cervical myelopathy cohort and develop deep learning models for predicting cervical canal stenosis from sagittal T2-weighted MRI.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Materials and methods<\/jats:title>\n            <jats:p>Data was collected retrospectively from patients who underwent a cervical spine MRI from January 2007 to December 2022 at a single institution. Ground truth labels for cervical canal stenosis were obtained from sagittal T2-weighted MRI using Kang\u2019s grade, a four-level scoring system that classifies stenosis with the degree of subarachnoid space obliteration and cord indentation. ResNet50, VGG16, MobileNetV3, and EfficientNetV2 were trained using threefold cross-validation, and the models exhibiting the largest area under the receiver operating characteristic curve (AUC) were selected to produce the ensemble model. Gradient-weighted class activation mapping was adopted for qualitative assessment. Models that incorporate demographic features were trained, and their corresponding AUCs on the test set were evaluated.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>Of 8676 patients, 7645 were eligible for developing deep learning models, where 6880 (mean age, 56.0\u2009\u00b1\u200914.3 years, 3480 men) were used for training while 765 (mean age, 56.5\u2009\u00b1\u200914.4 years, 386 men) were set aside for testing. The ensemble model exhibited the largest AUC of 0.95 (0.94\u20130.97). Accuracy was 0.875 (0.851\u20130.898), sensitivity was 0.885 (0.855\u20130.915), and specificity was 0.861 (0.824\u20130.898). Qualitative analyses demonstrated that the models accurately pinpoint radiologic findings suggestive of cervical canal stenosis and myelopathy. Incorporation of demographic features did not result in a gain of AUC.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>We have developed deep learning models from a large degenerative cervical myelopathy cohort and thoroughly explored their robustness and explainability.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s00256-025-04917-2","type":"journal-article","created":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T15:56:51Z","timestamp":1743350211000},"page":"2067-2076","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Deep learning-based prediction of cervical canal stenosis from mid-sagittal T2-weighted MRI"],"prefix":"10.1007","volume":"54","author":[{"given":"Wounsuk","family":"Rhee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung Cheol","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4500-9653","authenticated-orcid":false,"given":"Hyoungmin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bong-Soon","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sam Yeol","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,28]]},"reference":[{"issue":"12","key":"4917_CR1","doi-asserted-by":"publisher","first-page":"E675","DOI":"10.1097\/BRS.0000000000000913","volume":"30","author":"A Nouri","year":"2015","unstructured":"Nouri A, Tetreault L, Singh A, Karadimas SK, Fehlings MG. Degenerative cervical myelopathy: epidemiology, genetics, and pathogenesis. Spine J. 2015;30(12):E675\u201393. https:\/\/doi.org\/10.1097\/BRS.0000000000000913.","journal-title":"Spine J"},{"key":"4917_CR2","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1038\/s41582-019-0303-0","volume":"16","author":"JH Badhiwala","year":"2020","unstructured":"Badhiwala JH, Ahuja CS, Akbar MA, Martin AR, Kurpad SN, Fehlings MG, et al. Degenerative cervical myelopathy\u2014update and future directions. Nat Rev Neurol. 2020;16:108\u201324. https:\/\/doi.org\/10.1038\/s41582-019-0303-0.","journal-title":"Nat Rev Neurol"},{"key":"4917_CR3","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s00586-013-2781-x","volume":"24","author":"HD Boogaarts","year":"2015","unstructured":"Boogaarts HD, Bartels RHMA. Prevalence of cervical spondylotic myelopathy. Eur Spine J. 2015;24:139\u201341. https:\/\/doi.org\/10.1007\/s00586-013-2781-x.","journal-title":"Eur Spine J"},{"issue":"5","key":"4917_CR4","doi-asserted-by":"publisher","first-page":"710","DOI":"10.31616\/asj.2020.0490","volume":"14","author":"SH Choi","year":"2020","unstructured":"Choi SH, Kang CN. Degenerative cervical myelopathy: pathophysiology and current treatment strategies. Asian Spine J. 2020;14(5):710\u201320. https:\/\/doi.org\/10.31616\/asj.2020.0490.","journal-title":"Asian Spine J"},{"key":"4917_CR5","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1007\/s00256-023-04329-0","volume":"52","author":"S Hesni","year":"2023","unstructured":"Hesni S, Baxter D, Saifuddin A. The imaging of cervical spondylotic myeloradiculopathy. Skeletal Radiol. 2023;52:2341\u201365. https:\/\/doi.org\/10.1007\/s00256-023-04329-0.","journal-title":"Skeletal Radiol"},{"issue":"1","key":"4917_CR6","doi-asserted-by":"publisher","first-page":"W134","DOI":"10.2214\/AJR.10.5560","volume":"197","author":"Y Kang","year":"2011","unstructured":"Kang Y, Lee JW, Koh YH, Kim SJ, Kim JH, Shin Y, et al. New MRI grading system for the cervical canal stenosis. Am J Roentgenol. 2011;197(1):W134\u201340. https:\/\/doi.org\/10.2214\/AJR.10.5560.","journal-title":"Am J Roentgenol"},{"issue":"7","key":"4917_CR7","doi-asserted-by":"publisher","first-page":"e5073","DOI":"10.7759\/cureus.5073","volume":"11","author":"H Waheed","year":"2019","unstructured":"Waheed H, Khan MS, Muneeb A, Jahanzeb S, Ahmad MN. Radiologic assessment of cervical canal stenosis using Kang MRI grading system: do clinical symptoms correlate with imaging findings? Cureus. 2019;11(7):e5073. https:\/\/doi.org\/10.7759\/cureus.5073.","journal-title":"Cureus"},{"key":"4917_CR8","doi-asserted-by":"publisher","first-page":"102444","DOI":"10.1016\/j.media.2022.102444","volume":"79","author":"X Chen","year":"2022","unstructured":"Chen X, Wang X, Zhang K, Li Y, Zhou Z, Liu J, et al. Recent advances and clinical applications of deep learning in medical image analysis. Med Image Anal. 2022;79:102444. https:\/\/doi.org\/10.1016\/j.media.2022.102444.","journal-title":"Med Image Anal"},{"key":"4917_CR9","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.ejrad.2019.02.038","volume":"114","author":"L Saba","year":"2019","unstructured":"Saba L, Biswas M, Kuppili V, Cuadrado-Godia E, Zhang Y, Suri JS, et al. The present and future of deep learning in radiology. J Radiol. 2019;114:14\u201324. https:\/\/doi.org\/10.1016\/j.ejrad.2019.02.038.","journal-title":"J Radiol"},{"issue":"8","key":"4917_CR10","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1097\/BRS.0000000000004595","volume":"48","author":"K Tamai","year":"2023","unstructured":"Tamai K, Terai H, Hoshin M, Nakamura H, Takeuchi K, Yoshimoto M, et al. Deep learning algorithm for identifying cervical cord compression due to degenerative canal stenosis on radiography. Spine J. 2023;48(8):519\u201325. https:\/\/doi.org\/10.1097\/BRS.0000000000004595.","journal-title":"Spine J"},{"issue":"1","key":"4917_CR11","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1186\/s12883-022-02670-w","volume":"22","author":"GW Lee","year":"2022","unstructured":"Lee GW, Shin H, Chang MC. Deep learning algorithm to evaluate cervical spondylotic myelopathy using lateral cervical spine radiograph. BMC Neurol. 2022;22(1):147. https:\/\/doi.org\/10.1186\/s12883-022-02670-w.","journal-title":"BMC Neurol"},{"issue":"1","key":"4917_CR12","doi-asserted-by":"publisher","first-page":"10473","DOI":"10.1038\/s41598-021-89848-3","volume":"11","author":"Z Merali","year":"2021","unstructured":"Merali Z, Wang JZ, Badhiwala JH, Witiw CD, Wilson JR, Fehlings MG. A deep learning model for detection of cervical spinal cord compression in MRI scans. Sci Rep. 2021;11(1):10473. https:\/\/doi.org\/10.1038\/s41598-021-89848-3.","journal-title":"Sci Rep"},{"key":"4917_CR13","doi-asserted-by":"publisher","unstructured":"Lee A, Wu J, Liu C, Zhang Y, Chen B, Wang X, et al. Deep learning model for automated diagnosis of degenerative cervical spondylosis and altered spinal cord signal on MRI. Spine J. (in press). https:\/\/doi.org\/10.1016\/j.spinee.2024.09.015","DOI":"10.1016\/j.spinee.2024.09.015"},{"issue":"3","key":"4917_CR14","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1148\/radiol.2021204731","volume":"301","author":"CMW Goedmakers","year":"2021","unstructured":"Goedmakers CMW, Lak AM, Duey AH, Smith TR, Johnson RD, Fehlings MG, et al. Deep learning for adjacent segment disease at preoperative MRI for cervical radiculopathy. Radiol. 2021;301(3):664\u201371. https:\/\/doi.org\/10.1148\/radiol.2021204731.","journal-title":"Radiol"},{"issue":"11","key":"4917_CR15","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.3390\/bioengineering11111082","volume":"11","author":"HR Lee","year":"2024","unstructured":"Lee HR, Rhee W, Chang SY, Chang BS, Kim H. Deep learning in spinal endoscopy: U-net models for neural tissue detection. Bioeng. 2024;11(11):1082. https:\/\/doi.org\/10.3390\/bioengineering11111082.","journal-title":"Bioeng"},{"key":"4917_CR16","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis. 2020;128:336\u201359. https:\/\/doi.org\/10.1007\/s11263-019-01228-7.","journal-title":"Int J Comput Vis"},{"key":"4917_CR17","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume":"2016","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J, Deep residual learning for image recognition. In,. IEEE Conf Comput Vis Pattern Recognit (CVPR); Las Vegas, NV. USA. 2016;2016:770\u20138. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","journal-title":"USA"},{"key":"4917_CR18","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. Published September 4, 2014. Updated April 10, 2015. Accessed November 18, 2024. Available from: https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"4917_CR19","doi-asserted-by":"publisher","unstructured":"Howard A, Sandler M, Chu G, Chen L, Chen B, Tan M, et al. (2019) Searching for MobileNetV3. In: 2019 IEEE\/CVF Int Conf Comput Vis (ICCV); Seoul, South Korea. 2019. 1314-1324https:\/\/doi.org\/10.1109\/ICCV.2019.00140","DOI":"10.1109\/ICCV.2019.00140"},{"key":"4917_CR20","unstructured":"Tan M, Le Q. EfficientNetV2: smaller models and faster training. arXiv preprint arXiv:2104.00298. Published April 1, 2021. Updated June 23, 2021. Accessed November 18, 2024. Available from: https:\/\/arxiv.org\/abs\/2104.00298"},{"issue":"10","key":"4917_CR21","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1016\/j.ccell.2022.09.012","volume":"40","author":"J Lipkova","year":"2022","unstructured":"Lipkova J, Chen RJ, Chen B, Liu X, Wang L, Yu KH, et al. Artificial intelligence for multimodal data integration in oncology. Cancer Cell. 2022;40(10):1095\u2013110. https:\/\/doi.org\/10.1016\/j.ccell.2022.09.012.","journal-title":"Cancer Cell"},{"issue":"1","key":"4917_CR22","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1038\/s41746-022-00689-4","volume":"5","author":"LR Soenksen","year":"2022","unstructured":"Soenksen LR, Ma Y, Zeng C, Escamilla V, Hernandez-Boussard T, Patel BN, et al. Integrated multimodal artificial intelligence framework for healthcare applications. NPJ Digit Med. 2022;5(1):149. https:\/\/doi.org\/10.1038\/s41746-022-00689-4.","journal-title":"NPJ Digit Med"},{"key":"4917_CR23","doi-asserted-by":"publisher","unstructured":"Maturana D, Scherer S (2015) VoxNet: a 3D convolutional neural network for real-time object recognition. In: 2015 IEEE\/RSJ Int Conf Intell Robots Syst (IROS); Hamburg, Germany. 2015. 922-928https:\/\/doi.org\/10.1109\/IROS.2015.7353481","DOI":"10.1109\/IROS.2015.7353481"}],"container-title":["Skeletal Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00256-025-04917-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00256-025-04917-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00256-025-04917-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T20:02:03Z","timestamp":1755547323000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00256-025-04917-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,28]]},"references-count":23,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["4917"],"URL":"https:\/\/doi.org\/10.1007\/s00256-025-04917-2","relation":{},"ISSN":["0364-2348","1432-2161"],"issn-type":[{"value":"0364-2348","type":"print"},{"value":"1432-2161","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,28]]},"assertion":[{"value":"13 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and\/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. Approval from the Institutional Review Board was obtained, and a waiver of informed consent was obtained following the retrospective nature of the study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}