{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T15:28:03Z","timestamp":1794324483985,"version":"4.9.0"},"reference-count":32,"publisher":"Journal of Neurosurgery Publishing Group (JNSPG)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,22]]},"abstract":"<jats:sec>\n                    <jats:title>OBJECTIVE<\/jats:title>\n                    <jats:p>This study aimed to develop a deep learning (DL) model for the detection of cervical spinal cord compression on cervical radiographs and compare its performance with spine surgeons.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>The authors conducted a retrospective study on consecutive hospitalized patients who underwent cervical spine radiography and MRI at their center. Data from 600 patients were randomly divided into the training (n = 480), validation (n = 60), and internal test (n = 60) sets. Additionally, patients from another center were included as an external test set (n = 60). MR images were used as the gold standard for determining the presence of cervical segmental compression. The model was trained on cervical radiographs, where a segmentation-based localization algorithm was first developed to identify cervical segments, followed by a binary classification to diagnose spinal cord compression. Furthermore, the gradient-weighted class activation mapping (Grad-CAM) was used to visualize the area with high feature densities extracted by the model. Model performance was evaluated based on accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC), and compared to the diagnoses of two spine surgeons.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>In the internal test set, the model achieved 94.67% accuracy and an AUC of 0.9911, significantly outperforming the two spine surgeons (69.09% and 71.18% accuracy, p &lt; 0.05). In the external test set, the model achieved 93.33% accuracy with an AUC of 0.9868. Compared to the reference standard, the kappa coefficients for the model, reader 1, and reader 2 were 0.893, 0.378, and 0.422, respectively. Grad-CAM showed high feature density in the intervertebral discs, intervertebral foramina, and facet joints.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSIONS<\/jats:title>\n                    <jats:p>The DL model developed in this study achieved binary classification of cervical spinal cord compression and localized the affected segments on cervical radiographs, demonstrating superior diagnostic performance to that of spine surgeons. This DL model ensures high detection rates for cervical spinal cord compression and holds promise for clinical diagnosis, particularly in resource-limited or remote settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3171\/2026.1.spine251409","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T14:52:30Z","timestamp":1779288750000},"page":"277-286","source":"Crossref","is-referenced-by-count":1,"title":["Performance comparison between a deep learning model and spine surgeons in detecting cervical spinal cord compression on radiographs"],"prefix":"10.3171","volume":"45","author":[{"given":"Ruiyuan","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghui","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing;"},{"name":"Longwood Valley Medical Technology Co. Ltd., Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing;"},{"name":"School of Life Sciences, Tsinghua University, Beijing;"},{"name":"Institute of Biomedical and Health Engineering (iBHE), Tsinghua Shenzhen International Graduate School, Shenzhen; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aobo","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqian","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Xi","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Gu","sequence":"additional","affiliation":[{"name":"Longwood Valley Medical Technology Co. Ltd., Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Fei","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Friendship Hospital, Capital Medical University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zang","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, Beijing Chaoyang Hospital, Capital Medical University, Beijing;"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1754","reference":[{"key":"b1","series-title":"BMJ","first-page":"k186","article-title":"Degenerative cervical myelopathy","volume":"360","author":"Davies BM","year":"2018","unstructured":"Davies BM, Mowforth OD, Smith EK, Kotter MR. Degenerative cervical myelopathy. BMJ. 2018;360:k186. doi:10.1136\/bmj.k186"},{"issue":"Suppl 2","key":"b2","series-title":"Eur Spine J","first-page":"139","article-title":"Prevalence of cervical spondylotic myelopathy","volume":"24","author":"Boogaarts HD","year":"2015","unstructured":"Boogaarts HD, Bartels RHMA. Prevalence of cervical spondylotic myelopathy. Eur Spine J. 2015;24 Suppl 2:139\u2013141. doi:10.1007\/s00586-013-2781-x"},{"issue":"2","key":"b3","series-title":"J Am Board Fam Med","first-page":"303","article-title":"Cervical spondylotic myelopathy: a guide to diagnosis and management","volume":"33","author":"McCormick JR","year":"2020","unstructured":"McCormick JR, Sama AJ, Schiller NC, Butler AJ, Donnally CJ. Cervical spondylotic myelopathy: a guide to diagnosis and management. J Am Board Fam Med. 2020;33(2):303\u2013313. doi:10.3122\/jabfm.2020.02.190195"},{"issue":"1","key":"b4","series-title":"Eur J Neurol","first-page":"15","article-title":"Degenerative cervical radiculopathy: diagnosis and conservative treatment. A review","volume":"16","author":"Kuijper B","year":"2009","unstructured":"Kuijper B, Tans JTJ, Schimsheimer RJ,  Degenerative cervical radiculopathy: diagnosis and conservative treatment. A review. Eur J Neurol. 2009;16(1):15\u201320. doi:10.1111\/j.1468-1331.2008.02365.x"},{"issue":"8","key":"b5","series-title":"Spine (Phila Pa 1976)","first-page":"519","article-title":"Deep learning algorithm for identifying cervical cord compression due to degenerative canal stenosis on radiography","volume":"48","author":"Tamai K","year":"2023","unstructured":"Tamai K, Terai H, Hoshino M,  Deep learning algorithm for identifying cervical cord compression due to degenerative canal stenosis on radiography. Spine (Phila Pa 1976). 2023;48(8):519\u2013525. doi:10.1097\/BRS.0000000000004595"},{"issue":"1","key":"b6","series-title":"Eur Radiol Exp","first-page":"35","article-title":"Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine","volume":"2","author":"Pesapane F","year":"2018","unstructured":"Pesapane F, Codari M, Sardanelli F. Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine. Eur Radiol Exp. 2018;2(1):35. doi:10.1186\/s41747-018-0061-6"},{"issue":"1","key":"b7","series-title":"Diagn Interv Imaging","first-page":"5","article-title":"Artificial intelligence in interventional radiology: current concepts and future trends","volume":"106","author":"Lesaunier A","year":"2025","unstructured":"Lesaunier A, Khlaut J, Dancette C, Tselikas L, Bonnet B, Boeken T. Artificial intelligence in interventional radiology: current concepts and future trends. Diagn Interv Imaging. 2025;106(1):5\u201310. doi:10.1016\/j.diii.2024.08.004"},{"issue":"2","key":"b8","series-title":"Radiographics","first-page":"505","article-title":"Machine learning for medical imaging","volume":"37","author":"Erickson BJ","year":"2017","unstructured":"Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. Radiographics. 2017;37(2):505\u2013515. doi:10.1148\/rg.2017160130"},{"issue":"1","key":"b9","series-title":"Curr Rev Musculoskelet Med","first-page":"69","article-title":"Machine learning and artificial intelligence: definitions, applications, and future directions","volume":"13","author":"Helm JM","year":"2020","unstructured":"Helm JM, Swiergosz AM, Haeberle HS,  Machine learning and artificial intelligence: definitions, applications, and future directions. Curr Rev Musculoskelet Med. 2020;13(1):69\u201376. doi:10.1007\/s12178-020-09600-8"},{"issue":"2","key":"b10","series-title":"Transl Vis Sci Technol","first-page":"14","article-title":"Introduction to machine learning, neural networks, and deep learning","volume":"9","author":"Choi RY","year":"2020","unstructured":"Choi RY, Coyner AS, Kalpathy-Cramer J, Chiang MF, Campbell JP. Introduction to machine learning, neural networks, and deep learning. Transl Vis Sci Technol. 2020;9(2):14. doi:10.1167\/tvst.9.2.14"},{"key":"b11","series-title":"Med Image Anal","first-page":"102444","article-title":"Recent advances and clinical applications of deep learning in medical image analysis","volume":"79","author":"Chen X","year":"2022","unstructured":"Chen X, Wang X, Zhang K,  Recent advances and clinical applications of deep learning in medical image analysis. Med Image Anal. 2022;79:102444. doi:10.1016\/j.media.2022.102444"},{"issue":"1","key":"b12","series-title":"NPJ Digit Med","first-page":"65","article-title":"Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis","volume":"4","author":"Aggarwal R","year":"2021","unstructured":"Aggarwal R, Sounderajah V, Martin G,  Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis. NPJ Digit Med. 2021;4(1):65. doi:10.1038\/s41746-021-00438-z"},{"issue":"4","key":"b13","series-title":"Insights Imaging","first-page":"611","article-title":"Convolutional neural networks: an overview and application in radiology","volume":"9","author":"Yamashita R","year":"2018","unstructured":"Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging. 2018;9(4):611\u2013629. doi:10.1007\/s13244-018-0639-9"},{"issue":"3","key":"b14","series-title":"Radiology","first-page":"590","article-title":"Convolutional neural networks for radiologic images: a radiologist\u2019s guide","volume":"290","author":"Soffer S","year":"2019","unstructured":"Soffer S, Ben-Cohen A, Shimon O, Amitai MM, Greenspan H, Klang E. Convolutional neural networks for radiologic images: a radiologist\u2019s guide. Radiology. 2019;290(3):590\u2013606. doi:10.1148\/radiol.2018180547"},{"issue":"1","key":"b15","series-title":"J Neurosurg Spine","first-page":"104","article-title":"Diagnostic triage in patients with central lumbar spinal stenosis using a deep learning system of radiographs","volume":"37","author":"Kim T","year":"2022","unstructured":"Kim T, Kim YG, Park S,  Diagnostic triage in patients with central lumbar spinal stenosis using a deep learning system of radiographs. J Neurosurg Spine. 2022;37(1):104\u2013111. doi:10.3171\/2021.11.SPINE211136"},{"issue":"11","key":"b16","series-title":"Spine J","first-page":"2086","article-title":"Deep learning-based detection of lumbar spinal canal stenosis using convolutional neural networks","volume":"24","author":"Suzuki H","year":"2024","unstructured":"Suzuki H, Kokabu T, Yamada K,  Deep learning-based detection of lumbar spinal canal stenosis using convolutional neural networks. Spine J. 2024;24(11):2086\u20132101. doi:10.1016\/j.spinee.2024.06.009"},{"key":"b17","series-title":"J Med Internet Res","first-page":"e54676","article-title":"Machine learning and deep learning for diagnosis of lumbar spinal stenosis: systematic review and meta-analysis","volume":"26","author":"Wang T","year":"2024","unstructured":"Wang T, Chen R, Fan N,  Machine learning and deep learning for diagnosis of lumbar spinal stenosis: systematic review and meta-analysis. J Med Internet Res. 2024;26:e54676. doi:10.2196\/54676"},{"issue":"1","key":"b18","series-title":"BMC Neurol","first-page":"147","article-title":"Deep learning algorithm to evaluate cervical spondylotic myelopathy using lateral cervical spine radiograph","volume":"22","author":"Lee GW","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. doi:10.1186\/s12883-022-02670-w"},{"key":"b19","series-title":"BMJ","first-page":"g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins GS","year":"2015","unstructured":"Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. 2015;350:g7594. doi:10.1136\/bmj.g7594"},{"issue":"1","key":"b20","series-title":"AJR Am J Roentgenol","first-page":"W134","article-title":"New MRI grading system for the cervical canal stenosis","volume":"197","author":"Kang Y","year":"2011","unstructured":"Kang Y, Lee JW, Koh YH,  New MRI grading system for the cervical canal stenosis. AJR Am J Roentgenol. 2011;197(1):W134\u2013W140. doi:10.2214\/AJR.10.5560"},{"issue":"13","key":"b21","series-title":"Sensors (Basel)","first-page":"4166","article-title":"A comprehensive review of explainable artificial intelligence (XAI) in computer vision","volume":"25","author":"Cheng Z","year":"2025","unstructured":"Cheng Z, Wu Y, Li Y, Cai L, Ihnaini B. A comprehensive review of explainable artificial intelligence (XAI) in computer vision. Sensors (Basel). 2025;25(13):4166. doi:10.3390\/s25134166"},{"issue":"22 Suppl 1","key":"b22","series-title":"Spine (Phila Pa 1976)","first-page":"S21","article-title":"Pathophysiology and natural history of cervical spondylotic myelopathy.","volume":"38","author":"Karadimas SK","year":"2013","unstructured":"Karadimas SK, Erwin WM, Ely CG, Dettori JR, Fehlings MG. Pathophysiology and natural history of cervical spondylotic myelopathy. Spine (Phila Pa 1976). 2013;38(22 Suppl 1):S21\u2013S36. doi:10.1097\/BRS.0b013e3182a7f2c3"},{"issue":"2","key":"b23","series-title":"N Engl J Med","first-page":"159","article-title":"Degenerative cervical spondylosis","volume":"383","author":"Theodore N","year":"2020","unstructured":"Theodore N. Degenerative cervical spondylosis. N Engl J Med. 2020;383(2):159\u2013168. doi:10.1056\/NEJMra2003558"},{"issue":"2","key":"b24","series-title":"J Orthop Surg (Hong Kong)","first-page":"239","article-title":"Correlation between magnetic resonance imaging and radiographic measurement of cervical spine in cervical myelopathic patients","volume":"12","author":"Wong TM","year":"2004","unstructured":"Wong TM, Leung HB, Wong WC. Correlation between magnetic resonance imaging and radiographic measurement of cervical spine in cervical myelopathic patients. J Orthop Surg (Hong Kong). 2004;12(2):239\u2013242. doi:10.1177\/230949900401200220"},{"key":"b25","series-title":"Brain Spine","first-page":"101666","article-title":"Machine learning for image analysis in the cervical spine: systematic review of the available models and methods","volume":"2","author":"Goedmakers CMW","year":"2022","unstructured":"Goedmakers CMW, Pereboom LM, Schoones JW,  Machine learning for image analysis in the cervical spine: systematic review of the available models and methods. Brain Spine. 2022;2:101666. doi:10.1016\/j.bas.2022.101666"},{"issue":"1","key":"b26","series-title":"PLoS One","first-page":"e0262838","article-title":"Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks","volume":"17","author":"Rajaraman S","year":"2022","unstructured":"Rajaraman S, Ganesan P, Antani S. Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks. PLoS One. 2022;17(1):e0262838. doi:10.1371\/journal.pone.0262838"},{"issue":"7553","key":"b27","series-title":"Nature","first-page":"436","article-title":"Deep learning","volume":"521","author":"LeCun Y","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015 May 28;521(7553):436\u2013444. doi:10.1038\/nature14539"},{"issue":"19","key":"b28","series-title":"Phys Med Biol","first-page":"195015","article-title":"Multi-view radiomics and dosiomics analysis with machine learning for predicting acute-phase weight loss in lung cancer patients treated with radiotherapy","volume":"65","author":"Lee SH","year":"2020","unstructured":"Lee SH, Han P, Hales RK,  Multi-view radiomics and dosiomics analysis with machine learning for predicting acute-phase weight loss in lung cancer patients treated with radiotherapy. Phys Med Biol. 2020;65(19):195015. doi:10.1088\/1361-6560\/ab8531"},{"key":"b29","series-title":"Front Public Health","first-page":"307","article-title":"Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice","volume":"5","author":"Trevethan R","year":"2017","unstructured":"Trevethan R. Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice. Front Public Health. 2017;5:307. doi:10.3389\/fpubh.2017.00307"},{"issue":"22 Suppl 1","key":"b30","series-title":"Spine (Phila Pa 1976)","first-page":"S19","article-title":"Symptomatic progression of cervical myelopathy and the role of nonsurgical management: a consensus statement","volume":"38","author":"Fehlings MG","year":"2013","unstructured":"Fehlings MG, Wilson JR, Yoon ST, Rhee JM, Shamji MF, Lawrence BD. Symptomatic progression of cervical myelopathy and the role of nonsurgical management: a consensus statement. Spine (Phila Pa 1976). 2013;38(22 Suppl 1):S19\u2013S20. doi:10.1097\/BRS.0b013e3182a7f4de"},{"issue":"1","key":"b31","series-title":"NPJ Digit Med","first-page":"26","article-title":"The impact of inconsistent human annotations on AI driven clinical decision making","volume":"6","author":"Sylolypavan A","year":"2023","unstructured":"Sylolypavan A, Sleeman D, Wu H, Sim M. The impact of inconsistent human annotations on AI driven clinical decision making. NPJ Digit Med. 2023;6(1):26. doi:10.1038\/s41746-023-00773-3"},{"issue":"7","key":"b32","series-title":"J Am Med Inform Assoc","first-page":"1596","article-title":"Deep learning with noisy labels in medical prediction problems: a scoping review","volume":"31","author":"Wei Y","year":"2024","unstructured":"Wei Y, Deng Y, Sun C, Lin M, Jiang H, Peng Y. Deep learning with noisy labels in medical prediction problems: a scoping review. J Am Med Inform Assoc. 2024;31(7):1596\u20131607. doi:10.1093\/jamia\/ocae108"}],"container-title":["Journal of Neurosurgery: Spine"],"original-title":[],"link":[{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg-spine\/45\/2\/article-p277.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg-spine\/45\/2\/article-p277.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg-spine\/45\/2\/article-p277.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T15:20:39Z","timestamp":1794324039000},"score":1,"resource":{"primary":{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg-spine\/45\/2\/article-p277.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":32,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3171\/2026.1.spine251409","relation":{},"ISSN":["1547-5654"],"issn-type":[{"value":"1547-5654","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5,22]]}}}