{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T20:04:49Z","timestamp":1787169889598,"version":"build-2736575974"},"reference-count":26,"publisher":"Journal of Neurosurgery Publishing Group (JNSPG)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,1]]},"abstract":"\n OBJECTIVE<\/jats:title>\n Magnetic resonance imaging (MRI) is the gold-standard tool for diagnosing lumbar spinal stenosis (LSS), but it is difficult to promptly examine all suspected cases with MRI considering the modality\u2019s high cost and limited accessibility. Although radiography is an efficient screening technique owing to its low cost, rapid operability, and wide availability, its diagnostic accuracy is relatively poor. In this study, the authors aimed to develop a deep learning model with a convolutional neural network (CNN) for diagnosing severe central LSS using radiography and to evaluate radiological diagnostic features using gradient-weighted class activation mapping (Grad-CAM).<\/jats:p>\n <\/jats:sec>\n \n METHODS<\/jats:title>\n Patients who had undergone both spinal MRI and radiography in the period from May 1, 2005, to December 31, 2017, were screened. According to the formal MRI report, participants were consecutively included in the severe central LSS or healthy control group, and radiographs for both groups were collected. A CNN-based transfer learning algorithm was developed to classify radiographic findings as LSS or normal (binary classification). The proposed models were evaluated using six performance metrics: area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, and positive and negative predictive values.<\/jats:p>\n <\/jats:sec>\n \n RESULTS<\/jats:title>\n The VGG19 model achieved the highest accuracy with an AUROC of 90.0% (95% CI 89.8%\u201390.3%) by training 12,442 images. Accuracy was 82.8% (95% CI 82.5%\u201383.1%) by averaging 5-fold models. Feature points on Grad-CAM were reasonable, and the features could be categorized into reduced disc height, narrow foramina, short pedicle, and hyperdense facet joint. The AUROC in the extra validation was 89.3% (95% CI 88.7%\u201390.0%). Accuracy was 81.8% (95% CI 80.6%\u201383.0%) by averaging 5-fold models. Multivariate logistic regression analysis showed that a combination of demographic factors (age and sex) did not improve the model performance.<\/jats:p>\n <\/jats:sec>\n \n CONCLUSIONS<\/jats:title>\n The algorithm trained by a CNN to identify central LSS on radiographs showed high diagnostic accuracy and is expected to be useful as a triage tool. The algorithm could accurately localize the stenotic lesion to assist physicians in the identification of LSS.<\/jats:p>\n <\/jats:sec>","DOI":"10.3171\/2021.11.spine211136","type":"journal-article","created":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T02:20:02Z","timestamp":1643336402000},"page":"104-111","source":"Crossref","is-referenced-by-count":24,"title":["Diagnostic triage in patients with central lumbar spinal stenosis using a deep learning system of radiographs"],"prefix":"10.3171","volume":"37","author":[{"given":"Tackeun","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, Seoul National University Bundang Hospital, Seongnam;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young-Gon","family":"Kim","sequence":"additional","affiliation":[{"name":"Transdisciplinary Department of Medicine & Advanced Technology, Seoul National University Hospital, Seoul;"},{"name":"AI Institute, Seoul National University, Seoul;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seyeon","family":"Park","sequence":"additional","affiliation":[{"name":"Transdisciplinary Department of Medicine & Advanced Technology, Seoul National University Hospital, Seoul;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae-Koo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Seoul National University Bundang Hospital, Seongnam;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Hyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Seoul National University Bundang Hospital, Seongnam;"},{"name":"Department of Neurosurgery, Seoul National University Hospital, Seoul;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung-Jae","family":"Hyun","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Seoul National University Bundang Hospital, Seongnam;"},{"name":"Seoul National University College of Medicine, Seoul; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi Heon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Seoul National University Hospital, Seoul;"},{"name":"Seoul National University College of Medicine, Seoul; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ki-Jeong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Seoul National University Bundang Hospital, Seongnam;"},{"name":"Seoul National University College of Medicine, Seoul; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun Kee","family":"Chung","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Seoul National University Hospital, Seoul;"},{"name":"Seoul National University College of Medicine, Seoul; and"},{"name":"Department of Brain and Cognitive Sciences, Seoul National University College of Natural Sciences, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1754","reference":[{"key":"b1","series-title":"Eur J Radiol","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.ejrad.2019.02.023","article-title":"Qualitative versus quantitative lumbar spinal stenosis grading by machine learning supported texture analysis-Experience from the LSOS study cohort","volume":"114","author":"Huber FA","year":"2019","unstructured":"Huber FA, Stutz S, Vittoria de Martini I, Qualitative versus quantitative lumbar spinal stenosis grading by machine learning supported texture analysis-Experience from the LSOS study cohort. Eur J Radiol. 2019;114:45\u201350.3100517510.1016\/j.ejrad.2019.02.023"},{"issue":"1","key":"b2","series-title":"Neurospine","doi-asserted-by":"publisher","first-page":"66","DOI":"10.14245\/ns.1836038.019","article-title":"Health care burden of spinal diseases in the Republic of Korea: analysis of a nationwide database from 2012 through 2016","volume":"15","author":"Lee CH","year":"2018","unstructured":"Lee CH, Chung CK, Kim CH, Kwon JW. Health care burden of spinal diseases in the Republic of Korea: analysis of a nationwide database from 2012 through 2016. Neurospine. 2018;15(1):66\u201376.2965662410.14245\/ns.1836038.019"},{"issue":"8","key":"b3","series-title":"Clin Radiol","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1053\/crad.2000.0223","article-title":"The imaging of lumbar spinal stenosis","volume":"55","author":"Saifuddin A","year":"2000","unstructured":"Saifuddin A. The imaging of lumbar spinal stenosis. Clin Radiol. 2000;55(8):581\u2013594.1096472810.1053\/crad.2000.0223"},{"issue":"3","key":"b4","series-title":"Vet Radiol Ultrasound","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1111\/j.1740-8261.2002.tb00994.x","article-title":"Accuracy of survey radiographic diagnosis of intervertebral disc protrusion in dogs","volume":"43","author":"Lamb CR","year":"2002","unstructured":"Lamb CR, Nicholls A, Targett M, Mannion P. Accuracy of survey radiographic diagnosis of intervertebral disc protrusion in dogs. Vet Radiol Ultrasound. 2002;43(3):222\u2013228.1208831510.1111\/j.1740-8261.2002.tb00994.x"},{"issue":"1","key":"b5","series-title":"NPJ Digit Med","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41746-021-00438-z","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):65.3382821710.1038\/s41746-021-00438-z"},{"issue":"4","key":"b6","series-title":"Neurospine","doi-asserted-by":"publisher","first-page":"705","DOI":"10.14245\/ns.1938388.194","article-title":"Internet of things, digital biomarker, and artificial intelligence in spine: current and future perspectives","volume":"16","author":"Nam KH","year":"2019","unstructured":"Nam KH, Kim DH, Choi BK, Han IH. Internet of things, digital biomarker, and artificial intelligence in spine: current and future perspectives. Neurospine. 2019;16(4):705\u2013711.3190546110.14245\/ns.1938388.194"},{"issue":"8","key":"b7","series-title":"Skeletal Radiol","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1007\/s00256-011-1153-z","article-title":"A new grading system of lumbar central canal stenosis on MRI: an easy and reliable method","volume":"40","author":"Lee GY","year":"2011","unstructured":"Lee GY, Lee JW, Choi HS, Oh KJ, Kang HS. A new grading system of lumbar central canal stenosis on MRI: an easy and reliable method. Skeletal Radiol. 2011;40(8):1033\u20131039.2128671410.1007\/s00256-011-1153-z"},{"key":"b8","series-title":"In: Proceedings of the 29th IEEE International Conference on Computer Vision and Pattern Recognition.","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He K","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the 29th IEEE International Conference on Computer Vision and Pattern Recognition.IEEE;2016:770\u2013778."},{"key":"b9","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan K","year":"2014","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv. Preprint posted online September 4,2014.doi:1409.1556"},{"key":"b10","series-title":"In: Proceedings of the 36th International Conference on Machine Learning, PMLR 97.","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan M","year":"2019","unstructured":"Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning, PMLR 97.PMLR;2019:6105\u20136114."},{"key":"b11","series-title":"In: Proceedings of the 29th IEEE International Conference on Computer Vision and Pattern Recognition.","first-page":"2921","article-title":"Learning deep features for discriminative localization","author":"Zhou B","year":"2016","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. In: Proceedings of the 29th IEEE International Conference on Computer Vision and Pattern Recognition.IEEE;2016:2921\u20132929."},{"key":"b12","series-title":"In: Proceedings of the 2017 IEEE International Conference on Computer Vision.","first-page":"618","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju RR","year":"2017","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the 2017 IEEE International Conference on Computer Vision.IEEE;2017:618\u2013626."},{"key":"b13","series-title":"EBioMedicine","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1016\/j.ebiom.2018.12.043","article-title":"Machine learning for detecting moyamoya disease in plain skull radiography using a convolutional neural network","volume":"40","author":"Kim T","year":"2019","unstructured":"Kim T, Heo J, Jang DK, Machine learning for detecting moyamoya disease in plain skull radiography using a convolutional neural network. EBioMedicine. 2019;40:636\u2013642.3059837210.1016\/j.ebiom.2018.12.043"},{"issue":"4","key":"b14","series-title":"Emerg Radiol","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/s10140-020-01767-4","article-title":"Can AI outperform a junior resident? Comparison of deep neural network to first-year radiology residents for identification of pneumothorax","volume":"27","author":"Yi PH","year":"2020","unstructured":"Yi PH, Kim TK, Yu AC, Bennett B, Eng J, Lin CT. Can AI outperform a junior resident? Comparison of deep neural network to first-year radiology residents for identification of pneumothorax. Emerg Radiol. 2020;27(4):367\u2013375.10.1007\/s10140-020-01767-4"},{"issue":"1","key":"b15","series-title":"Health Inf Sci Syst","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s13755-020-00135-3","article-title":"Classification of COVID-19 chest X-rays with deep learning: new models or fine tuning?","volume":"9","author":"Pham TD","year":"2020","unstructured":"Pham TD. Classification of COVID-19 chest X-rays with deep learning: new models or fine tuning?. Health Inf Sci Syst. 2020;9(1):2.10.1007\/s13755-020-00135-3"},{"issue":"4","key":"b16","series-title":"Clin Rheumatol","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1007\/s10067-019-04487-4","article-title":"Detection of rheumatoid arthritis from hand radiographs using a convolutional neural network","volume":"39","author":"\u00dcreten K","year":"2020","unstructured":"\u00dcreten K, Erbay H, Mara\u015f HH. Detection of rheumatoid arthritis from hand radiographs using a convolutional neural network. Clin Rheumatol. 2020;39(4):969\u2013974.3085096210.1007\/s10067-019-04487-4"},{"issue":"4","key":"b17","series-title":"Neurospine","doi-asserted-by":"publisher","first-page":"637","DOI":"10.14245\/ns.1938410.205","article-title":"Artificial intelligence and the future of spine surgery","volume":"16","author":"Joshi RS","year":"2019","unstructured":"Joshi RS, Lau D, Ames CP. Artificial intelligence and the future of spine surgery. Neurospine. 2019;16(4):637\u2013639.3190545010.14245\/ns.1938410.205"},{"issue":"4","key":"b18","series-title":"Neurospine","doi-asserted-by":"publisher","first-page":"640","DOI":"10.14245\/ns.1938404.202","article-title":"Artificial intelligence in neurosurgery: a comment on the possibilities","volume":"16","author":"Perez-Breva L","year":"2019","unstructured":"Perez-Breva L, Shin JH. Artificial intelligence in neurosurgery: a comment on the possibilities. Neurospine. 2019;16(4):640\u2013642.3190545110.14245\/ns.1938404.202"},{"issue":"4","key":"b19","series-title":"Neurospine","doi-asserted-by":"publisher","first-page":"643","DOI":"10.14245\/ns.1938386.193","article-title":"Applications of machine learning using electronic medical records in spine surgery","volume":"16","author":"Schwartz JT","year":"2019","unstructured":"Schwartz JT, Gao M, Geng EA, Mody KS, Mikhail CM, Cho SK. Applications of machine learning using electronic medical records in spine surgery. Neurospine. 2019;16(4):643\u2013653.3190545210.14245\/ns.1938386.193"},{"issue":"4","key":"b20","series-title":"Neurospine","doi-asserted-by":"publisher","first-page":"657","DOI":"10.14245\/ns.1938396.198","article-title":"Deep learning in medical imaging","volume":"16","author":"Kim M","year":"2019","unstructured":"Kim M, Yun J, Cho Y, Deep learning in medical imaging. Neurospine. 2019;16(4):657\u2013668.3190545410.14245\/ns.1938396.198"},{"issue":"9","key":"b21","series-title":"Appl Sci (Basel)","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.3390\/app8091656","article-title":"Fine-grain segmentation of the intervertebral discs from MR spine images using deep convolutional neural networks: BSU-Net","volume":"8","author":"Kim S","year":"2018","unstructured":"Kim S, Bae WC, Masuda K, Chung CB, Hwang D. Fine-grain segmentation of the intervertebral discs from MR spine images using deep convolutional neural networks: BSU-Net. Appl Sci (Basel). 2018;8(9):1656.10.3390\/app8091656"},{"key":"b22","series-title":"Comput Math Methods Med","doi-asserted-by":"publisher","first-page":"6357171","DOI":"10.1155\/2019\/6357171","article-title":"Cobb angle measurement of spine from x-ray images using convolutional neural network","volume":"2019","author":"Horng MH","year":"2019","unstructured":"Horng MH, Kuok CP, Fu MJ, Lin CJ, Sun YN. Cobb angle measurement of spine from x-ray images using convolutional neural network. Comput Math Methods Med. 2019;2019:6357171.3099673110.1155\/2019\/6357171"},{"issue":"11","key":"b23","series-title":"J Clin Med","doi-asserted-by":"publisher","first-page":"E1826","DOI":"10.3390\/jcm8111826","article-title":"Artificial intelligence for automatic measurement of sagittal vertical axis using ResUNet framework","volume":"8","author":"Weng CH","year":"2019","unstructured":"Weng CH, Wang CL, Huang YJ, Artificial intelligence for automatic measurement of sagittal vertical axis using ResUNet framework. J Clin Med. 2019;8(11):E1826.3168391310.3390\/jcm8111826"},{"issue":"4","key":"b24","series-title":"Neurospine","doi-asserted-by":"publisher","first-page":"686","DOI":"10.14245\/ns.1938414.207","article-title":"Artificial intelligence for adult spinal deformity","volume":"16","author":"Joshi RS","year":"2019","unstructured":"Joshi RS, Haddad AF, Lau D, Ames CP. Artificial intelligence for adult spinal deformity. Neurospine. 2019;16(4):686\u2013694.3190545710.14245\/ns.1938414.207"},{"issue":"12","key":"b25","series-title":"Spine (Phila Pa 1976).","first-page":"E671","article-title":"Deep learning automates measurement of spinopelvic parameters on lateral lumbar radiographs","volume":"46","author":"Schwartz JT","year":"2021","unstructured":"Schwartz JT, Cho BH, Tang P, Deep learning automates measurement of spinopelvic parameters on lateral lumbar radiographs. Spine (Phila Pa 1976).2021;46(12):E671\u2013E678."},{"issue":"1","key":"b26","series-title":"Radiology","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1148\/107.1.89","article-title":"The narrow lumbar spinal canal syndrome","volume":"107","author":"Roberson GH","year":"1973","unstructured":"Roberson GH, Llewellyn HJ, Taveras JM. The narrow lumbar spinal canal syndrome. Radiology. 1973;107(1):89\u201397.468945010.1148\/107.1.89"}],"container-title":["Journal of Neurosurgery: Spine"],"original-title":[],"link":[{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg-spine\/37\/1\/article-p104.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg-spine\/37\/1\/article-p104.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg-spine\/37\/1\/article-p104.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T16:24:34Z","timestamp":1681575874000},"score":1,"resource":{"primary":{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg-spine\/37\/1\/article-p104.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,1]]},"references-count":26,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3171\/2021.11.spine211136","relation":{},"ISSN":["1547-5654"],"issn-type":[{"value":"1547-5654","type":"print"}],"subject":[],"published":{"date-parts":[[2022,7,1]]}}}