{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T16:19:29Z","timestamp":1776788369019,"version":"3.51.2"},"reference-count":18,"publisher":"Journal of Neurosurgery Publishing Group (JNSPG)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4,1]]},"abstract":"<jats:sec>\n<jats:title>OBJECTIVE<\/jats:title>\n<jats:p>Knowledge of the manufacturer of the previously implanted pedicle screw systems prior to revision spinal surgery may facilitate faster and safer surgery. Often, this information is unavailable because patients are referred by other centers or because of missing information in the patients\u2019 records. Recently, machine learning and computer vision have gained wider use in clinical applications. The authors propose a computer vision approach to classify posterior thoracolumbar instrumentation systems.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>METHODS<\/jats:title>\n<jats:p>Lateral and anteroposterior (AP) radiographs obtained in patients undergoing posterior thoracolumbar pedicle screw implantation for any indication at the authors\u2019 institution (2015\u20132021) were obtained. DICOM images were cropped to include both the pedicle screws and rods. Images were labeled with the manufacturer according to the operative record. Multiple feature detection methods were tested (SURF, MESR, and Minimum Eigenvalues); however, the bag-of-visual-words technique with KAZE feature detection was ultimately used to construct a computer vision support vector machine (SVM) classifier for lateral, AP, and fused lateral and AP images. Accuracy was tested using an 80%\/20% training\/testing pseudorandom split over 100 iterations. Using a reader study, the authors compared the model performance with the current practice of surgeons and manufacturer representatives identifying spinal hardware by visual inspection.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>RESULTS<\/jats:title>\n<jats:p>Among the three image types, 355 lateral, 379 AP, and 338 fused radiographs were obtained. The five pedicle screw implants included in this study were the Globus Medical Creo, Medtronic Solera, NuVasive Reline, Stryker Xia, and DePuy Expedium. When the two most common manufacturers used at the authors\u2019 institution were binarily classified (Globus Medical and Medtronic), the accuracy rates for lateral, AP, and fused images were 93.15% \u00b1 4.06%, 88.98% \u00b1 4.08%, and 91.08% \u00b1 5.30%, respectively. Classification accuracy decreased by approximately 10% with each additional manufacturer added. The multilevel five-way classification accuracy rates for lateral, AP, and fused images were 64.27% \u00b1 5.13%, 60.95% \u00b1 5.52%, and 65.90% \u00b1 5.14%, respectively. In the reader study, the model performed five-way classification on 100 test images with 79% accuracy in 14 seconds, compared with an average of 44% accuracy in 20 minutes for two surgeons and three manufacturer representatives.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>CONCLUSIONS<\/jats:title>\n<jats:p>The authors developed a KAZE feature detector with an SVM classifier that successfully identified posterior thoracolumbar hardware at five-level classification. The model performed more accurately and efficiently than the method currently used in clinical practice. The relative computational simplicity of this model, from input to output, may facilitate future prospective studies in the clinical setting.<\/jats:p>\n<\/jats:sec>","DOI":"10.3171\/2022.11.spine221009","type":"journal-article","created":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T17:16:51Z","timestamp":1672161411000},"page":"417-424","source":"Crossref","is-referenced-by-count":2,"title":["A computer vision approach to identifying the manufacturer of posterior thoracolumbar instrumentation systems"],"prefix":"10.3171","volume":"38","author":[{"given":"Adrish","family":"Anand","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, Baylor College of Medicine, Houston;"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex R.","family":"Flores","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Baylor College of Medicine, Houston;"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malcolm F.","family":"McDonald","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Baylor College of Medicine, Houston;"},{"name":"Medical Scientist Training Program, Baylor College of Medicine, Houston, Texas; and"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron","family":"Gadot","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Baylor College of Medicine, Houston;"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David S.","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Ohio State University School of Medicine, Columbus, Ohio"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander E.","family":"Ropper","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Baylor College of Medicine, Houston;"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1754","reference":[{"issue":"2","key":"b1","series-title":"Turk Neurosurg","first-page":"167","article-title":"A systematic review on machine learning in neurosurgery: the future of decision-making in patient care","volume":"28","author":"Celtikci E","year":"2018","unstructured":"Celtikci E. A systematic review on machine learning in neurosurgery: the future of decision-making in patient care. Turk Neurosurg. 2018;28(2):167\u2013173.28481395"},{"key":"b2","series-title":"World Neurosurg","first-page":"512","article-title":"Use of machine learning and artificial intelligence to drive personalized medicine approaches for spine care","volume":"140","author":"Khan O","year":"2020","unstructured":"Khan O, Badhiwala JH, Grasso G, Fehlings MG. Use of machine learning and artificial intelligence to drive personalized medicine approaches for spine care. World Neurosurg. 2020;140:512\u2013518.32797983"},{"issue":"10","key":"b3","series-title":"AJNR Am J Neuroradiol","first-page":"1776","article-title":"Deep learning in neuroradiology","volume":"39","author":"Zaharchuk G","year":"2018","unstructured":"Zaharchuk G, Gong E, Wintermark M, Rubin D, Langlotz CP. Deep learning in neuroradiology. AJNR Am J Neuroradiol. 2018;39(10):1776\u20131784.29419402"},{"key":"b4","series-title":"Med Image Anal","first-page":"66","article-title":"Large-scale retrieval for medical image analytics: a comprehensive review","volume":"43","author":"Li Z","year":"2018","unstructured":"Li Z, Zhang X, M\u00fcller H, Zhang S. Large-scale retrieval for medical image analytics: a comprehensive review. Med Image Anal. 2018;43:66\u201384.29031831"},{"issue":"6","key":"b5","series-title":"J Neural Eng","first-page":"066028","article-title":"Comparison of logistic regression, support vector machines, and deep learning classifiers for predicting memory encoding success using human intracranial EEG recordings","volume":"15","author":"Arora A","year":"2018","unstructured":"Arora A, Lin JJ, Gasperian A,  Comparison of logistic regression, support vector machines, and deep learning classifiers for predicting memory encoding success using human intracranial EEG recordings. J Neural Eng. 2018;15(6):066028.30211695"},{"issue":"14","key":"b6","series-title":"Sensors (Basel)","first-page":"4669","article-title":"Classical machine learning versus deep learning for the older adults free-living activity classification","volume":"21","author":"Awais M","year":"2021","unstructured":"Awais M, Chiari L, Ihlen EAF, Helbostad JL, Palmerini L. Classical machine learning versus deep learning for the older adults free-living activity classification. Sensors (Basel). 2021;21(14):4669.34300409"},{"issue":"5","key":"b7","series-title":"Neurosurg Rev","first-page":"1235","article-title":"Machine learning applications to clinical decision support in neurosurgery: an artificial intelligence augmented systematic review","volume":"43","author":"Buchlak QD","year":"2020","unstructured":"Buchlak QD, Esmaili N, Leveque JC,  Machine learning applications to clinical decision support in neurosurgery: an artificial intelligence augmented systematic review. Neurosurg Rev. 2020;43(5):1235\u20131253.31422572"},{"key":"b8","series-title":"World Neurosurg","first-page":"476","article-title":"Machine learning and neurosurgical outcome prediction: a systematic review","volume":"109","author":"Senders JT","year":"2018","unstructured":"Senders JT, Staples PC, Karhade AV,  Machine learning and neurosurgical outcome prediction: a systematic review. World Neurosurg. 2018;109:476\u2013486.e1.28986230"},{"issue":"5","key":"b9","series-title":"Spine (Phila Pa 1976)","first-page":"E318","article-title":"Deep learning application in spinal implant identification","volume":"46","author":"Yang HS","year":"2021","unstructured":"Yang HS, Kim KR, Kim S, Park JY. Deep learning application in spinal implant identification. Spine (Phila Pa 1976). 2021;46(5):E318\u2013E324.33534442"},{"issue":"6","key":"b10","series-title":"J Neurosurg Spine","first-page":"844","article-title":"A computer vision approach to identifying the manufacturer and model of anterior cervical spinal hardware","volume":"31","author":"Huang KT","year":"2019","unstructured":"Huang KT, Silva MA, See AP,  A computer vision approach to identifying the manufacturer and model of anterior cervical spinal hardware. J Neurosurg Spine. 2019;31(6):844\u2013850."},{"key":"b11","series-title":"Pattern Recognit","first-page":"480","article-title":"Synergy of foreground\u2013background images for feature extraction: offline signature verification using Fisher vector with fused KAZE features","volume":"79","author":"Okawa M","year":"2018","unstructured":"Okawa M. Synergy of foreground\u2013background images for feature extraction: offline signature verification using Fisher vector with fused KAZE features. Pattern Recognit. 2018;79:480\u2013489."},{"issue":"8","key":"b12","series-title":"IEEE Trans Multimed","first-page":"1391","article-title":"Fast object retrieval using direct spatial matching","volume":"17","author":"Zhong Z","year":"2015","unstructured":"Zhong Z, Zhu J, Hoi SCH. Fast object retrieval using direct spatial matching. IEEE Trans Multimed. 2015;17(8):1391\u20131397."},{"issue":"1","key":"b13","series-title":"Nat Med","first-page":"24","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva A","year":"2019","unstructured":"Esteva A, Robicquet A, Ramsundar B,  A guide to deep learning in healthcare. Nat Med. 2019;25(1):24\u201329.30617335"},{"issue":"12","key":"b14","series-title":"Acta Neurochir (Wien)","first-page":"3081","article-title":"Machine learning in neurosurgery: a global survey","volume":"162","author":"Staartjes VE","year":"2020","unstructured":"Staartjes VE, Stumpo V, Kernbach JM,  Machine learning in neurosurgery: a global survey. Acta Neurochir (Wien). 2020;162(12):3081\u20133091.32812067"},{"issue":"10162","key":"b15","series-title":"Lancet","first-page":"2388","article-title":"Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study","volume":"392","author":"Chilamkurthy S","year":"2018","unstructured":"Chilamkurthy S, Ghosh R, Tanamala S,  Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet. 2018;392(10162):2388\u20132396.30318264"},{"issue":"5","key":"b16","series-title":"IEEE Pulse","first-page":"16","article-title":"Imaging intelligence: AI is transforming medical imaging across the imaging spectrum","volume":"9","author":"Mandal S","year":"2018","unstructured":"Mandal S, Greenblatt AB, An J. Imaging intelligence: AI is transforming medical imaging across the imaging spectrum. IEEE Pulse. 2018;9(5):16\u201324.30273136"},{"issue":"9","key":"b17","series-title":"Spine (Phila Pa 1976)","first-page":"E407","article-title":"Identification of anterior cervical spinal instrumentation using a smartphone application powered by machine learning","volume":"47","author":"Schwartz JT","year":"2022","unstructured":"Schwartz JT, Valliani AA, Arvind V,  Identification of anterior cervical spinal instrumentation using a smartphone application powered by machine learning. Spine (Phila Pa 1976). 2022;47(9):E407\u2013E414.34269759"},{"key":"b18","series-title":"Med Image Anal","first-page":"60","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens G","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi BE,  A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60\u201388.28778026"}],"container-title":["Journal of Neurosurgery: Spine"],"original-title":[],"link":[{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg-spine\/38\/4\/article-p417.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg-spine\/38\/4\/article-p417.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg-spine\/38\/4\/article-p417.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T13:12:16Z","timestamp":1733490736000},"score":1,"resource":{"primary":{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg-spine\/38\/4\/article-p417.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":18,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3171\/2022.11.spine221009","relation":{},"ISSN":["1547-5654"],"issn-type":[{"value":"1547-5654","type":"print"}],"subject":[],"published":{"date-parts":[[2023,4,1]]}}}