• John T Schwartz, Aly A Valliani, Varun Arvind, Brian H Cho, Eric Geng, Philip Henson, K Daniel Riew, Ronald A Lehman, Lawrence G Lenke, Samuel K Cho, and Jun S Kim.
• Department of Orthopedic Surgery, Mount Sinai Health System, New York, NY.
• Spine. 2022 May 1; 47 (9): E407E414E407-E414.

Study DesignCross-sectional study.ObjectiveThe purpose of this study is to develop and validate a machine learning algorithm for the automated identification of anterior cervical discectomy and fusion (ACDF) plates from smartphone images of anterior-posterior (AP) cervical spine radiographs.Summary Of Background DataIdentification of existing instrumentation is a critical step in planning revision surgery for ACDF. Machine learning algorithms that are known to be adept at image classification may be applied to the problem of ACDF plate identification.MethodsA total of 402 smartphone images containing 15 different types of ACDF plates were gathered. Two hundred seventy-five images (∼70%) were used to train and validate a convolution neural network (CNN) for classification of images from radiographs. One hundred twenty-seven (∼30%) images were held out to test algorithm performance.ResultsThe algorithm performed with an overall accuracy of 94.4% and 85.8% for top-3 and top-1 accuracy, respectively. Overall positive predictive value, sensitivity, and f1-scores were 0.873, 0.858, and 0.855, respectively.ConclusionThis algorithm demonstrates strong performance in the classification of ACDF plates from smartphone images and will be deployed as an accessible smartphone application for further evaluation, improvement, and eventual widespread use.Level of Evidence: 3.Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.

14 keywords...

hide…