Abstract
We present an automated method for measuring the sagittal vertical axis (SVA) from lateral radiography of whole spine using a convolutional neural network for keypoint detection (ResUNet) with our improved localization method. The algorithm is robust to various clinical conditions, such as degenerative changes or deformities. The ResUNet was trained and evaluated on 990 standing lateral radiographs taken at Chang Gung Memorial Hospital, Linkou and performs SVA measurement with median absolute error of 1.183 ± 0.166 mm. The 5-mm detection rate of the C7 body and the sacrum are 91% and 87%, respectively. The SVA calculation takes approximately 0.2 s per image. The intra-class correlation coefficient of the SVA estimates between the algorithm and physicians of different years of experience ranges from 0.946 to 0.993, indicating an excellent consistency. The superior performance of the proposed method and its high consistency with physicians proved its usefulness for automatic measurement of SVA in clinical settings.
Highlights
Adult spinal deformity (ASD) is a broad diagnosis referring to stable asymptomatic curves and disabling deformities in the spine that contribute to pain, weakness, and low health-related quality of life (HRQOL)
As median absolute error (MAE) is insensitive to outliers, we report the number of outliers (>10 mm) for absolute errors
Among these 68 images, there were 33 and 17 images whose predictions were suspected to be influenced by numerical variation of mobile vertebrae (NVMV), and the occlusion of C7 or sacrum, respectively. In the former case, we found it difficult to predict the sacral point when confronting with cases of NVMV, or variable sacral fusion, by using the lateral plain radiographs only
Summary
Adult spinal deformity (ASD) is a broad diagnosis referring to stable asymptomatic curves and disabling deformities in the spine that contribute to pain, weakness, and low health-related quality of life (HRQOL). ASD is quite common, the variation and unique pattern of each spinal deformity make reproducible measurement difficult. Previous studies investigating the correlation between radiographic appearances and clinical symptoms yielded rather low predictive power due to highly variable health status [1]. In 2005, Glassman et al showed that sagittal plane balance is the most reliable predictor of clinical symptoms in adults with spinal deformity [3]. Even mild positive sagittal balance results in destructive spinal deformity, clinical symptoms of which deteriorate linearly [4]. A surgical plan for restoring sagittal balance is crucial in all spinal reconstructive surgeries [3]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.