2019/11/04 by Florian Dubost, Benjamin Collery, Dubost, Florian +13
Engineering · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Medical Imaging and Analysis #Scoliosis diagnosis and treatment #Spinal Fractures and Fixation Techniques #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1911.01126
openalex publication_date 2019/11/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Scoliosis is a condition defined by an abnormal spinal curvature. For\ndiagnosis and treatment planning of scoliosis, spinal curvature can be\nestimated using Cobb angles. We propose an automated method for the estimation\nof Cobb angles from X-ray scans. First, the centerline of the spine was\nsegmented using a cascade of two convolutional neural networks. After smoothing\nthe centerline, Cobb angles were automatically estimated using the derivative\nof the centerline. We evaluated the results using the mean absolute error and\nthe average symmetric mean absolute percentage error between the manual\nassessment by experts and the automated predictions. For optimization, we used\n609 X-ray scans from the London Health Sciences Center, and for evaluation, we\nparticipated in the international challenge "Accurate Automated Spinal\nCurvature Estimation, MICCAI 2019" (100 scans). On the challenge's test set, we\nobtained an average symmetric mean absolute percentage error of 22.96.\n