Purpose: A method for automatic computation of global spinal alignment (GSA) metrics is presented to mitigate thehigh variability of manual definitions in radiographic images. The proposed algorithm segments vertebral endplatesin CT as a basis for automatic computation of metrics of global spinal morphology. The method is developed as apotential tool for intraoperative guidance in deformity correction surgery, and/or automatic definition of GSA in largedatasets for analysis of surgical outcome.Methods: The proposed approach segments vertebral endplates in spine CT images using vertebral labels as input.The segmentation algorithm extracts vertebral boundaries using a continuous max-flow algorithm and segments thevertebral endplate surface by region-growing. The point cloud of the segmented endplate is forward-projected as adigitally reconstructed radiograph (DRR), and a linear fit is computed to extract the endplate angle in the radiographicplane. Two GSA metrics (lumbar lordosis and thoracic kyphosis) were calculated using these automatically measuredendplate angles. Experiments were performed in seven patient CT images acquired from Spineweb and accuracy wasquantified by comparing automatically-computed endplate angles and GSA metrics to manual definitions.Results: Endplate angles were automatically computed with median accuracy = 2.7o, upper quartile (UQ) = 4.8o, andlower quartile (LQ) = 1.0° with respect to manual ground-truth definitions. This was within the measured intraobservervariability = 3.1o (RMS) of manual definitions. GSA metrics had median accuracy = 1.1o (UQ = 3.1o) forlumbar lordosis and median accuracy = 0.4o (UQ = 3.0o) for thoracic kyphosis. The performance of GSAmeasurements was also within the variability of the manual approach.Conclusions: The method offers a potential alternative to time-consuming, manual definition of endplate angles forGSA computation. Such automatic methods could provide a means of intraoperative decision support in correction ofspinal deformity and facilitate data-intensive analysis in identifying metrics correlating with surgical outcomes.
展开▼