The change of lumbar curvature is used as the intuitionistic reflection for nearly all lumbar spine lesions, such as low back pain. Although several automatic segmentation methods have been proposed for the lumbar spine, those techniques cannot be directly applied to the diagnosis of spinal lesions due to the lack of quantitative estimation in lumbar curvature. In this study, by using a machine learning strategy, we designed an analysis pipeline and developed a fully automated measurement system of lumbar curvature, then validated it against a dataset of 45 subjects with T2w images.
This abstract and the presentation materials are available to members only; a login is required.