Incremental regression of localization context for automatic segmentation of ossified ligamentum flavum from CT data.

Abstract

Segmentation of ossified ligamentum flavum (OLF) plays a crucial role in developing computer-assisted, image-guided systems for decompressive thoracic laminectomy. Manual segmentation is time-consuming, tedious, and label-intensive. It also suffers from inter- and intra-observer variability. Automatic segmentation is highly desired. A two-stage, localization context-aware framework is developed for automatic segmentation of ossified ligamentum flavum. In the first stage, localization heatmaps of OLFs are obtained via incremental regression. In the second stage, the obtained heatmaps are then treated as the localization context for a segmentation U-Net. Our framework can directly map a whole volumetic data to its volume-wise labels. We designed and conducted comprehensive experiments on datasets of 100 patients to evaluate the performance of the proposed method. Our method achieved an average Dice similarity coefficient of 61.2±7.6%, an average surface distance of 1.1±0.5mm, and an average positive predictive value of 62.0±12.8%. To the best knowledge of the authors, this is the first study aiming for automatic segmentation of ossified ligamentum flavum. Results from the comprehensive experiments demonstrate the superior performance of the proposed method over the state-of-the-art methods.