Level Set Segmentation of Lumbar Vertebrae Using Appearance Models

Abstract

Abstract. For the planning of surgical interventions of the spine exact knowledge about 3D shape and the local bone quality of vertebrae are of great importance in order to estimate the anchorage strength of screws or implants. As a prerequisite for quantitative analysis a method for objective and therefore automated segmentation of vertebrae is needed. In this paper a framework for the automatic segmentation of vertebrae using 3D appearance models in a level set framework is presented. In this framework model information as well as gradient information and probabilities of pixel intensities at object edges in the unseen image are used. The method is tested on 29 lumbar vertebrae leading to accurate results, which can be useful for surgical planning and further analysis of the local bone quality.

Statistical model based analysis of bone mineral density of lumbar spine

“…All calculations have been performed on these resampled datasets. Afterwards, the images were segmented automatically by the model-based level-set method described in [2,3], followed by manual corrections of the segmentation results. These segmented images formed the basis to apply the following methods:…”

“…at the proximal femur has been described in detail previously [1,3]. First results of generating InShape models for the lumbar spine and their application to automated level set segmentation are presented in [2]. Therefore, this paper will present the underlying methods only briefly and will focus on the application of the model-based approach for automated ROI-placement and bone quality analysis of the lumbar vertebrae.…”