A novel spinal vertebrae segmentation framework combining geometric flow and shape prior with level set method

Segmentation of spinal vertebrae is extremely important in the study of spinal related disease or disorders. However, limited work has been done on precise segmentation of spinal vertebrae. The complexity of vertebrae shapes, with gaps in the cortical bone, internal boundaries, as well as the noisy, incomplete or missing information from the images have undoubtedly increased the challenge for image analysis. In this paper, we introduce a novel level set segmentation framework that integrates shape prior and the Willmore flow to drive the level set evolution. While the shape energy draws the level set function towards a range of possible prior shapes, the edge-mounted Willmore energy captures the localized geometry information and smooths the surface during the level set evolution. Experimental results on segmentation of spinal vertebrae from CT images demonstrate the powerful combination of prior knowledge and geometrical flow.