A robust segmentation framework for spine trauma diagnosis
In: Jianhua Yao, Tobias Klinder and Shuo Li (eds), Computational Methods and Clinical Applications for Spine Imaging. Lecture Notes in Computational Vision and Biomechanics, vol. 17, pp. 25–33. Springer, Cham.
Abstract
An abstract is not available in the lab archive. View the paper at its source.
This 2014 conference paper presents a level set framework for segmenting normal and fractured spinal vertebrae in CT images, combining prior shape knowledge with local geometric features.
Summary
Lim, Bagci and Bai describe a level set image-segmentation framework intended to segment both normal and fractured spinal vertebrae. It combines prior shape knowledge, estimated using kernel density estimation, with local geometric features represented by an edge-mounted Willmore energy. The authors report experiments on CT images of normal and fractured vertebrae and describe the 3D segmentation results as promising. The chapter reports an experimental evaluation; it does not establish clinical readiness.
- Authors: Poay Hoon Lim, Ulas Bagci and Li Bai, in that order.
- Venue: Computational Methods and Clinical Applications for Spine Imaging, Lecture Notes in Computational Vision and Biomechanics, volume 17, pp. 25–33.
- Scientific publication year: 2014.
Cite this work
Poay Hoon Lim; Ulas Bagci; Li Bai (2014). A robust segmentation framework for spine trauma diagnosis. In: Jianhua Yao, Tobias Klinder and Shuo Li (eds), Computational Methods and Clinical Applications for Spine Imaging. Lecture Notes in Computational Vision and Biomechanics, vol. 17, pp. 25–33. Springer, Cham. https://doi.org/10.1007/978-3-319-07269-2_3
BibTeX