12 March 2013 A statistical multi-vertebrae shape+pose model for segmentation of CT images
Author Affiliations +
Abstract
Segmentation of the spinal column from CT images is a pre-processing step for a range of image guided interventions. Current techniques focus on identification and separate segmentation of each vertebra. Recently, statistical multi-object shape models have been introduced to extract common statistical characteristics between several anatomies. These models are also used for segmentation purposes and are shown to be robust, accurate, and computationally tractable. In this paper, we reconstruct a statistical multi-vertebrae shape+pose model and propose a novel technique to register such a model to CT images. We validate our technique in terms of accuracy of the multi-vertebrae segmentation of CT images acquired from 16 subjects. The mean distance error achieved for all vertebrae is 1.17 mm with standard deviation of 0.38 mm.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Abtin Rasoulian, Abtin Rasoulian, Robert N. Rohling, Robert N. Rohling, Purang Abolmaesumi, Purang Abolmaesumi, } "A statistical multi-vertebrae shape+pose model for segmentation of CT images", Proc. SPIE 8671, Medical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling, 86710P (12 March 2013); doi: 10.1117/12.2007448; https://doi.org/10.1117/12.2007448
PROCEEDINGS
6 PAGES


SHARE
Back to Top