Information Technology Reference
In-Depth Information
Model-Based Segmentation,
Reconstruction and Analysis
of the Vertebral Body from Spinal CT
Melih Aslan, Ahmed Shalaby, Asem Ali and Aly A. Farag
Abstract In this chapter, we present novel vertebral body segmentation methods in
computed tomography (CT) images. Three pieces of information (intensity, spatial
interaction, and shape) are modeled to optimize new probabilistic energy functions;
and hence to obtain the optimum segmentation. The information of the intensity and
spatial interaction are modeled using the Gaussian and Gibbs distribution, respec-
tively. A shape model is proposed using new probabilistic functions to enhance the
segmentation results. The models are generic shape information which is obtained
using the cervical, lumbar, and thoracic spinal regions. The proposed methods are
validated with clinical CT images and on a phantom with various Gaussian noise
levels. This study reveals that the proposed methods are robust under various noise
levels, less variant to the initialization, and quite faster than alternative methods.
Applications on bone mineral density (BMD) measurements of vertebral body are
given to illustrate the accuracy of the proposed segmentation approach.
1 Introduction
Isolating an organ from its surrounding anatomical structures is a crucial step in
many unsupervised frameworks. Examples of these frameworks are those that
assess the organ functions and those that are proposed for automatic classi
cation
of normal organ and acute rejection transplants. In this work, we propose seg-
mentation frameworks for spine bone [more speci
cally the Vertebral Body (VB)].
