Biomedical Engineering Reference
In-Depth Information
Chapter 9
Advanced Segmentation Techniques
Aly A. Farag,
1
Mohamed N. Ahmed,
2
Ayman El-Baz,
1
and
Hossam Hassan
1
9.1 Introduction
The principal goal of the segmentation process is to partition an image into
regions that are homogeneous with respect to one or more characteristics or
features. Segmentation is an important tool in medical image processing and
it has been useful in many applications including lesion quatification, surgery
simulations, surgical planning, multiple scleroris, functional mapping, computer
assisted diagnosis, image registration and matching, etc.
A wide varity of segmentation techniques has been proposed. However, there
is no one standard segmentation technique that can produce satisfactory results
for all imaging applications. Quite often, methods are optimized to deal with spe-
cific imaging modalities such as magnetic resonance (MR) imaging and X-ray
computed tomography (CT), or modeled to segment specific anatomic struc-
tures such as the brain, the lungs, and the vascular system.
Recent research has demonstrated that the segmentation of anatomical
structures from MRI and CT will benefit from the exploitation of three different
types of knowledge: intensity models that describe the gray-level appearance
of individual structures, shape models that descibe the shape of different struc-
tures as well as imaging models that capture the characteristics of the imaging
process.
1
Computer Vision and Image Processing Laboratory, Department of Electrical and Com-
puter Engineering, University of Louisville, Louisville, KY 40292, USA
2
Software Research, C19L, Lexmark International Inc., Lexington, KY 40550, USA, E-mail:
farag@cvip.uofl.edu
479
