Biomedical Engineering Reference
In-Depth Information
Stochastic image models are useful in quantitatively specifying natural con-
straints and general assumption about the physical world and the imaging pro-
cess. Random field models permit the introduction of spatial context into pixel
labeling problem. An introduction to random fields and its application in lung
CT segmentation will be presented in Section 9.2.
Crisp segmentation, by which a pixel is assigned to a one particular region,
often presents problems. In many situations, it is not easy to determine if a pixel
should belong to a region or not. This is because the features used to determine
homogeneity may not have sharp transitions at region boundaries. To alleviate
this situation, we can inset fuzzy set concepts into the segmentation process.
In Section 9.4, we will present an algorithm for fuzzy segmentation of MRI data
and estimation of intensity inhomogeneities using fuzzy logic. MRI intensity
inhomogeneities can be attributed to imperfections in the RF coils or to problems
associated with the acquisition sequences. The result is a slowly varying shading
artifact over the image that can produce errors with conventional intensity-
based classification. The algorithm is formulated by modifying the objective
function of the standard fuzzy c-means (FCM) algorithm to compensate for such
inhomogeneities and to allow the labeling of a pixel (voxel) to be influenced
by the labels in its immediate neighborhood. The neighborhood effect acts as
a regularizer and biases the solution toward piecewise-homogeneous labelings.
Such a regularization is useful in segmenting scans corrupted by salt and pepper
noise.
Section 9.5 is devoted to the description of geometrical methods and their
application in image segmentation. Among many methods used for shape recov-
ery, the level sets has proven to be a successful tool. The level set is a method for
capturing moving fronts introduced by Osher and Sethian in 1987. It was used
in many applications like fluid dynamics, graphics, visualization, image process-
ing, and computer vision. In this chapter, we introduce an overview of the level
set and its use in image segmentation with application in vascular segmentation.
The human cerebrovascular system is a complex three-dimensional anatomical
structure. Serious types of vascular diseases such as carotid stenosis, aneurysm,
and vascular malformation may lead to brain stroke, which are the third leading
cause of death and the main cause of disability. An accurate model of the vas-
cular system from MRA data volume is needed to detect these diseases at early
stages and hence may prevent invasive treatments. In this section, we will use
