Biomedical Engineering Reference
In-Depth Information
6.4.6 Multispectral techniques
Most traditional segmentation techniques use images
that represent only one type of data, for example MR or
CT. If different images of the same object are acquired
using several imaging modalities, such as CT, MR, PET,
ultrasound, or collecting images over time, they can
provide different features of the objects, and this spec-
trum of features can be used for segmentation. The
segmentation techniques based on integration of in-
formation from several images are called
multispectral
or
multimodal
[20, 22, 29, 90, 103, 118]
.
6.4.6.1 Segmentation using multiple
images acquired by different imaging
techniques
In the case of a single image, pixel classification is based
on a single feature (gray level), and segmentation is done
in one-dimensional (single-channel) feature space. In
multispectral images, each pixel is characterized by a set
of features and the segmentation can be performed in
multidimensional (multichannel) feature space using
clustering algorithms. For example, if the MR images
were collected using
T
1,
T
2, and a proton-density im-
aging protocol, the relative multispectral data set for each
tissue class result in the formation of tissue clusters in
three-dimensional feature space. The simplest approach
is to construct a 3D scatter plot, where the three axes
represent pixel intensities for
T
1,
T
2, and proton density
images. The clusters on such a scatter plot can be ana-
lyzed and the segmentation rules for different tissues can
be determined using
Figure 6.4-9 The results of adaptive segmentation applied to
dual-echo images of the brain. (A) Original T2-weighted image,
(B) original proton-density weighted image, (C) result of
conventional statistical classification, (D) result of EM
segmentation. The tissue classes are represented by colors:
blue, CSF; green, white matter; gray, gray matter; pink, fat; black,
background. (Courtesy of Dr. W. M. Wells III, Surgical Planning
Lab, Department of Radiology, Brigham and Women's Hospital,
Boston.)
algorithm (EM)
[26a]
and uses knowledge of tissue
properties and intensity inhomogeneities to correct and
segment MR images. The technique has been very ef-
fective in segmenting brain tissue in a study including
more than 1000 brain scans
[125]
.
Figures 6.4-9
A and B
present the original
T
2 and proton-density images, re-
spectively. Both images were obtained from a healthy
volunteer on a 1.5-T MR scanner.
Figure 6.4-9
C shows
a result of conventional statistical classification, using
nonparametric intensity models derived from images of
the same type from a different individual. The segmen-
tation is too heavy on white matter and shows asymmetry
in the gray matter thickness due to intrascan in-
homogeneities. Considerable improvement is evident in
Fig. 6.4-9
D, which shows the result of EM segmentation
after convergence at 19 iterations.
Adaptive segmentation
[125]
is a generalization of
standard intensity-based classification that, in addition to
the usual tissue class conditional intensity models, in-
corporates models of the intra- and interscan intensity
inhomogeneities that usually occur in MR images. The
EM algorithm is an iterative algorithm that alternates
between conventional statistical tissue classification (the
''E'' step) and the reestimation of a correction for the
unknown intensity inhomogeneity (the ''M'' step).
automatic or
semiautomatic
methods
[13, 19]
.
There are many segmentation techniques used in
multi-modality images. Some of them are
k
-nearest
neighbors (kNNs)
[19, 55, 76]
,
k
-means
[111, 118]
,
fuzzy
c
-means
[12, 40]
, artificial networks algorithms
[19, 89]
, expectation/maximization
[31, 58, 125]
, and
adaptive template moderated spatially varying statistical
classification techniques
[122]
. All multispectral tech-
niques require images to be properly registered. In order
to reduce noise and increase the performance of the
segmentation techniques, images can be smoothed. Ex-
cellent results have been obtained with adaptive filtering
[20]
, such as Bayesian processing, nonlinear anisotropic
diffusion filtering, and filtering with wavelet transforms
[32, 49, 50, 103, 124, 130]
.
To illustrate the advantages of using multispectral
segmentation, we show in
Fig. 6.4-9
the results of
adaptive segmentation by Wells
et al.
[125]
applied to
dual-echo (
T
2-weighted and proton-density weighted)
images of the brain. The adaptive segmentation tech-
nique
is based on the
expectation/maximization
