Biomedical Engineering Reference
In-Depth Information
Table 9.2: Segmentation accuracy of different
methods when applied on MR simulated data
SNR
Segmentation Method
13 db
10 db
8 db
FCM
98.92
86.24
78.9
EM
99.12
93.53
85.11
BCFCM
99.25
97.3
93.7
Figure 9.19 shows the results of applying the BCFCM algorithm to segment a
real axial-sectioned T1 MR brain. Strong inhomogeneities are apparent in the im-
age. The BCFCM algorithm segmented the image into three classes correspond-
ing to background, GM, and WM. The bottom right image shows the estimate of
the multiplicative gain, scaled from 1 to 255.
Figure 9.20 shows the results of applying the BCFCM for the segmentation
of noisy brain images. The results using traditional FCM without considering
the neighborhood field effect and the BCFCM are presented. Notice that the
BCFCM segmentation, which uses the the neighborhood field effect, is much
less fragmented than the traditional FCM approach. As mentioned before, the
relative importance of the regularizing term is inversely proportional to the
SNR of MRI signal. It is important to note, however, that the incorporation of
spatial constraints into the classification has the disadvantage of blurring some
fine details. There are current efforts to solve this problem by including contrast
information into the classification. High contrast pixels, which usually represent
boundaries between objects, should not be included in the neighbors.
9.5 Level Sets
The mathematical foundation of deformable models represents the confluence
of physics and geometry. Geometry serves to represent object shape and physics
puts some constrains on how it may vary over space and time. Deformable mod-
els have had great success in imaging and computer graphics. Deformable mod-
els include snakes and active contours. Snakes are used based on the geometric
properties in image data to extract objects and anatomical structures in medi-
cal imaging. After initialization, snakes evolve to get the object. The change of
