Biomedical Engineering Reference
In-Depth Information
Figure 9.25:
Histogram of empirical data.
time step of 0 . 1 sec. Using this initialization decreases the number of iterations,
leading to fast extraction of the vascular tree. The volume segmentation takes
about 20 min. on the unix workstation with the super computer. Segmentation
results are exposed to the connectivity filter to remove the nonvessel areas. Each
volume is visualized to show the vascular tree. The segmentation accuracy was
measured to be 94% which is very good for this type of data. The 2D phantom
can be modified to be a 3D one simulating the whole volume leading to more
accuracy. The results are promising with a good accuracy. This model can be
extended to unsupervised case including a parameter estimation capability in
future work. Future work will include geometrical features to the segmentation
model to enhance the segmentation results.
Questions
1. What are the main three properties of MRF?
2. Using traditional EM algorithm, estimate the mean, the variance, and
the proportional for the two classes shown in Fig. 9.25? (Hint: Before
applying EM algorithm, normalize f ( y ) such that for all y f ( y ) = 1 , and
assume each class comes from normal distribution).
3. What are the main advantages of using the genetic algorithm as optimiza-
tion tool?
4. When it is useful to use GMRF in image segmentation, and when is it not
useful?
Search WWH ::




Custom Search