Biomedical Engineering Reference
In-Depth Information
two improvements are proposed to augment the speed function. The relaxation
factor is first introduced. It provides a relaxing boundary condition, so as to stop
the evolving curve at a blurred or unclear boundary. Second, the speed term is
augmented by introducing visual content items. A simple and general model is
proposed to incorporate image features into the speed item in order to improve the
flexibility and performance of the speed function. Promising experimental results
have demonstrated that incorporation of the distance measure and proper image
features in the speed function can improve the segmentation result significantly.
As a further step, we present a unified approach for semiautomatic segmenta-
tion and tracking of the high-resolution color anatomical Chinese Visible Human
(CVH) data. A two-step scheme is proposed, starting from segmenting the first
image slice. The user need only to initialize on the first slice by clicking on the
area of interest. The contours in subsequent image slices can then be automatically
tracked. The advantage of this methods lies in two factors. The first is its ability to
deal with non-rigid objects, using a simple model that does not require important
prior knowledge. This makes it especially feasible in the context of general med-
ical segmentation. Furthermore, the proposed two-step scheme for segmentation
and tracking requires very little user intervention.
These advantages make it possible to employ this technique in future work on
the reconstruction of a complex vascular system with topological changes.
7.
ACKNOWLEDGMENTS
The work described in this chapter was supported by a grant from the Re-
search Grants Council of the Hong Kong Special Administrative Region, China
(Project No. CUHK4223/04E) and the CUHK Shun Hing Institute of Advanced
Engineering.
8.
REFERENCES
1. Bankman IN. 2000.
Handbook of medical imaging: processing and analysis
. New York: Acad-
emic Press.
2. Kass M, Witkin A, Terzopoulos D. 1987. Snakes: active contour models. In
Proceedings of the
international conference on computer vision
, pp. 261-268. Washington, DC: IEEE Computer
Society.
3. Kass M, Witkin A, Terzopoulos D. 1987. Snakes: active contour models.
Int J Comput Vision
1
:321-331.
4. Sethian J. 1999.
Level set methods and fast marching methods: evolving interfaces in computa-
tional geometry, fluidmechanics, computer vision, andmaterials science
. Cambridge: Cambridge
UP.
5. Xu C, Pham DL, Prince JL. 2000. Medical image segmentation using deformable models. In
Handbook of medical imaging
, Vol. 2:
Medical image processing and analysis
, pp. 129-174. Ed
M Sonka, JM Fitzpatrick. Bellingham, WA: SPIE Press.
6. Terzopoulos D. 1986. Regularization of inverse visual problems involving discontinuities.
IEEE
Trans Pattern Anal Machine Intell
8
(4):413-424.
