Biomedical Engineering Reference
In-Depth Information
Figure 6.
The image segmentation result of the nuclei of two Benign (BEN) cells being
detected and delineated simutaneously by applying the geodesic deformable model. The
top left panel shows the initial curve, the top right and bottom left panels show two snapshots
of the evolving contours, and the bottom right panel shows the final segmentation results
after 1000 iterations. See attached CD for color version.
where ∆
t
is the iteration step. Equation (45) can be implemented iteratively, and
the contour of the object is the zero level set of the functional Ψ.
Figures 6 and 7 show the experimental results applying the geodesic de-
formable model on the segmentation of two Benign (BEN) cells and an immunos-
tained breast cancer tissue microarray disc. From these experiments we conclude
that geodesic deformable models are also insensitive to initial positions and can
automatically split or merge to address complex topological changes in the image.
(As in the previous section, all the segmentation results are obtained after applying
the color gradients in [17]; the result does not converge if applying the traditional
gradient [6].)
5.
CONCLUDING REMARKS
Medical imaging and computer-assisted diagnosis are extremely active fields
of research with a wide range of application domains. In this chapter we have
chosen to focus our emphasis on the use of deformable models in diagnostic
pathology applications since this area has been relatively underrepresented in the
literature.
