Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Coupling Deformable Models for Multi-Object Segmentation

Summary: Coupling Deformable Models
for Multi-Object Segmentation
Dagmar Kainmueller, Hans Lamecker, Stefan Zachow, and Hans-Christian Hege
Zuse Institute Berlin, Germany
Abstract. For biomechanical simulations, the segmentation of multi-
ple adjacent anatomical structures from medical image data is often re-
quired. If adjacent structures are hardly distinguishable in image data,
automatic segmentation methods for single structures in general do not
yield sufficiently accurate results. To improve segmentation accuracy in
these cases, knowledge about adjacent structures must be exploited. Op-
timal graph searching based on deformable surface models allows for a
simultaneous segmentation of multiple adjacent objects. However, this
method requires a correspondence relation between vertices of adjacent
surface meshes. Line segments, each containing two corresponding ver-
tices, may then serve as shared displacement directions in the segmenta-
tion process. The problem is how to define suitable correspondences on
arbitrary surfaces. In this paper we propose a scheme for constructing
a correspondence relation in adjacent regions of two arbitrary surfaces.
When applying the thus generated shared displacement directions in seg-
mentation with deformable surfaces, overlap of the surfaces is guaranteed


Source: Andrzejak, Artur - Konrad-Zuse-Zentrum für Informationstechnik Berlin


Collections: Computer Technologies and Information Sciences