Title
Interactive constraints for 3D-simplex meshes
Abstract
Medical image segmentation is still a very time consuming task and therefore not often integrated into clinical routine. Various 3D segmentation approaches promise to facilitate the work. But they are rarely used in clinical setups due to complex intialization and parametrization of such models. Clinical users need interactive tools, intuitive and easy to handle. They do not want to play around with a set of parameters which will differ from dataset to dataset and often have a non-intuitive meaning. In this work new interactive constraints for deformable three-dimensional 2-simplex meshes are presented. The user can define attracting points in the original image data. These attractors are considered during model deformation and the new forces guarantee that the surface model will pass through these interactively set points. By using the constraints the model parameterization is simplified. Segmentation is started with a spherical surface model which is placed inside the structure of interest and then adapts to the boundaries. The user can directly influence the evolution of the deformable model and gets direct feedback during the segmentation process. The model deformation algorithm was implemented and integrated in ITK (Insight Segmentation and Registration Toolkit). The newly developed segmentation tool was tested on cardiac image data and MRI lung images, but is suitable for any kind of 3D and 3D+t medical image data. It has been shown that the model is less sensitive to preprocessing of the input data as well as model initialization.
Year
DOI
Venue
2005
10.1117/12.595218
PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE)
Keywords
Field
DocType
deformable model segmentation,2-simplex meshes,interactive forces,MRI,echocardiography
Computer vision,Scale-space segmentation,Polygon mesh,Parametrization,Segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Preprocessor,Artificial intelligence,Initialization
Conference
Volume
ISSN
Citations 
5747
0277-786X
1
PageRank 
References 
Authors
0.54
0
4
Name
Order
Citations
PageRank
thomas boettger110.54
Tobias Kunert215118.18
Hans-Peter Meinzer37916.17
Ivo Wolf473985.17