|Please use this identifier to cite or link to this publication: http://hdl.handle.net/1926/1532|
is presented in this paper. Our algorithm is based on the work of Chan and Vese  that uses level-
sets to accomplish region segmentation in images with poor or no gradient information. The basic idea
is to partion the image into two piecewise constant intensity regions. This work is in contrast to the
level-set methods currently available in ITK which necessarily require gradient information. Similar to
those methods, the methods presented in this paper are also made efﬁcient using a sparse implementation
strategy that solves the contour evolution PDE at the level-set boundary. The framework consists of 6
new ITK ﬁlters that inherit in succession from itk::SegmentationFilter. We include 2D/3D example
code, parameter settings and show the results generated on a 2D cardiac image.
The authors have developed an ITK based implementation of the 'Active Contours without edges' formulation of level set segmentation.Open Science:
Source code and demonstration data are included.Reproducibility:
Compiled from source and tested with the 2D datasets provided by authors. Compiles with minor modifications to the CMakeLists.txt file.Use of Open Source Software:
Software uses only open source toolkits.Open source Contributions:
Full source provided.Free comment :
Level sets using region-based criteria such as this submission are far more managable than the edge based criteria present in ITK today. This is very useful contribution to the ITK community.
|Download Paper , View Paper|
|Download Source code|
|Categories:||Level sets, Region growing|
|Keywords:||level set, chan and vese|
|Toolkits:||ITK (moved into the sandbox)|
Linked Publications more
A Label Geometry Image Filter for Multiple Object Measurement
by Padfield D., Miller J.
Diffeomorphic Demons Using ITK's Finite Difference Solver Hierarchy
by Vercauteren T., Pennec X., Perchant A., Ayache N.
Send a message to the author