Difference between revisions of "MGDM"

From IACL
Jump to: navigation, search
(start of MGDM research page)
 
(links to resources on NITRC)
Line 20: Line 20:
 
medical imaging.  Comparing the new framework with previous approaches
 
medical imaging.  Comparing the new framework with previous approaches
 
shows its superior performance and scalability.
 
shows its superior performance and scalability.
 +
 +
{{h3|Source code and demonstrations}}
 +
Source code and MATLAB demonstrations can be found on the [http://www.nitrc.org/projects/mgdm/ MGDM NITRC] page.
 +
* Compiled MGDM code and MATLAB scripts can be [http://www.nitrc.org/frs/download.php/5090/mgdm_20121204a.zip downloaded] from NITRC.  This release also contains several [http://www.nitrc.org/plugins/mwiki/index.php/mgdm:Demos demonstrations] of MGDM.
 +
* [http://www.nitrc.org/plugins/mwiki/index.php/mgdm:Build Instructions] for checking out and compiling the MGDM source code.
 +
* Users experienced with deformable models can take full advantage of MGDM by [http://www.nitrc.org/plugins/mwiki/index.php/mgdm:BoundarySpeedSpec specifying boundary-specific speeds].

Revision as of 14:28, 19 March 2013

A Multiple Object Geometric Deformable Model for Image Segmentation

John A. Bogovic, Jerry L. Prince, and Pierre-Louis Bazin

Abstract

Deformable models are widely used for image segmentation, most commonly to find single objects within an image. Although several methods have been proposed to segment multiple objects using deformable models, substantial limitations in their utility remain. This paper presents a multiple object segmentation method using a novel and efficient object representation for both two and three dimensions. The new framework guarantees object relationships and topology, prevents overlaps and gaps, enables boundary-specific speeds, and has a computationally efficient evolution scheme that is largely independent of the number of objects. Maintaining object relationships and straightforward use of object-specific and boundary-specific smoothing and advection forces enables the segmentation of objects with multiple compartments, a critical capability in the parcellation of organs in medical imaging. Comparing the new framework with previous approaches shows its superior performance and scalability.

Source code and demonstrations

Source code and MATLAB demonstrations can be found on the MGDM NITRC page.