Limits...
jClustering, an open framework for the development of 4D clustering algorithms.

Mateos-Pérez JM, García-Villalba C, Pascau J, Desco M, Vaquero JJ - PLoS ONE (2013)

Bottom Line: Providing an easily extensible open tool encourages publication of source code to facilitate the process of comparing algorithms and provide interested third parties with the opportunity to review code.The internal structure of the framework allows an external developer to implement new algorithms easily and quickly, focusing only on the particulars of the method being implemented and not on image data handling and preprocessing.Both binary packages and source code have been published, the latter under a free software license (GNU General Public License) to allow modification if necessary.

View Article: PubMed Central - PubMed

Affiliation: Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain ; Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain.

ABSTRACT
We present jClustering, an open framework for the design of clustering algorithms in dynamic medical imaging. We developed this tool because of the difficulty involved in manually segmenting dynamic PET images and the lack of availability of source code for published segmentation algorithms. Providing an easily extensible open tool encourages publication of source code to facilitate the process of comparing algorithms and provide interested third parties with the opportunity to review code. The internal structure of the framework allows an external developer to implement new algorithms easily and quickly, focusing only on the particulars of the method being implemented and not on image data handling and preprocessing. This tool has been coded in Java and is presented as an ImageJ plugin in order to take advantage of all the functionalities offered by this imaging analysis platform. Both binary packages and source code have been published, the latter under a free software license (GNU General Public License) to allow modification if necessary.

Show MeSH
Basic flow diagram.Flow diagram of the basic steps necessary to perform a clustering operation. In iterative algorithms, several loops of the voxel assignation stage can be performed until convergence is reached.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3750055&req=5

pone-0070797-g001: Basic flow diagram.Flow diagram of the basic steps necessary to perform a clustering operation. In iterative algorithms, several loops of the voxel assignation stage can be performed until convergence is reached.

Mentions: The workflow implemented was kept as simple as possible and is depicted in Figure 1. In short, each individual voxel TAC is passed to the ClusteringTechnique module, which can re-use a ClusteringMetric if the metric of a particular algorithm has already been used. This ClusteringTechnique module groups together objects of the class Voxel (which contains TAC data and spatial information) using the Cluster class and adds all the formed Cluster objects to a native ArrayList object. Then, the final ArrayList object is automatically converted to an ImagePlus object for cluster visualization, since it is a native ImageJ image object. In order to present the clusters comprehensively, a pseudo-dynamic image containing n+1 frames is used, with n being the total number of clusters formed. The nth frame contains the visual information for the nth cluster, and the last frame contains a simultaneous composition of all the clusters for better spatial reference. This simplified workflow will be expanded in the following section as the relevant classes are discussed. The full public API can be found in File S1.


jClustering, an open framework for the development of 4D clustering algorithms.

Mateos-Pérez JM, García-Villalba C, Pascau J, Desco M, Vaquero JJ - PLoS ONE (2013)

Basic flow diagram.Flow diagram of the basic steps necessary to perform a clustering operation. In iterative algorithms, several loops of the voxel assignation stage can be performed until convergence is reached.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3750055&req=5

pone-0070797-g001: Basic flow diagram.Flow diagram of the basic steps necessary to perform a clustering operation. In iterative algorithms, several loops of the voxel assignation stage can be performed until convergence is reached.
Mentions: The workflow implemented was kept as simple as possible and is depicted in Figure 1. In short, each individual voxel TAC is passed to the ClusteringTechnique module, which can re-use a ClusteringMetric if the metric of a particular algorithm has already been used. This ClusteringTechnique module groups together objects of the class Voxel (which contains TAC data and spatial information) using the Cluster class and adds all the formed Cluster objects to a native ArrayList object. Then, the final ArrayList object is automatically converted to an ImagePlus object for cluster visualization, since it is a native ImageJ image object. In order to present the clusters comprehensively, a pseudo-dynamic image containing n+1 frames is used, with n being the total number of clusters formed. The nth frame contains the visual information for the nth cluster, and the last frame contains a simultaneous composition of all the clusters for better spatial reference. This simplified workflow will be expanded in the following section as the relevant classes are discussed. The full public API can be found in File S1.

Bottom Line: Providing an easily extensible open tool encourages publication of source code to facilitate the process of comparing algorithms and provide interested third parties with the opportunity to review code.The internal structure of the framework allows an external developer to implement new algorithms easily and quickly, focusing only on the particulars of the method being implemented and not on image data handling and preprocessing.Both binary packages and source code have been published, the latter under a free software license (GNU General Public License) to allow modification if necessary.

View Article: PubMed Central - PubMed

Affiliation: Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain ; Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain.

ABSTRACT
We present jClustering, an open framework for the design of clustering algorithms in dynamic medical imaging. We developed this tool because of the difficulty involved in manually segmenting dynamic PET images and the lack of availability of source code for published segmentation algorithms. Providing an easily extensible open tool encourages publication of source code to facilitate the process of comparing algorithms and provide interested third parties with the opportunity to review code. The internal structure of the framework allows an external developer to implement new algorithms easily and quickly, focusing only on the particulars of the method being implemented and not on image data handling and preprocessing. This tool has been coded in Java and is presented as an ImageJ plugin in order to take advantage of all the functionalities offered by this imaging analysis platform. Both binary packages and source code have been published, the latter under a free software license (GNU General Public License) to allow modification if necessary.

Show MeSH