Topological Active Volumes

EURASIP J. Adv. Signal Process.

et al. 2013

In this article, we propose a novel image segmentation method called the whole mesh deformation (WMD) model, which aims at addressing the problems of modern medical imaging. Such problems have raised from the combination of several factors: (1) significant growth of medical image volumes sizes due to increasing capabilities of medical acquisition devices; (2) the will to increase the complexity of image processing algorithms in order to explore new functionality; (3) change in processor development and turn towards multi processing units instead of growing bus speeds and the number of operations per second of a single processing unit. Our solution is based on the concept of deformable models and is characterized by a very effective and precise segmentation capability. The proposed WMD model uses a volumetric mesh instead of a contour or a surface to represent the segmented shapes of interest, which allows exploiting more information in the image and obtaining results in shorter times, independently of image contents. The model also offers a good ability for topology changes and allows effective parallelization of workflow, which makes it a very good choice for large datasets. We present a precise model description, followed by experiments on artificial images and real medical data.

Section: Proposed Dynamic Topology Changes Modelmentioning

confidence: 99%

“…One of them was an implementation of the TAV model [20] and the other was based on the WMD model. Both models include the ability to perform topological changes.…”

Section: Performance Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

The whole mesh deformation model: a fast image segmentation method suitable for effective parallelization

EURASIP J. Adv. Signal Process.

et al. 2013

“…During this procedure the nodes of the mesh change their positions in a way which will results in placing them over the borders of objects of interests. This approach is similar to the general idea of segmentation methods based on the Deformable Models family and has the most in common with the Topological Active Volumes (TAV) [12] technique, which has served as the foundation for the WMD model. The characteristic of our model that differentiates it from the TAV solution is its ability to take advantage only from the groups of nodes that are initialized in the proximity of objects of interests -the remaining nodes would not be engaged in the segmentation process and at its end they would be discarded.…”

Section: The Dynamic Topology Changes Modelmentioning

confidence: 99%

Accelerating 3D Medical Image Segmentation with High Performance Computing

2008 First Workshops on Image Processing Theory, Tools and Applications

et al. 2008

Abstract-Deformable Models are a popular family of image segmentation techniques, which has been gaining significant focus in the last two decades, serving both for real-world applications as well as the base for research work. One of the features that the Deformable Models offer and that is considered a much desired one, is the ability to change their topology during the segmentation process. Using this characteristic it is possible to perform segmentation of objects with discontinuities in their bodies or to detect an undefined number of objects in the scene. In this paper we present our model for handling the topology changes in image segmentation methods based on the Active Volumes solution. The said model is capable of performing the changes in the structure of objects while the segmentation progresses, what makes it efficient and suitable for implementations over powerful execution environment, like multi-core architectures or computer clusters.

“…framework [2] and more specifically the Topological Active Volumes (TAV) model [3]. We have used several ideas of the original formulation of TAV as our foundation and introduced a number of improvements, including a major change in the organization of the model and in the way in which the segmentation is performed.…”

Section: Introductionmentioning

confidence: 99%

A new 3D image segmentation method for parallel architectures

2009 IEEE International Conference on Multimedia and Expo

et al. 2009

This paper presents a novel model for 3D image segmentation and reconstruction. It has been designed with the aim to be implemented over a computer cluster or a multi-core platform. The required features include a nearly absolute independence between the processes participating in the segmentation task and providing amount of work as equal as possible for all the participants. As a result, it is avoid many drawbacks often encountered when performing a parallelization of an algorithm that was constructed to operate in a sequential manner. Furthermore, the proposed algorithm based on the new segmentation model is efficient and shows a very good, nearly linear performance growth along with the growing number of processing units. 1