Deformable structural models

Tönnies

IEEE International Conference on Image Processing 2005

2005

Abstract-Shape models used for the segmentation of 3D image data often suffer from high instability of shape. Current approaches to avoid this instability often result in models with high computation times and few possibilities for interaction and modelling.We present a 3D mass-spring model which has been extended by torsion forces and the capability of explicit rotation. These models are stable with respect to shape collapse and contortion. Stability is achieved even if the model is only sparsely connected. This makes the computation efficient enough for real-time interaction.The extended model has been successfully applied to the segmentation of the left ventricle of the human heart in 3D SPECT data.

“…One solution is to create mass-spring models with a dense mesh of springs ( [2]), which require a large computational effort and therefore do not allow for real-time interaction.…”

Section: Related Workmentioning

confidence: 99%

Stable dynamic 3D shape models

Tönnies

IEEE International Conference on Image Processing 2005

2005

IEEE International Conference on Image Processing 2005

“…A control structure such as the one presented in [5] and used in [6] to find optimal instances of shape may be used to govern the adaptive behaviour of the model for a group of shape instances. A physically based model is created from some initial knowledge about the shape of objects of a given class.…”

Section: An Adaptive Dynamic Modelmentioning

confidence: 99%

“…We used a configurable spring-mass-model as presented in [6]. Springs represent the a-priori-knowledge about shape.…”

Section: The Dynamic Modelmentioning

confidence: 99%

“…The graph is placed on the image and node locations are changed until the total energy of the system is minimal. A semi-stochastic search developed in [6] is carried out where several instances of the model are created and placed arbitrarily in the image. Each instance is treated as initialisation for an iterative search for a location with minimum energy.…”

Section: Mass Points I Act As Sensors S(image[loc(i)])mentioning

confidence: 99%

See 1 more Smart Citation

A weight-adaptive dynamic model for shape segmentation

Toennies

Benedix

2005

“…As far as we know, only [4] use a simple quality of fit measure for estimating the fitness of mass spring model individuals during a genetic approach for object classification. In this case, the quality of fit depends on whether the sensors connected to the masses have high inputs and whether the global scaling of the model does not change.…”

Section: Introductionmentioning

confidence: 99%

Quality of fit of Stable Mass-Spring Models

Pattern Recognit. Image Anal.

2008

Shape models are used for many tasks in modern image analysis, e.g. segmentation, tracking, etc. Rarely, the quality of fit of adapted shape models is automatically determined to decide, whether the model fitting was successful. This paper develops a principal strategy to measure this quality of fit and defines a specific measure in the case of Stable Mass Spring Models, which are especially appropriate for that. The quality of fit measure is tested in two medical segmentation cases (left ventricles in SPECT data and lymph nodes in CT data) and has been shown to work well. Using application specific thresholds on the quality of fit, it could be automatically detected, whether a segmentation was successful or failed.