This paper presents the implementation and validation of a new 3D deformable model method, based on the Mumford-Shah functional for segmentation of three-dimensional real-time ultrasound. An experiment on 10 patients with primary hypertension was carried out to compare three segmentation methods for quantification of right and left ventricular ejection fraction: (1) manual tracing by an expert cardiologist, (2) 2D parametric deformable model, and (3) 3D implicit deformable model implemented with a level set framework. Deformable model segmentations were performed on denoised data using a (3D+Time) brushlet expansion. The clinical study showed superior performance of the deformable model in assessing ejection fraction when compared to MRI measures. It also showed that the three-dimensional deformable model improved EF measures, which is explained by a more accurate segmentation of small and convoluted ventricular shapes when integrating the third spatial dimension.
Segmentation of RT3D ultrasound with implicit deformable models without gradients
01.01.2003
449551 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Segmentation of RT3D Ultrasound with Implicit Deformable Models without Gradients
British Library Conference Proceedings | 2003
|Algorithms for Implicit Deformable Models
British Library Conference Proceedings | 1995
|Algorithms for implicit deformable models
IEEE | 1995
|Directional adaptive deformable models for segmentation
British Library Online Contents | 1998
|Implicit Edge-Based Gradients for Simplex Grids
AIAA | 2020
|