|
| << vorige | volgende >> |
Tijdschrift beschrijving
Alle jaargangen van het bijbehorende tijdschrift
Alle afleveringen van het bijbehorende jaargang
Alle artikelen van de bijbehorende aflevering
Details van artikel 68 van 122 gevonden artikelen
| Titel: |
GAUSSIAN MIXTURE MODEL BASED LEVEL SET TECHNIQUE FOR AUTOMATED SEGMENTATION OF CARDIAC MR IMAGES |
| Auteur: |
G. Dharanibai, J. P. Raina |
| Verschenen in: |
International journal of engineering science and technology |
| Paginering: | Jaargang 3 (2011) nr. 4 pagina's 2970-2976 |
| Jaar: |
2011 |
| Inhoud: |
In this paper we propose a Gaussian Mixture Model (GMM) integrated level set method for automated segmentation of left ventricle (LV), right ventricle (RV) and myocardium from short axis views of cardiacmagnetic resonance image. By fitting GMM to the image histogram, global pixel intensity characteristics of the blood pool, myocardium and background are estimated. GMM provides initial segmentation andthe segmentation solution is regularized using level set. Parameters for controlling the level set evolution are automatically estimated from the Bayesian inference classification of pixels. We propose a new speed function that combines edge and region information that stops the evolving level set at the myocardial boundary. Segmentation efficacy is analyzed qualitatively via visual inspection. Results show the improved performance of our of proposed speed function over the conventional Bayesian driven adaptive speed function in automatic segmentation of myocardium |
| Uitgever: |
Engg Journals Publication (provided by DOAJ) |
| Bronbestand: |
Elektronische Wetenschappelijke Tijdschriften |
Details van artikel 68 van 122 gevonden artikelen
| << vorige | volgende >> |