A Mumford-Shah Functional based Variational Model with Contour, Shape, and Probability Prior information for Prostate Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

A Mumford-Shah Functional based Variational Model with Contour, Shape, and Probability Prior information for Prostate Segmentation

Résumé

Inter patient shape, size and intensity variations of the prostate in transrectal ultrasound (TRUS) images challenge automatic segmentation of the prostate. In this paper we propose a variational model driven by Mumford-Shah (MS) functional for segmenting the prostate. Parametric representation of the implicit curve is derived from principal component analysis (PCA) of the signed distance representation of the labeled training data to impose shape prior. Posterior probability of the prostate region determined from random forest classification facilitates initialization and propagation of our model in a MS energy minimization framework. The proposed method achieves mean Dice similarity coefficient (DSC) value of 0.97±0.01, with a mean Hausdorff distance (HD) value of 1.73±0.24 mm when validated with 24 images from 6 datasets in a leave-one-patient-out validation framework. The model achieves statistically significant t-test p-value<0.0001 in mean DSC and mean HD values compared to traditional statistical models of shape and appearance.
Fichier principal
Vignette du fichier
ICPR2012_Soumya4.pdf (406.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00710957 , version 1 (22-06-2012)

Identifiants

  • HAL Id : hal-00710957 , version 1

Citer

Soumya Ghose, Jhimli Mitra, Arnau Oliver, Robert Marti, Xavier Llado, et al.. A Mumford-Shah Functional based Variational Model with Contour, Shape, and Probability Prior information for Prostate Segmentation. IAPR International Conference on Pattern Recognition, Nov 2012, Tsukba, Japan. ⟨hal-00710957⟩
125 Consultations
73 Téléchargements

Partager

Gmail Facebook X LinkedIn More