Discriminative Parameter Estimation for Random Walks Segmentation

Abstract : The Random Walks (RW) algorithm is one of the most e - cient and easy-to-use probabilistic segmentation methods. By combining contrast terms with prior terms, it provides accurate segmentations of medical images in a fully automated manner. However, one of the main drawbacks of using the RW algorithm is that its parameters have to be hand-tuned. we propose a novel discriminative learning framework that estimates the parameters using a training dataset. The main challenge we face is that the training samples are not fully supervised. Speci cally, they provide a hard segmentation of the images, instead of a proba- bilistic segmentation. We overcome this challenge by treating the opti- mal probabilistic segmentation that is compatible with the given hard segmentation as a latent variable. This allows us to employ the latent support vector machine formulation for parameter estimation. We show that our approach signi cantly outperforms the baseline methods on a challenging dataset consisting of real clinical 3D MRI volumes of skeletal muscles.
Type de document :
Communication dans un congrès
16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013), Sep 2013, Nagoya, Japan. 8p, 2013
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00856020
Contributeur : Puneet Kumar Dokania <>
Soumis le : vendredi 30 août 2013 - 12:20:38
Dernière modification le : lundi 1 octobre 2018 - 17:00:03
Document(s) archivé(s) le : jeudi 6 avril 2017 - 11:01:54

Fichiers

learnRW439.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00856020, version 1
  • ARXIV : 1308.6721

Citation

Pierre-Yves Baudin, Danny Goodman, Puneet Kumar, Noura Azzabou, Pierre G. Carlier, et al.. Discriminative Parameter Estimation for Random Walks Segmentation. 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013), Sep 2013, Nagoya, Japan. 8p, 2013. 〈hal-00856020〉

Partager

Métriques

Consultations de la notice

758

Téléchargements de fichiers

208