MICCAI 2013 - LNCS 8149-8151

Discriminative Parameter Estimation for Random Walks Segmentation

Pierre-Yves Baudin^1,2,3,4,5,6, Danny Goodman^1,2,3, Puneet Kumar^1,2,3, Noura Azzabou^4,5,6, Pierre G. Carlier^4,5,6, Nikos Paragios^1,2,3, and M. Pawan Kumar^1,2,3

¹Center for Visual Computing, École Centrale Paris, France

²Université Paris-Est, LIGM (UMR CNRS), École des Ponts ParisTech, France

³Équipe Galen, INRIA, Saclay, France

⁴Institute of Myology, Paris, France

⁵CEA, I2 BM, MIRCen, IdM NMR Laboratory, Paris, France

⁶UPMC University Paris 06, Paris, France

Abstract. The Random Walks (RW) algorithm is one of the most efficient 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. Specifically, they provide a hard segmentation of the images, instead of a probabilistic segmentation. We overcome this challenge by treating the optimal 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 significantly outperforms the baseline methods on a challenging dataset consisting of real clinical 3D MRI volumes of skeletal muscles.

LNCS 8151, p. 219 ff.

Full article in PDF | BibTeX