Knee reconstruction through efficient linear programming

Abstract : In this paper we propose a novel method to recover the 3D shape of the knee and of the prosthesis for the patients that have undergone total knee replacement surgery. We address this using a set of 2D X-Ray images of the knee taken from different viewpoints around it. The problem is then casted to a multiview stereo reconstruction problem and we consider an energy-minimization approach to recover the bone structure. This function is designed to recover a 3D surface which minimizes image and shape-based terms. The cost related to data is defined through the projections of the 3D surface onto 2D image planes while the prior-knowledge is introduced using a 3D model of the knee. The use of Markov Random Fileds as well as recent advances in discrete optimization and in particular the state-of-the-art Fast PD optimization algorithm is considered towards optimal reconstruction. Promising results demonstrate the potentials of our method.
Type de document :
Communication dans un congrès
ISBI, 2008, France. pp.664 - 667, 2008
Liste complète des métadonnées
Contributeur : Enzo Ferrante <>
Soumis le : samedi 14 décembre 2013 - 12:32:09
Dernière modification le : vendredi 15 février 2019 - 13:58:08


  • HAL Id : hal-00918719, version 1



Mihai Sardarescu, Nikos Paragios, Nikos Komodakis, R. Raymond, P. Hernigou, et al.. Knee reconstruction through efficient linear programming. ISBI, 2008, France. pp.664 - 667, 2008. 〈hal-00918719〉



Consultations de la notice