Joint Tumor Segmentation and Dense Deformable Registration of Brain MR Images

Abstract : In this paper we propose a novel graph-based concurrent registration and segmentation framework. Registration is modeled with a pairwise graphical model formulation that is modular with respect to the data and regularization term. Segmentation is addressed by adopt- ing a similar graphical model, using image-based classi cation techniques while producing a smooth solution. The two problems are coupled via a relaxation of the registration criterion in the presence of tumors as well as a segmentation through a registration term aiming the separation be- tween healthy and diseased tissues. E cient linear programming is used to solve both problems simultaneously. State of the art results demon- strate the potential of our method on a large and challenging low-grade glioma data set.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-00773618
Contributor : Sarah Parisot <>
Submitted on : Monday, January 14, 2013 - 1:56:22 PM
Last modification on : Thursday, February 7, 2019 - 5:29:16 PM
Document(s) archivé(s) le : Saturday, April 1, 2017 - 4:28:41 AM

File

MICCAI12_Parisot.pdf
Files produced by the author(s)

Identifiers

Citation

Sarah Parisot, Hugues Duffau, Stéphane Chemouny, Nikos Paragios. Joint Tumor Segmentation and Dense Deformable Registration of Brain MR Images. MICCAI - 15th International Conference on Medical Image Computing and Computer-Assisted Intervention - 2012, Oct 2012, Nice, France. pp.651-658, ⟨10.1007/978-3-642-33418-4_80⟩. ⟨hal-00773618⟩

Share

Metrics

Record views

531

Files downloads

353