Segmentation multimodale optimale par coupe de graphe multispectral : applications aux lésions de sclérose en plaques en IRM

Jérémy Lecoeur 1, * Jean-Christophe Ferré 1 Christian Barillot 1
* Corresponding author
1 VisAGeS - Vision, Action et Gestion d'informations en Santé
INSERM - Institut National de la Santé et de la Recherche Médicale : U746, Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : We present an optimized supervised segmentation method from multimodal MRIs. As MR images do not behave as natural images, using a spectral gradient based on a psycho-visual paradigm is sub-optimal. Therefore, we propose to create an optimized colorimetric spectral gradient using multi-modalities MRIs. To that purpose, the algorithm learns the optimized parameters of the spectral gradient based on ground truth which are either phantoms or manual delineations of an expert. Using Dice Similarity Coefficient as a cost function for an optimization algorithm, we were able to compute an optimized gradient and to utilize it in order to segment MRIs with the same kind of modalities. Results show that the optimized gradient matrices perform significantly better segmentations and that the supervized learning of an optimized matrix is a good way to enhance the segmentation method.
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/inria-00449510
Contributor : Jérémy Lecoeur <>
Submitted on : Friday, January 22, 2010 - 10:32:10 AM
Last modification on : Monday, March 4, 2019 - 2:07:47 PM
Long-term archiving on : Thursday, October 18, 2012 - 1:05:08 PM

File

RFIA_optim.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00449510, version 1

Citation

Jérémy Lecoeur, Jean-Christophe Ferré, Christian Barillot. Segmentation multimodale optimale par coupe de graphe multispectral : applications aux lésions de sclérose en plaques en IRM. 17ème conférence en Reconnaissance des Formes et Intelligence Artificielle, Jan 2010, Caen, France. pp.5B-2. ⟨inria-00449510⟩

Share

Metrics

Record views

333

Files downloads

515