Adaptive weighted fusion of multiple MR sequences for brain lesion segmentation

Florence Forbes 1, * Senan Doyle 1 Daniel Garcia-Lorenzo 2 Christian Barillot 2 Michel Dojat 3
* Corresponding author
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 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 propose a technique for fusing the output of multiple Magnetic Resonance (MR) sequences to robustly and accurately segment brain lesions. It is based on a Bayesian multi-sequence Markov model that includes weight parameters to account for the relative importance and control the impact of each sequence. The Bayesian framework has the advantage of allowing 1) the incorporation of expert knowledge on the a priori relevant information content of each sequence and 2) a weighting scheme which is modified adaptively according to the data and the segmentation task under consideration. The model, applied to the detection of multiple sclerosis and stroke lesions shows promising results.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://www.hal.inserm.fr/inserm-00723807
Contributor : Christian Barillot <>
Submitted on : Tuesday, August 14, 2012 - 11:55:25 AM
Last modification on : Monday, March 4, 2019 - 2:08:22 PM
Long-term archiving on : Thursday, November 15, 2012 - 2:21:55 AM

File

isbi2010_FF.pdf
Files produced by the author(s)

Identifiers

Citation

Florence Forbes, Senan Doyle, Daniel Garcia-Lorenzo, Christian Barillot, Michel Dojat. Adaptive weighted fusion of multiple MR sequences for brain lesion segmentation. 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Apr 2010, Rotterdam, Netherlands. pp.69-72, ⟨10.1109/ISBI.2010.5490413⟩. ⟨inserm-00723807⟩

Share

Metrics

Record views

886

Files downloads

611