A non-local fuzzy segmentation method: Application to brain MRI

Benoît Caldairou 1 François Rousseau 1 Nicolas Passat 1 Piotr Habas 2 Colin Studholme 2 Christian Heinrich 1
1 LSIIT - Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection
2 Biomedical Image Computing Group
Abstract : The Fuzzy C-Means algorithm is a widely used and flexible approach for brain tissue segmentation from 3D MRI. Despite its recent enrichment by addition of a spatial dependency to its formulation, it remains quite sensitive to noise. In order to improve its reliability in noisy contexts, we propose a way to select the most suitable example regions for regularisation. This approach inspired by the Non-Local Mean strategy used in image restoration is based on the computation of weights modelling the grey-level similarity between the neighbourhoods being compared. Experiments were performed on MRI data and results illustrate the usefulness of the approach in the context of brain tissue classification.
Keywords : fuzzy clustering regularisation non-local processing image segmentation MRI
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download
https://hal.univ-reims.fr/hal-01695014
Contributor : Nicolas Passat <>
Submitted on : Saturday, March 3, 2018 - 4:54:15 PM
Last modification on : Wednesday, August 7, 2019 - 12:16:02 PM
Long-term archiving on : Monday, June 4, 2018 - 3:57:02 PM

File

Caldairou CAIP 2009.pdf
Files produced by the author(s)

Identifiers

Collections

URCA

Citation

Benoît Caldairou, François Rousseau, Nicolas Passat, Piotr Habas, Colin Studholme, et al.. A non-local fuzzy segmentation method: Application to brain MRI. International Conference on Computer Analysis of Images and Patterns (CAIP), 2009, Münster, Germany. pp.606-613, ⟨10.1007/978-3-642-03767-2_74⟩. ⟨hal-01695014⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

75

Files downloads

96

 

HAL-contact@univ-reims.fr