Combining Robust Expectation Maximization and Mean Shift algorithms for Multiple Sclerosis Brain Segmentation - Inserm - Institut national de la santé et de la recherche médicale Access content directly
Conference Papers Year : 2008

Combining Robust Expectation Maximization and Mean Shift algorithms for Multiple Sclerosis Brain Segmentation

Abstract

A new algorithm for segmentation of white matter lesions and normal appearing brain tissues in Multiple Sclerosis (MS) is presented. Two different segmentation methods are combined in order to have a better and more meaningful segmentation. On the one hand, a local segmentation approach, the Mean Shift, is used to generate local regions in our images. On the other hand, a variant of the Expectation Maximization is employed to classify these regions as Normal Appearing Brain Tissues (NABT) or lesions. Validation of this method is performed with synthetic and real data. The output is a more powerful algorithm that employs at the same time global and local information to improve image segmentation.

Domains

Bioengineering
Fichier principal
Vignette du fichier
miccai-ms4ms.pdf (161.22 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inserm-00421706 , version 1 (02-10-2009)

Identifiers

  • HAL Id : inserm-00421706 , version 1

Cite

Daniel García-Lorenzo, Sylvain Prima, D. Louis Collins, Douglas L. Arnold, Sean Patrick Morrissey, et al.. Combining Robust Expectation Maximization and Mean Shift algorithms for Multiple Sclerosis Brain Segmentation. MICCAI workshop on Medical Image Analysis on Multiple Sclerosis (validation and methodological issues) (MIAMS'2008), Sep 2008, New York, United States. pp.82-91. ⟨inserm-00421706⟩
281 View
312 Download

Share

Gmail Facebook X LinkedIn More