The MIDAS Journal logo

The MIDAS Journal

Home

Multiple Sclerosis Lesion Segmentation Using Statistical and Topological Atlases

Shiee, Navid, Bazin, Pierre-Louis, Pham, Dzung L.
Johns Hopkins University
The MIDAS Journal logo

Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/1442
New: Prefer using the following doi: https://doi.org/10.54294/i1vy9q
Published in The MIDAS Journal - MICCAI 2008 Workshop: MS Lesion Segmentation.
Submitted by Navid Shiee on 2008-10-02 16:13:54.

This paper presents a new fully automatic method for segmentation of brain images that possess multiple sclerosis (MS) lesions. Multichannel magnetic resonance images are used to delineate multiple sclerosis lesions while segmenting the brain into its major structures. The method is an atlas based segmentation technique employing a topological atlas as well as a statistical atlas. An advantage of this approach is that all segmented structures are topologically constrained, thereby allowing subsequent processing with cortical unfolding or diffeomorphic shape analysis techniques. Validation on data from two studies demonstrates that the method has an accuracy comparable with other MS lesion segmentation methods, while simultaneously segmenting the whole brain.