Abstract
A fully automatic workflow for Multiple Sclerosis (MS) lesion segmentation is described. Fully automatic means that no user interaction is performed in any of the steps and that all parameters are fixed for all the images processed in beforehand. Our workflow is composed of three steps: an intensity inhomogeneity (IIH) correction, skull-stripping and MS lesions segmentation. A validation comparing our results with two experts is done on MS MRI datasets of 24 MS patients from two different sites.
Keywords
Source Code and Data
No source code files available for this publication.
Reviews
Simon Warfield
Friday 25 July 2008
This paper describes an algorithm for the segmentation of MS lesions that is fully automated.
The approach utilizes a trimmed likelihood estimator to avoid outliers influencing the calculation of the mixture model parameters.
The evaluation of the method indicates it performs well.
Typos:
apperaring - appearing
datasets where - datasets were
Martin Styner
Tuesday 29 July 2008
This paper presents the use of a robust EM classification method to segment MS lesions. The EM classifier needs a prior bias field correction and skull stripping, unlike other methods that incorporate these steps as part of the EM loop. First the normal brain tissue classes are determined via the robust EM, followed by an outlier detection for a rule based MS lesion segmentation.
Good results, but it is not clear what happened with cases UNC 07 and CHB 15 which have an empty image (no lesions).
Well written paper overall, no major revisions needed.