A COMPARISON OF FOUR UNSUPERVISED CLUSTERING ALGORITHMS FOR SEGMENTING BRAIN TISSUE IN MULTI-SPECTRAL MR DATA

Maria C. Valdés Hernández, J. M. Wardlaw, Sean Murphy

2010

Abstract

The effects of atrophy and diffusion of the boundary between grey and white matter, common in elder individuals, represents a difficult problem for segmentation, not observed in healthy younger adults. The aim of this study is to evaluate four well-known unsupervised clustering algorithms in brain tissue segmentation using MR scans with atrophies and lesions. The brain is segmented into 3 different types: white matter, grey matter and CSF. We used four MR sequences: T1W, T2W, T2*W and FLAIR to classify each voxel in the image. No spatial information was used. The algorithms tested were k - means, EM (Gaussian mixture), MVQ (minimum variance quantisation) and Mean Shift. The datasets were acquired from an aged cohort (> 70 years). The resulting segmentations were quantitatively compared to expertly collected ground truth on 12 datasets, using the Dice coefficient as an overlap measure. The classification algorithms could be ranked in the following order: MVQ, k - means, EM and MeanShift from best to worst. The MVQ algorithm did best of all with over a .9 Dice overlap on CSF, and over .8 on white matter.

Paper Citation

in Harvard Style

C. Valdés Hernández M., M. Wardlaw J. and Murphy S. (2010). A COMPARISON OF FOUR UNSUPERVISED CLUSTERING ALGORITHMS FOR SEGMENTING BRAIN TISSUE IN MULTI-SPECTRAL MR DATA . In Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: Special Session MIAD, (BIOSTEC 2010) ISBN 978-989-674-018-4, pages 507-514. DOI: 10.5220/0002766005070514

in Bibtex Style

@conference{special session miad10,
author={Maria C. Valdés Hernández and J. M. Wardlaw and Sean Murphy},
title={A COMPARISON OF FOUR UNSUPERVISED CLUSTERING ALGORITHMS FOR SEGMENTING BRAIN TISSUE IN MULTI-SPECTRAL MR DATA},
booktitle={Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: Special Session MIAD, (BIOSTEC 2010)},
year={2010},
pages={507-514},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002766005070514},
isbn={978-989-674-018-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: Special Session MIAD, (BIOSTEC 2010)
TI - A COMPARISON OF FOUR UNSUPERVISED CLUSTERING ALGORITHMS FOR SEGMENTING BRAIN TISSUE IN MULTI-SPECTRAL MR DATA
SN - 978-989-674-018-4
AU - C. Valdés Hernández M.
AU - M. Wardlaw J.
AU - Murphy S.
PY - 2010
SP - 507
EP - 514
DO - 10.5220/0002766005070514