Optimal Gaussian mixture models of tissue intensities in brain MRI of patients with multiple-sclerosis

Authors:
Yiming Xiao;Mohak Shah;Simon Francis;Douglas L. Arnold;Tal Arbel;D. Louis Collins
Affiliations:
Montreal Neurological Institute, McGill University, Canada;Centre for Intelligent Machines, McGill University, Canada and NeuroRx Research, Montreal, Canada;Montreal Neurological Institute, McGill University, Canada and NeuroRx Research, Montreal, Canada;Montreal Neurological Institute, McGill University, Canada and NeuroRx Research, Montreal, Canada;Centre for Intelligent Machines, McGill University, Canada;Montreal Neurological Institute, McGill University, Canada
Venue:
MLMI'10 Proceedings of the First international conference on Machine learning in medical imaging
Year:
2010

Citing 2
Cited 0

Empirical Evaluation of Dissimilarity Measures for Color and Texture

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Tissue classification of noisy MR brain images using constrained GMM

MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Brain tissue segmentation is important in studying markers in human brain Magnetic Resonance Images (MRI) of patients with diseases such as Multiple Sclerosis (MS). Parametric segmentation approaches typically assume unimodal Gaussian distributions on MRI intensities of individual tissue classes, even in applications on multi-spectral images. However, this assumption has not been rigorously verified especially in the context of MS. In this work, we evaluate the local MRI intensities of both healthy and diseased brain tissues of 21 multi-spectral MRIs (63 volumes in total) of MS patients for adherence to this assumption. We show that the tissue intensities are not uniform across the brain and vary across (anatomical) regions of the brain. Consequently, we show that Gaussian mixtures can better model the multi-spectral intensities. We utilize an Expectation Maximization (EM) based approach to learn the models along with a symmetric Jeffreys divergence criterion to study differences in intensity distributions. The effects of these findings are also empirically verified on automatic segmentation of brains with MS.