Modelling of Magnetic Resonance Spectra Using Mixtures for Binned and Truncated Data

Authors:
Juan M. Garcia-Gomez;Montserrat Robles;Sabine Huffel;Alfons Juan-Císcar
Affiliations:
BET-IBM, Polytechnical University of Valencia,;BET-IBM, Polytechnical University of Valencia,;Katholieke Universiteit Leuven, Dept. of Electrical Engineering, ESAT-SCD(SISTA),;DSIC, Polytechnical University of Valencia,
Venue:
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part II
Year:
2007

Citing 2
Cited 0

Maximum Likelihood Estimation of Mixture Densities for Binned and Truncated Multivariate Data

Machine Learning - Special issue: Unsupervised learning
A classification EM algorithm for binned data

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

Magnetic Resonance Spectroscopy (MRS) provides the biochemical composition of a tissue under study. This information is useful for the in-vivo diagnosis of brain tumours. Prior knowledge of the relative position of the organic compound contributions in the MRS suggests the development of a probabilistic mixture model and its EM-based Maximum Likelihood Estimation for binned and truncated data. Experiments for characterizing and classifying Short Time Echo (STE) spectra from brain tumours are reported.