Nonnegative matrix factorization for rapid recovery of constituent spectra in magnetic resonance chemical shift imaging of the brain.

Publication Type	Academic Article
Authors	Sajda P, Du S, Brown T, Stoyanova R, Shungu D, Mao X, Parra L
Journal	IEEE Trans Med Imaging
Volume	23
Issue	12
Pagination	1453-65
Date Published	12/01/2004
ISSN	0278-0062
Keywords	Algorithms, Brain, Image Interpretation, Computer-Assisted, Magnetic Resonance Spectroscopy, Phosphorus Compounds, Spectrum Analysis
Abstract	We present an algorithm for blindly recovering constituent source spectra from magnetic resonance (MR) chemical shift imaging (CSI) of the human brain. The algorithm, which we call constrained nonnegative matrix factorization (cNMF), does not enforce independence or sparsity, instead only requiring the source and mixing matrices to be nonnegative. It is based on the nonnegative matrix factorization (NMF) algorithm, extending it to include a constraint on the positivity of the amplitudes of the recovered spectra. This constraint enables recovery of physically meaningful spectra even in the presence of noise that causes a significant number of the observation amplitudes to be negative. We demonstrate and characterize the algorithm's performance using 31P volumetric brain data, comparing the results with two different blind source separation methods: Bayesian spectral decomposition (BSD) and nonnegative sparse coding (NNSC). We then incorporate the cNMF algorithm into a hierarchical decomposition framework, showing that it can be used to recover tissue-specific spectra given a processing hierarchy that proceeds coarse-to-fine. We demonstrate the hierarchical procedure on 1H brain data and conclude that the computational efficiency of the algorithm makes it well-suited for use in diagnostic work-up.
DOI	10.1109/TMI.2004.834626
PubMed ID	15575404