Author:

Keywords:

SISTA, Science & Technology, Technology, Physical Sciences, Automation & Control Systems, Chemistry, Analytical, Computer Science, Artificial Intelligence, Instruments & Instrumentation, Mathematics, Interdisciplinary Applications, Statistics & Probability, Chemistry, Computer Science, Mathematics, blind source separation, HR-MAS, necrosis, cellularity, tumor tissue abundancy, INDEPENDENT COMPONENT ANALYSIS, MAGNETIC-RESONANCE-SPECTROSCOPY, CONSTRAINED LEAST-SQUARES, PROTON MR SPECTROSCOPY, VIVO H-1 MRS, EX-VIVO, MATRIX FACTORIZATION, CLASSIFICATION, QUANTIFICATION, IDENTIFICATION, 0301 Analytical Chemistry, Analytical Chemistry, 3401 Analytical chemistry

Abstract:

Given high-resolution magic angle spinning (HR-MAS) spectra from several glial tumor subjects, our goal is to differentiate between tumor tissue types by separating the different sources that contribute to the profile of each spectrum. Blind source separation techniques are applied for obtaining characteristic profiles for necrosis, highly cellular tumor and border tumor tissue and providing the contribution (abundance) of each of these tumor tissue types to the profile of each spectrum. The problem is formulated as a non-negative source separation problem. Non-negative matrix factorization, convex analysis of non-negative sources and non-negative independent component analysis methods are considered. The results are in agreement with the pathology obtained by the histopathological examination that succeeded the HR-MAS measurements. Furthermore, an analysis to verify to which extent the dimension of the input space, the input features and the number of sources to be extracted from the HR-MAS data could influence the performance of the source separation is presented. © 2012 John Wiley & Sons, Ltd.