6533b836fe1ef96bd12a0ba5

RESEARCH PRODUCT

A Novel Semi-Supervised Methodology for Extracting Tumor Type-Specific MRS Sources in Human Brain Data

subject

description

Background: The clinical investigation of human brain tumors often starts with a non-invasive imaging study, providing \ud information about the tumor extent and location, but little insight into the biochemistry of the analyzed tissue. Magnetic \ud Resonance Spectroscopy can complement imaging by supplying a metabolic fingerprint of the tissue. This study analyses \ud single-voxel magnetic resonance spectra, which represent signal information in the frequency domain. Given that a single \ud voxel may contain a heterogeneous mix of tissues, signal source identification is a relevant challenge for the problem of\ud tumor type classification from the spectroscopic signal.\ud Methodology/Principal Findings: Non-negative matrix factorization techniques have recently shown their potential for the \ud identification of meaningful sources from brain tissue spectroscopy data. In this study, we use a convex variant of these \ud methods that is capable of handling negatively-valued data and generating sources that can be interpreted as tumor class \ud prototypes. A novel approach to convex non-negative matrix factorization is proposed, in which prior knowledge about \ud class information is utilized in model optimization. Class specific information is integrated into this semi-supervised process \ud by setting the metric of a latent variable space where the matrix factorization is carried out. The reported experimental \ud study comprises 196 cases from different tumor types drawn from two international, multi-center databases. The results \ud indicate that the proposed approach outperforms a purely unsupervised process by achieving near perfect correlation of the extracted sources with the mean spectra of the tumor types. It also improves tissue type classification. \ud Conclusions/Significance: We show that source extraction by unsupervised matrix factorization benefits from the\ud integration of the available class information, so operating in a semi-supervised learning manner, for discriminative source identification and brain tumor labeling from single-voxel spectroscopy data. We are confident that the proposed methodology has wider applicability for biomedical signal processing.