Per citar aquest document:
Scopus: 7 cites, Web of Science: 7 cites,
A Novel Semi-Supervised Methodology for Extracting Tumor Type-Specific MRS Sources in Human Brain Data
Ortega-Martorell, Sandra (Liverpool John Moores University. Department of Mathematics and Statistics)
Ruiz, Héctor (Liverpool John Moores University. Department of Mathematics and Statistics)
Vellido, Alfredo (Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics)
Olier, Iván (University of Manchester. Institute of Population Health.)
Romero, Enrique (Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics)
Julià Sapé, Ma. Margarita (Centro de Investigación Biomédica en Red en Bioingeniería, Biomateriales y Nanomedicina (CIBER-BBN))
Martín, José D. (Universidad de Valencia. Departamento de Ingeniería Electrónica.)
Jarman, Ian H. (Liverpool John Moores University. Department of Mathematics and Statistics)
Arús i Caraltó, Carles (Universitat Autònoma de Barcelona. Departament de Bioquímica i de Biologia Molecular)
Lisboa, Paulo J. G. (Liverpool John Moores University. Department of Mathematics and Statistics)

Data: 2013
Resum: Background: the clinical investigation of human brain tumors often starts with a non-invasive imaging study, providing information about the tumor extent and location, but little insight into the biochemistry of the analyzed tissue. Magnetic Resonance Spectroscopy can complement imaging by supplying a metabolic fingerprint of the tissue. This study analyzes single-voxel magnetic resonance spectra, which represent signal information in the frequency domain. Given that a single voxel may contain a heterogeneous mix of tissues, signal source identification is a relevant challenge for the problem of tumor type classification from the spectroscopic signal. Methodology: non-negative matrix factorization techniques have recently shown their potential for the identification of meaningful sources from brain tissue spectroscopy data. In this study, we use a convex variant of these methods that is capable of handling negatively-valued data and generating sources that can be interpreted as tumor class prototypes. A novel approach to convex non-negative matrix factorization is proposed, in which prior knowledge about class information is utilized in model optimization. Class-specific information is integrated into this semi-supervised process by setting the metric of a latent variable space where the matrix factorization is carried out. The reported experimental study comprises 196 cases from different tumor types drawn from two international, multi-center databases. The results 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. Conclusions: We show that source extraction by unsupervised matrix factorization benefits from the 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.
Drets: Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original. Creative Commons
Llengua: Anglès
Document: article ; recerca ; publishedVersion
Matèria: Lipid signaling ; Algorithms ; Prototypes ; Data acquisition ; Magnetic resonance spectroscopy ; Cancer detection and diagnosis ; Glioblastoma multiforme ; Magnetic resonance imaging
Publicat a: PLoS one, Vol. 8 Issue 12 (December 2013) , p. e83773, ISSN 1932-6203

DOI: 10.1371/journal.pone.0083773
PMID: 24376744

14 p, 1.1 MB

El registre apareix a les col·leccions:
Articles > Articles de recerca
Articles > Articles publicats

 Registre creat el 2015-10-20, darrera modificació el 2016-10-04

   Favorit i Compartir