Ortega-Martorell, S and Ruiz, H and Vellido, A and Olier, I and Romero, E and Julia-Sape, M and Martin, JD and Jarman, I and Arus, C and Lisboa, P (2013) A Novel Semi-Supervised Methodology for Extracting Tumor Type-Specific MRS Sources in Human Brain Data. PLOS ONE, 8 (12). pp. 1-14. ISSN 1932-6203
A novel semi-supervised methodology for extracting tumor type-specific MRS sources in human brain data..pdf - Published Version
Available under License Creative Commons Attribution.
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 analyses
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/Principal Findings: 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/Significance: 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.
|Uncontrolled Keywords:||MD Multidisciplinary|
|Subjects:||R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer)
R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
|Publisher:||Public Library Science|
|Date Deposited:||07 May 2015 14:17|
|Last Modified:||07 Oct 2016 10:37|
|DOI or Identification number:||10.1371/journal.pone.0083773|
Actions (login required)