Outlier exploration and diagnostic classification of a multi-centre 1H-MRS brain tumour database

Alfredo Vellido, Enrique Romero, Felix F. González-Navarro, Lluís A. Belanche-Muñoz, Margarida Juliá-Sapé, Carles Arús

Research output: Contribution to journalArticleResearchpeer-review

27 Citations (Scopus)

Abstract

Non-invasive techniques such as magnetic resonance spectroscopy (MRS) are often required for assisting the diagnosis of tumours. Radiologists are not always accustomed to make sense of the biochemical information provided by MRS and they may benefit from computer-based support in their decision making. The high dimensionality of the MR spectra obscures atypical aspects of the data that may jeopardize their classification. In this study, we describe a method to overcome this problem that combines nonlinear dimensionality reduction, outlier detection, and expert opinion. MR spectra subsequently undergo a feature selection process followed by classification. The impact of outlier removal on classification performance is assessed. © 2009 Elsevier B.V.
Original languageEnglish
Pages (from-to)3085-3097
JournalNeurocomputing
Volume72
Issue number13-15
DOIs
Publication statusPublished - 1 Jan 2009

Keywords

  • Brain tumours
  • Feature selection
  • Medical decision support systems
  • Nonlinear dimensionality reduction
  • Outlier detection
  • Proton magnetic resonance spectroscopy

Fingerprint Dive into the research topics of 'Outlier exploration and diagnostic classification of a multi-centre <sup>1</sup>H-MRS brain tumour database'. Together they form a unique fingerprint.

Cite this