Exploratory Characterization of Outliers in a Multi-centre 1H-MRS Brain Tumour Dataset

  • Authors:

  • Alfredo Vellido;Margarida Julià-Sapé;Enrique Romero;Carles Arús

  • Affiliations:

  • Dept. de Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya, Barcelona, Spain 08034;Centro de Investigación Biomédica en Red en Bioingeniería, Biomaterialesy, Nanomedicina (CIBER-BBN), Cerdanyola del Vallès, Spain and Grup d'Aplicacions Biomèdiques de la ...;Dept. de Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya, Barcelona, Spain 08034;Grup d'Aplicacions Biomèdiques de la RMN (GABRMN) Departament de Bioquímica i Biología Molecular (BBM). Unitat de Biociències, Universitat Autònoma de Barcelona (UAB), Cer ...

  • Venue:
  • KES '08 Proceedings of the 12th international conference on Knowledge-Based Intelligent Information and Engineering Systems, Part II
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

As part of the AIDTumour research project, the analysis of MRS data corresponding to various tumour pathologies is used to assist expert diagnosis. The high dimensionality of the MR spectra might obscure atypical aspects of the data that would jeopardize their automated classification and, as a result, the process of computer-based diagnostic assistance. In this paper, we put forward a method to overcome this potential problem that combines automatic outlier detection, visualization through dimensionality reduction, and expert opinion.