Exploratory characterization of outliers in a multi-centre 1H-MRS brain tumour dataset

Vellido Alcacena, Alfredo; Julià Sapé, Margarida; Romero Merino, Enrique; Arús, Carles

doi:10.1007/978-3-540-85565-1_24

View/Open

VellidoetalKES08print.pdf (509,7Kb) (Restricted access) Request copy

View Usage Statistics

Cita com:

Show full item record

Vellido Alcacena, Alfredo

Julià Sapé, Margarida

Romero Merino, Enrique

Arús, Carles

Document typeArticle

Defense date2008-09

Rights accessRestricted access - publisher's policy

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder

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.

CitationVellido, A. [et al.]. Exploratory characterization of outliers in a multi-centre 1H-MRS brain tumour dataset. "Lecture notes in computer science", Setembre 2008, vol. 5178, p. 189-196.

URIhttp://hdl.handle.net/2117/10944

DOI10.1007/978-3-540-85565-1_24

ISSN0302-9743

Collections

View Usage Statistics

Show full item record

Files	Description	Size	Format	View
VellidoetalKES08print.pdf		509,7Kb	PDF	Restricted access

UPCommons. Global access to UPC knowledge

Exploratory characterization of outliers in a multi-centre 1H-MRS brain tumour dataset

View/Open

Browse