On the improvement of brain tumour data clustering using class information

Authors:
Raúl Cruz;Alfredo Vellido
Affiliations:
Soft Computing Group. Univ. Politècnica de Catalunya, Barcelona, Spain and Grup d'Aplicacions Biomèdiques de la RMN, Univ. Autònoma de Barcelona, Spain;Soft Computing Group. Univ. Politècnica de Catalunya, Barcelona, Spain
Venue:
Proceedings of the 2006 conference on STAIRS 2006: Proceedings of the Third Starting AI Researchers' Symposium
Year:
2006

Citing 2
Cited 2

GTM: the generative topographic mapping

Neural Computation
Missing data imputation through GTM as a mixture of t-distributions

Neural Networks

On the Initialization of Two-Stage Clustering with Class-GTM

Current Topics in Artificial Intelligence
On the influence of class information in the two-stage clustering of a human brain tumour dataset

MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Cluster analysis can benefit from the use of class labels, if these are available, in a semi-supervised approach. In this study, we propose the integration of class information in the clustering of Magnetic Resonance Spectra (MRS) corresponding to human brain tumours using an extension of Generative Topographic Mapping (GTM) that behaves robustly in the presence of outliers.