Authors:
Raúl Cruz-Barbosa
and
Alfredo Vellido
Affiliation:
Universitat Politècnica de Catalunya, Spain
Keyword(s):
Brain tumours, MRS, Generative Topographic Mapping, two-stage clustering, outliers.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Computer Vision, Visualization and Computer Graphics
;
Data Manipulation
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
Abstract:
This paper analyzes, through clustering and visualization, Magnetic Resonance spectra of a complex multi-center human brain tumour dataset. Clustering is performed as a two-stage process, in which the models used in the first stage are variants of Generative Topographic Mapping (GTM). Class information-enriched variants of GTM are used to obtain a primary cluster description of the data. The number of clusters used by GTM is usually large and does not necessarily correspond to the overall class structure. Consequently, in a second stage, clusters are agglomerated using K-means with different initialization strategies, some of them defined ad hoc for the GTM models. We evaluate if the use of class information influence the brain tumour cluster-wise class separability resulting from the process. We also resort to a robust variant of GTM that detects outliers while effectively minimizing their negative impact in the clustering process.