A quantitative comparison of functional MRI cluster analysis

Authors:
Evgenia Dimitriadou;Markus Barth;Christian Windischberger;Kurt Hornik;Ewald Moser
Affiliations:
Institut für Statistik und Wahrscheinlichkeitstheorie, Technische Universität Wien, Wien, Austria;Univ. Klinik für Radiodiagnostik, Medizinische Universität Wien, Wien, Austria;AG NMR, Institut für Medizinische Physik, Medizinische Universität Wien, Wien, Austria;Institut für Statistik und Wahrscheinlichkeitstheorie, Technische Universität Wien, Wien, Austria;Univ. Klinik für Radiodiagnostik, Medizinische Universität Wien, Wien, Austria and AG NMR, Institut für Medizinische Physik, Medizinische Universität Wien, Wien, Austria
Venue:
Artificial Intelligence in Medicine
Year:
2004

Citing 9
Cited 10

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Sequential competitive learning and the fuzzy c-means clustering algorithms

Neural Networks
Voting-Merging: An Ensemble Method for Clustering

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Exploratory analysis of fMRI data by fuzzy clustering: philosophy, strategy, tactics, implementation

Exploratory analysis and data modeling in functional neuroimaging
Globally optimal vector quantizer design by stochastic relaxation

IEEE Transactions on Signal Processing
Exploring regions of interest with cluster analysis (EROICA) using a spectral peak statistic for selecting and testing the significance of fMRI activation time-series

Artificial Intelligence in Medicine
Fuzzy cluster analysis of high-field functional MRI data

Artificial Intelligence in Medicine
EvIdentTM: a functional magnetic resonance image analysis system

Artificial Intelligence in Medicine
`Neural-gas' network for vector quantization and its application to time-series prediction

IEEE Transactions on Neural Networks

Clustering quality based feature selection method

Machine Graphics & Vision International Journal
Parallel adaptive simulated annealing for computer-aided measurement in functional MRI analysis

Expert Systems with Applications: An International Journal
An Integrated Approach for Modeling Learning Patterns of Students in Web-Based Instruction: A Cognitive Style Perspective

ACM Transactions on Computer-Human Interaction (TOCHI)
Visual MRI: Merging information visualization and non-parametric clustering techniques for MRI dataset analysis

Artificial Intelligence in Medicine
A monospectral approach for fMRI analysis using Kohonen self-organised networks and objective dialectical classifiers

International Journal of Innovative Computing and Applications
Resource constraints on computation and communication in the brain

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Extracting activated regions of fMRI data using unsupervised learning

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Clustering of fMRI data using affinity propagation

BI'10 Proceedings of the 2010 international conference on Brain informatics
Exploring functional connectivity networks in fMRI data using clustering analysis

BI'11 Proceedings of the 2011 international conference on Brain informatics
Exploring brain activation patterns during heuristic problem solving using clustering approach

AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The aim of this work is to compare the efficiency and power of several cluster analysis techniques on fully artificial (mathematical) and synthesized (hybrid) functional magnetic resonance imaging (fMRI) data sets. The clustering algorithms used are hierarchical, crisp (neural gas, self-organizing maps, hard competitive learning, k-means, maximin-distance, CLARA) and fuzzy (c-means, fuzzy competitive learning). To compare these methods we use two performance measures, namely the correlation coefficient and the weighted Jaccard coefficient (wJC). Both performance coefficients (PCs) clearly show that the neural gas and the k-means algorithm perform significantly better than all the other methods using our setup. For the hierarchical methods the ward linkage algorithm performs best under our simulation design. In conclusion, the neural gas method seems to be the best choice for fMRI cluster analysis, given its correct classification of activated pixels (true positives (TPs)) whilst minimizing the misclassification of inactivated pixels (false positives (FPs)), and in the stability of the results achieved.