Exploring functional connectivity networks in fMRI data using clustering analysis

Authors:
Dazhong Liu;Ning Zhong;Yulin Qin
Affiliations:
International WIC Institute, Beijing University of Technology, Beijing China and School of Mathematics and Computer Science, Hebei University, Baoding China;International WIC Institute, Beijing University of Technology, Beijing China and Dept. of Life Science and Informatics, Maebashi Institute of Technology, Maebashi Japan;International WIC Institute, Beijing University of Technology, Beijing China
Venue:
BI'11 Proceedings of the 2011 international conference on Brain informatics
Year:
2011

Citing 7
Cited 0

Learning to Decode Cognitive States from Brain Images

Machine Learning
Top 10 algorithms in data mining

Knowledge and Information Systems
Brain Activation Detection by Neighborhood One-Class SVM

WI-IATW '07 Proceedings of the 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops
Web Page Clustering via Partition Adaptive Affinity Propagation

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Magnetic Resonance Image Segmentation Based on Affinity Propagation

GCIS '09 Proceedings of the 2009 WRI Global Congress on Intelligent Systems - Volume 04
Comparison of two exploratory data analysis methods for fMRI: unsupervised clustering versus independent component analysis

IEEE Transactions on Information Technology in Biomedicine
A quantitative comparison of functional MRI cluster analysis

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Some approaches have been proposed for exploring functional brain connectivity networks from functional magnetic resonance imaging (fMRI) data. Based on a popular algorithm K-means and an effective clustering algorithm called Affinity Propagation (AP), a combined clustering method to explore the functional brain connectivity networks is presented. In the proposed method, K-means is used for data reduction and AP is used for clustering. Without setting the seed of ROI in advance, the proposed method is especially appropriate for the analysis of fMRI data collected with a periodic experimental paradigm. The validity of the proposed method is illustrated by experiments on a simulated dataset and a human dataset. Receiver operating characteristic (ROC) analysis was performed on the simulated dataset. Results show that this method can efficiently and robustly detect the actual functional response with typical signal changes in the aspect of noise ratio, phase and amplitude. On the human dataset, the proposed method discovered brain networks which are compatible with the findings of previous studies.