Abstract #1727

An Efficient Global Clustering Algorithm for the Identification of Functional Connectivity from BOLD FMRI

Andrew Ryan McIntyre^1,2, Xiaowei Song^1,3, Evangelos E. Milios², Malcolm I. Heywood², Alma Major¹, Ryan D'Arcy^1,4, Kenneth Rockwood^3,5

¹Institute for Biodiagnostics - Atlantic, National Research Council, Halifax, NS, Canada; ²Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada; ³Medicinie, Dalhousie University, Halifax, NS, Canada; ⁴Psychology and Neuroscience, Dalhousie University, Halifax, NS, Canada; ⁵Centre for Health Care for the Elderly, QEII Health Sciences Centre, Halifax, NS, Canada

A clustering approach is proposed for globally identifying functional connectivity patterns from resting state fMRI data. The Self-Organizing Map algorithm is directly applied to time course data to reduce the input space for efficient application of the k-means algorithm. Hard clusters are selected and correlated time course patterns are assigned to each cluster. Results on two benchmark data sets indicate that the approach is able to efficiently and accurately identify embedded target time course patterns with low variation between initializations.