Abstract
Exploratory data-driven methods such as unsupervised clustering and independent component analysis (ICA) are considered to be hypothesis-generating procedures and are complementary to the hypothesis-led statistical inferential methods in functional magnetic resonance imaging (fMRI). Recently, a new paradigm in ICA emerged, that of finding "clusters" of dependent components. This intriguing idea found its implementation into two new ICA algorithms: tree-dependent and topographic ICA. For fMRI, this represents the unifying paradigm of combining two powerful exploratory data analysis methods, ICA and unsupervised clustering techniques. For the fMRI data, a comparative quantitative evaluation between the two methods, tree-dependent and topographic ICA, was performed. The comparative results were evaluated by (1) task-related activation maps, (2) associated time courses, and (3) ROC study. The most important findings in this paper are that (1) both tree-dependent and topographic ICA are able to identify signal components with high correlation to the fMRI stimulus, and that (2) topographic ICA outperforms all other ICA methods including tree-dependent ICA for 8 and 9 ICs. However for 16 ICs, topographic ICA is outperformed by tree-dependent ICA (KGV) using as an approximation of the mutual information the kernel generalized variance. The applicability of the new algorithm is demonstrated on experimental data.
Highlights
Functional magnetic resonance imaging with high temporal and spatial resolution represents a powerful technique for visualizing rapid and fine activation patterns of the human brain [1, 2, 3, 4, 5]
It can be seen that topographic independent component analysis (ICA) outperforms all other ICA methods for 8 and 9 independent components (ICs)
For 16 ICs topographic ICA is outperformed by tree-dependent ICA (KGV) using as an approximation of the mutual information the kernel generalized variance
Summary
Functional magnetic resonance imaging with high temporal and spatial resolution represents a powerful technique for visualizing rapid and fine activation patterns of the human brain [1, 2, 3, 4, 5]. As is known from both theoretical estimations and experimental results [4, 6, 7], an activated signal variation appears very low on a clinical scanner. This motivates the application of analysis methods to determine the response waveforms and associated activated regions. These techniques can be divided into two groups: model-based techniques require prior knowledge about activation patterns, whereas model-free techniques do not. The second kind, fuzzy clustering analysis [14, 15, 16, 17] or self-organizing maps [17, 18, 19], EURASIP Journal on Applied Signal Processing attempts to classify time signals of the brain into several patterns according to temporal similarity among these signals
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call