Functional magnetic resonance imaging activation detection: Fuzzy cluster analysis in wavelet and multiwavelet domains

Abstract

Purpose: To present novel feature spaces, based on multiscale decompositions obtained by scalar wavelet and multiwavelet transforms, to remedy problems associated with high dimension of functional magnetic resonance imaging (fMRI) time series (when they are used directly in clustering algorithms) and their poor signal-to-noise ratio (SNR) that limits accurate classification of fMRI time series according to their activation contents. Materials and Methods:Using randomization, the proposed method finds wavelet/multiwavelet coefficients that represent the activation content of fMRI time series and combines them to define new feature spaces. Using simulated and experimental fMRI data sets, the proposed feature spaces are compared to the cross-correlation (CC) feature space and their performances are evaluated. In these studies, the false positive detection rate is controlled using randomization. To compare different methods, several points of the receiver operating characteristics (ROC) curves, using simulated data, are estimated and compared. Results:The proposed features suppress the effects of confounding signals and improve activation detection sensitivity. Experimental results show improved sensitivity and robustness of the proposed method compared to the conventional CC analysis. Conclusion:More accurate and sensitive activation detection can be achieved using the proposed feature spaces compared to CC feature space. Multiwavelet features show superior detection sensitivity compared to the scalar wavelet features.

Clustering of fMRI data: the elusive optimal number of clusters

“…Typically, users have to set objective criteria to distinguish relevant clusters from noise or artefact-driven clusters. For instance, for task-related fMRI data, clusters of interest are expected to have centroids similar (highly correlated) to the paradigm ( Chuang et al, 1999 ; Fadili et al, 2000 ; Goutte et al, 1999 ; Jahanian, Soltanian-Zadeh & Hossein-Zadeh, 2005 ), as illustrated in Fig. 7 .…”

“…Although FCM allows high computational flexibility, its robustness may depend on several methodological issues. Specifically, these include the initialisation problem, the choice of similarity or distance metric, and the usually unknown optimal number of classes or prototypes (e.g., Alexiuk & Pizzi, 2004 ; Esposito et al, 2002 ; Fatemizadeh, Taalimi & Davoudi, 2009 ; Jahanian, Soltanian-Zadeh & Hossein-Zadeh, 2005 ; Lange et al, 2004 ; Moller et al, 2002 ; Quiqley et al, 2002 ; Soltanian-Zadeh et al, 2004 ; Windischberger et al, 2003 ). This study focuses on the issue of the optimal number of clusters that can be extracted from fMRI data.…”

Peer Review #1 of "Clustering of fMRI data: the elusive optimal number of clusters (v0.1)"

“…Typically, users have to set objective criteria to distinguish relevant clusters from noise or artefact-driven clusters. For instance, for task-related fMRI data, clusters of interest are expected to have centroids similar (highly correlated) to the paradigm (Chuang et al 1999;Fadili et al 2000;Goutte et al 1999;Jahanian et al 2005), as illustrated in Figure 7. For task-free fMRI data, irrelevant clusters should be discarded, including clusters that are less consistent across sessions (Levin & Uftring 2001) or when they include irrelevant brain voxels (e.g.…”