Clustering fMRI time series has emerged in recent years as a possible alternative to parametric modelling approaches. Most of the work has been so far concerned with clustering raw time series. In this contribution we investigate the applicability of a clustering method applied to features extracted from the data. This approach is extremely versatile and encompasses previously published results (Goutte et al., 1999) as special cases. A typical application is in data reduction: as the increase in temporal resolution of fMRI experiments routinely yields fMRI sequences containing several hundreds of images, it is sometimes necessary to invoke feature extraction to reduce the dimensionality of the data space. A second interesting application is in the meta-analysis of fMRI experiment, where features are obtained from a possibly large number of single-voxel analyses. This allows in particular to check the differences and agreements between different methods of analysis. Both approaches are illustrated on a fMRI dataset involving visual stimulation, and we show that the feature space clustering approach yields non-trivial results, and in particular shows interesting differences between individual voxel analysis performed with traditional methods.
Technical report IMM-REP-1999-13
Submitted to Academic Press for possible publication