Clustering-based framework for comparing fMRI analysis methods

In this paper, a cluster-based framework is introduced for comparing analysis methods of functional magnetic resonance images (fMRI). In the proposed framework, fMRI data is replaced with a feature space and each method considered as a clustering method in the new space. As a result, different methods can be compared by means of a cluster validity measure. The feature space is computed using a non-parametric method (principal component analysis-PCA). Four subjects have been analyzed with three methods and the proposed cluster-based framework has evaluated performance of the methods. The results are identical to those of the modified receiver operating characteristics (ROC). This validates the proposed approach.