AN EFFECTIVE AND EFFICIENT TECHNIQUE FOR SEARCHING FOR SIMILAR BRAIN ACTIVATION PATTERNS

In this paper, we introduce a new approach for content-based similarity search for brain images. Based on the keyblock representation, our framework employs the principal component analysis to reduce the dimensionality and improve the computational efficiency. Moreover, the "similarity" between two images is measured using both the histogram model and the summed Euclidean distance. We performed experiments on different fMRI datasets, and compared the proposed framework with the keyblock approach. The results of the experiments demonstrated the improved effectiveness and efficiency of the proposed approach in similarity searches.