A Similarity Retrieval Tool for Functional Magnetic Resonance Imaging Statistical Maps

Rosalia Tungaraza, Jinyan G

Abstract

Objective. We propose a method for retrieving similar functional magnetic resonance imaging (fMRI) statistical images given a query fMRI statistical image. Method. Our method thresholds the voxels within those images and extracts spatially distinct regions from the voxels that remain. Each region is defined by a feature vector that contains the region centroid, the region area, the average activation value for all the voxels within that region, the variance of those activation values, the average distance of each voxel within that region to the region’s centroid, and the variance of the voxel’s distance to the region’s centroid. The similarity between two images is obtained by the summed minimum distance (SMD) of their constituent feature vectors. Results and conclusion. Our method is sensitive to similarities in brain activation patterns from members of the same data set. Using a subset of the features such as the centroid location and the average activation value (individually or in combination), maximized the sensitivity of our method. We also identified the similarity structure of the entire data set using those two features and the SMD.