Hill Climbing Optimized Twin Classification Using Resting-State Functional MRI

Twin imaging studies are an important part of human brain research that can reveal the importance of genetic influences on different aspects of brain behavior and disorders. Accurate characterization of identical and fraternal twins allows inference to be performed on the genetic influence in a population. In this paper, we propose a novel pairwise feature representation to classify the zygosity of twin pairs using resting state functional magnetic resonance images (rs-fMRI). Specifically, we project an fMRI signal to a set of cosine series basis, and use the projection coefficients as the compact and discriminative feature representation of noisy fMRI data. The pairwise relation is encoded by a set of twin-wise correlations between the new feature representations across brain regions. We further employ Hill Climbing variable selection to identify the brain regions that are most genetically affected. The proposed framework has been applied to 208 twin pairs in the Human Connectome Project (HCP) and we achieved 94.19($\pm$3.53)% classification accuracy in determining the zygosity of paired images.