Several studies have used structural correlation networks, derived from anatomical covariance of brain regions, to analyze neurologic changes associated with multiple sclerosis, schizophrenia and breast cancer [1][2]. Graph-theoretical analyses of human brain structural networks have consistently shown the characteristic of small-worldness that reflects a network with both high segregation and high integration. A large neuroimaging literature on football players, with and without history of concussion, has shown both functional and anatomical changes. Here we use graph-based topological properties of anatomical correlation networks to study the effect of prior concussion in collision-sport athletes. 40 high school collision-sport athletes (23 male football, 17 female soccer; CSA) without self-reported history of concussion (HOC-), 18 athletes (13 male football, 5 female soccer) with self-reported history of concussion (HOC+) and 24 healthy controls (19 male, 5 female; CN) participated in imaging sessions before the beginning of a competition season. The extracted residual volumes for each group were used for building the correlation networks and their small-worldness, , is calculated. The small-worldness of CSA without prior history of concussion, , is significantly greater than that of controls, . CSA with prior history have significantly higher (vs. 95% confidence interval) small-worldness compared to HOC+, over a range of network densities. The longer path lengths in HOC+ group could indicate disrupted neuronal integration relative to healthy controls.