Quantifying the progression of a condition is one the most difficult challenges facing physicians as they look to provide the most effective treatment customized for individual patients. To achieve these goals, a novel image processing algorithm providing automated quantification has been developed to analyze the cranial vault and sutures using CT in humans and construct predictive models of the condition. Currently, very few preoperative or postoperative quantification tools exist for children with craniosynostosis so we used a customized active contour snake algorithm and 3D reconstruction to quantify the intracranial volume and measure the cranial sutures of these patients. A set of 117-patient CT scans was collected and analyzed, 77 with varying types of craniosynostosis and 40 normal patients as a control. Total intracranial volume was maintained in craniosynostosis patients in comparison to normal resulting in a uniform growth curve that showed no significant difference between the two groups. Assessing the asymmetry in the intracranial volume and measurements of suture volume and patency resulted in quantitative separations in synostosis types. These separations were further validated by a logistic regression model with pseudo R2 values greater than 0.95 and an 86.9% average accuracy in cross-validation of the seven groups, which increased to 91.9% with the removal of the underrepresented lambdoid synostosis group.