Many diagnostic and therapeutic procedures depend on medical images. In order to overcome imperfections of obtained images which are due to acquisition process and to obtain new information from available images, many techniques have been developed. In this study relatively new method of image segmentation, active contour model-“snakes” was applied in analyzing computed tomography (CT) images in patients with acute head trauma. Using this method, lesion to brain (LBR) and ventricle to brain ratio (VBR) were obtained accurately. Quantitative variable LBR, is significantly higher in patients with other pathologic CT findings and who do not survive during hospitalization. Thus, by applying segmentation “snakes” model it is possible to extract maximum information from available CT scans. These variables could be basis for medical decision making in patients with acute head trauma.