A method for automatic modelling of blood vessels and their bifurcations from 3D scans of the brain is presented. The method is a three-step procedure. First, a skeleton of the cerebral blood vessels is developed, and then the surfaces of the blood vessels are located using an active contour approach. The active contour approach uses circular homogeneous generalised cylinders (CHGCs) to model the thin, elongated blood vessels. Finally, a novel method for modelling the surfaces of the bifurcations in a vessel tree is presented. The method was tested on simulated data: a computed tomography angiography (CTA) and four magnetic resonance angiography (MRA) volumes. Furthermore, the method was tested on ten magnetic resonance images (MRIs) to demonstrate its robustness. The test on the simulated data indicated that the approach for the surface modelling of vessels had a mean radius error of less than 0.1 mm and a mean localisation error of 0.1 mm. Surface models evaluated by an expert in vascular neurosurgery were found to have a smooth appearance and generally agreed with the image data. The test on the MRI scans indicated that the method performed well in noisy environments.