Training in interventional radiology is slowly shifting towards simulation which allows the repetition of many interventions without putting the patient at risk. Accurate segmentation of anatomical structures is a prerequisite of realistic surgical simulation. Therefore, our aim is to develop a generic approach to provide fast and precise segmentation of various virtual anatomies covering a wide range of pathology, directly from patient CT/MRA images. This paper presents a segmentation framework including two segmentation methods: region model based level set segmentation and hierarchical segmentation. We compare them to an open source application ITK-SNAP which provides similar approaches. The subjective human influence such as inconsistent inter-observer errors and aliasing artifacts etc. are analysed. The proposed segmentation techniques have been successfully applied to create a database of various anatomies with different pathologies, which is used in computer-based simulation for interventional radiology training.