Segmentation of nontrivial images is one of the most difficult tasks in image processing. Segmentation accuracy determines the success or failure of computerized analysis procedures. Medical image segmentation has become an important diagnostic tool in the practice of modern medicine. Segmentation of MRI Brain images is the delineation of neuro-anatomical structures such as the Cerebrum, Cerebellum, Hippocampus, etc. as well as abnormalities such as tumors. Although numerous methods have been proposed during the past two decades for brain MRI segmentation, it remains a challenging task. In this paper brain MRI segmentation is demonstrated for delineation of a tumor, ventricles and other anatomical structures using Insight Segmentation and Registration Toolkit (ITK) routines as the foundation. This public software provides callable routines only. It does not provide graphics, visualization, or other interactive tools specific to a given task, such as segmentation. Segmentation of medical images is an important step in forming realistic tissue models. To assist in classifying the relevant literature, three generations of development are identified where each generation adds an additional level of algorithmic complexity. The first generation is composed of the simplest forms of image analysis, the second is characterized by the application of uncertainty models and optimization methods, and the third incorporates knowledge into the segmentation process. The progress toward fully automatic segmentation is discussed and sources of segmentation software from industry and academia are identified, along with databases for segmentation validation. We have implemented a variety of semiautomatic and automatic segmentation routines as well as preprocessing algorithms provided by ITK. This implementation facilitates interactive adjustments of algorithm parameters and their consequences on the segmentation results via an intuitive GUI incorporating the ITK segmentation routines.