Active contours in medical image processing. Theory and applications

Among the most promising techniques for extraction of complex objects from digital images are active contours or snakes, originally introduced by Kass et al. Since the seminal work of Kass and colleagues, techniques based on active contours have been applied to many object extraction tasks with a different degree of success. In particular, snakes have been used to locate the objects in various applications of medical image processing such as segmentation of abnormalities in the images of the human heart, liver, brain, breast, etc. This paper offers a short survey of the snake-based segmentation methods employed by computerized medical image processing along with relevant pre-processing such as speckle noise filters, region growing and clustering methods. Furthermore, the paper introduces a recent modification of the gradient vector flow snakes based on the continuous vector filed analysis.