Title: Segmentation of Soft Tissue Using Texture Features and Gradient Snakes
Published: September 2007
Authors: Carl PhilipsRuchaneewan Susomboon, Reem Mokhtar, Daniela Raicu, Jacob Furst 
Abstract: Snakes have been used extensively in locating object boundaries. However, in the medical imaging field, many organs in close proximity have similar intensity values, limiting the usefulness of snakes in segmentation of abdominal organs. In this paper, we use the gradient vector flow snake to test the benefits of running snakes on texture features from a Markov Random Fields model as opposed to the pixel intensity. Our results show that using Markov Random Fields has a positive effect on the effectiveness of snake.
Full Paper: [doc]