Maximum a posteriori estimation of image boundaries by dynamic programming

We seek a computationally fast method for solving a difficult image segmentation problem: the positioning of boundaries on medical scanner images to delineate tissues of interest. We formulate a Bayesian model for image boundaries such that the maximum a posteriori estimator is obtainable very efficiently by dynamic programming. The prior model for the boundary is a biased random walk and the likelihood is based on a border appearance model, with parameter values obtained from training images. The method is applied successfully to the segmentation of ultrasound images and X-ray computed tomographs of sheep, for application in sheep breeding programmes.