A retinal vessel boundary tracking method based on Bayesian theory and multi-scale line detection

A recursive Bayesian approach to describe retinal vasculature geometry

“…where P (z k+1 |y 0:k ) and P (y k+1 |z k+1 ) respectively show the prior probability distribution of the geometry parameters and their likelihood at iteration k + 1. The prior probability distribution reflects our belief about vessel parameters, which is represented with the updated initial estimate of the geometry parameters at the start of each iteration, k. When k = 0, the prior probability distribution could be initialised by manual input, or a method that detects vessel tracks as they leave the optic disc [14]. As iterations proceed, the prior probability distribution could be evolved according to the geometry model G(·) in (1), where the posterior probability distribution of the geometry parameters at iteration k is used as the prior probability distribution of the geometry parameters for iteration k + 1.…”

“…To date, many Bayesian tracking methods [12,13,14] have modelled the appearance of the cross-section of a vessel segment conditional on centerline location, diameter and orientation, by Gaussian functions. Though analytically convenient, it is not realistic when the shape of the intensity profile changes due to uneven illumination, pathologies or other noise components.…”

“…Vessel centerline and width parameters or each vessel segment were initialized with the reference data in the REVIEW. In the same way, vessel direction is assigned the direction from the first reference centerline location to second one, similar to [14].…”

“…However, because they did not present the percentage of meaningful width estimations, it is not clear if the results reflect the Precision of overall sub-datasets, or only those corresponding to the successfully estimated profiles. The performance of Araújoa et al's method [7] is followed by that of tracking methods [13,14], whose performance mostly surpasses that of other supervised and unsupervised methods [5,6,10,11,31].…”

“…As an example, Chutatape et al [12] used an extended Kalman filter, Yin et al and Zhang et al Maximum a Posteriori (MAP) and, Wu et al generalized particle filters [15]. In all of these approaches, a key component influencing the performance of tracking seems to relate to how well the likelihood function reflects the actual vessel geometry and appearance in the original image data [13,14].…”