Trainable COSFIRE filters for vessel delineation with application to retinal images

Abstract

a b s t r a c tRetinal imaging provides a non-invasive opportunity for the diagnosis of several medical pathologies. The automatic segmentation of the vessel tree is an important pre-processing step which facilitates subsequent automatic processes that contribute to such diagnosis.We introduce a novel method for the automatic segmentation of vessel trees in retinal fundus images. We propose a filter that selectively responds to vessels and that we call B-COSFIRE with B standing for bar which is an abstraction for a vessel. It is based on the existing COSFIRE (Combination Of Shifted Filter Responses) approach. A B-COSFIRE filter achieves orientation selectivity by computing the weighted geometric mean of the output of a pool of Difference-of-Gaussians filters, whose supports are aligned in a collinear manner. It achieves rotation invariance efficiently by simple shifting operations. The proposed filter is versatile as its selectivity is determined from any given vessel-like prototype pattern in an automatic configuration process. We configure two B-COSFIRE filters, namely symmetric and asymmetric, that are selective for bars and bar-endings, respectively. We achieve vessel segmentation by summing up the responses of the two rotation-invariant B-COSFIRE filters followed by thresholding.The results that we achieve on three publicly available data sets (DRIVE: Se = 0.7655, Sp = 0.9704; STARE: Se = 0.7716, Sp = 0.9701; CHASE_DB1: Se = 0.7585, Sp = 0.9587) are higher than many of the state-of-the-art methods. The proposed segmentation approach is also very efficient with a time complexity that is significantly lower than existing methods.

Supervised vessel delineation in retinal fundus images with the automatic selection of B-COSFIRE filters

“…B-COSFIRE filters are trainable and in [6] they were configured to be selective for bar-like structures. Such a filter takes as input the response of a Difference-of-Gaussians (DoG) filter at certain positions with respect to the center of its area of support.…”

“…A model of the vessels based on their concavity and built by using a differentiable concavity measure was proposed in [18]. In previous works [6,35], we introduced trainable filters selective for vessels and vesselendings. We demonstrated that by combining their responses we could build an effective unsupervised delineation technique.…”

“…We propose to address the problem of segmenting elongated structures, such as blood vessels in retinal fundus images, by using a set of B-COSFIRE filters of the type proposed in [6], selective for vessels of various thickness. The B-COSFIRE filter approach was originally proposed for delineation of retinal vessels.…”

“…This demonstrates their suitability for various applications. In [6], two B-COSFIRE filters, one specific for the detection of vessels and the other for the detection of vessel-endings, were combined together by simply summing up their responses. The parameters of the vessel-ending filter were chosen in such a way to maximize the performance of the two filters.…”

A fluid-dynamic based approach to reconnect the retinal vessels in fundus photography

“…However, identification and quantification of such changes are challenging tasks since the retina is extremely heterogeneous and, as a consequence low signal-to-noise ratio, nonuniform illumination and contrast shifts in the images complicate the automated detection and analysis of geometrical changes. The latest segmentation algorithms produce highly accurate vessel segmentations [4] [5] [6] [7]. Nevertheless, the identification of the mutually overlapping venous and arterial trees is a nontrivial problem.…”