28-12-2012, 06:17 PM
Locating the Optic Nerve in a Retinal Image Using the
Fuzzy Convergence of the Blood Vessels
[attachment=45672]
Abstract
We describe an automated method to locate the optic nerve in images of the ocular fundus. Our method uses a novel algorithm we call fuzzy convergence to determine the origination of the blood vessel network. We evaluate our method using 30 images of healthy retinas and 51 images of diseased retinas, containing such diverse symptoms as tortuous vessels, choroidal neovascularization, and hemorrhages that completely obscure the actual nerve. On this difficult data set, our method achieved 89% correct detection. We are making all our images and data publicly available for interested researchers to use in evaluating related methods.
Introduction
The optic nerve is one of the most important organs in the human retina. The central retinal artery and central retinal vein emanate through the optic nerve, supplying the retina with blood. The optic nerve also serves as the conduit for the flow of information from the eye to the brain. Most retinal pathology is local in its early stages, not affecting the entire retina, so that vision impairment is more gradual. In contrast, pathology on or near the nerve can have a more severe effect in early stages, due to the necessity of the nerve for vision [15, pg. 719].
To find the vessel network convergence, we describe a novel algorithm we call fuzzy convergence. The algorithm is a voting type method that works in the spatial domain of the image. The input to the algorithm is a binary segmentation of the blood vessels. Each vessel is modeled by a fuzzy segment, which contributes to a cumulative voting image. The output from the algorithm is a convergence image, which is thresholded to identify the strongest point(s) of convergence.
We test our method on 30 images of healthy retinas and 51 images of diseased retinas. We report the success of our method to detect the optic nerve using fuzzy convergence alone, and in conjunction with using brightness as a salient feature.
Related work
The problem of optic nerve detection has rarely received unique attention. It has been investigated as a precursor for other issues, for example as identifying a starting point for blood vessel segmentation [21,22]. It has also been investigated as a byproduct of general retinal image segmentation, for instance into separate identifications of arteries, veins, the nerve, the fovea, and lesions [1,6,12,16]. Here we review these related works.
In [12] a method is presented to segment a retinal image into arteries, veins, the optic disk, the macula, and background. The method is based upon split-and-merge segmentation, followed by feature based classification. The features used for classification include region intensity and shape. The primary goal of the paper was vessel measurement; the nerve was identified only to prevent its inclusion in the measurement of vessels.
Fuzzy Convergence of the Blood Vessels
[attachment=45672]
Abstract
We describe an automated method to locate the optic nerve in images of the ocular fundus. Our method uses a novel algorithm we call fuzzy convergence to determine the origination of the blood vessel network. We evaluate our method using 30 images of healthy retinas and 51 images of diseased retinas, containing such diverse symptoms as tortuous vessels, choroidal neovascularization, and hemorrhages that completely obscure the actual nerve. On this difficult data set, our method achieved 89% correct detection. We are making all our images and data publicly available for interested researchers to use in evaluating related methods.
Introduction
The optic nerve is one of the most important organs in the human retina. The central retinal artery and central retinal vein emanate through the optic nerve, supplying the retina with blood. The optic nerve also serves as the conduit for the flow of information from the eye to the brain. Most retinal pathology is local in its early stages, not affecting the entire retina, so that vision impairment is more gradual. In contrast, pathology on or near the nerve can have a more severe effect in early stages, due to the necessity of the nerve for vision [15, pg. 719].
To find the vessel network convergence, we describe a novel algorithm we call fuzzy convergence. The algorithm is a voting type method that works in the spatial domain of the image. The input to the algorithm is a binary segmentation of the blood vessels. Each vessel is modeled by a fuzzy segment, which contributes to a cumulative voting image. The output from the algorithm is a convergence image, which is thresholded to identify the strongest point(s) of convergence.
We test our method on 30 images of healthy retinas and 51 images of diseased retinas. We report the success of our method to detect the optic nerve using fuzzy convergence alone, and in conjunction with using brightness as a salient feature.
Related work
The problem of optic nerve detection has rarely received unique attention. It has been investigated as a precursor for other issues, for example as identifying a starting point for blood vessel segmentation [21,22]. It has also been investigated as a byproduct of general retinal image segmentation, for instance into separate identifications of arteries, veins, the nerve, the fovea, and lesions [1,6,12,16]. Here we review these related works.
In [12] a method is presented to segment a retinal image into arteries, veins, the optic disk, the macula, and background. The method is based upon split-and-merge segmentation, followed by feature based classification. The features used for classification include region intensity and shape. The primary goal of the paper was vessel measurement; the nerve was identified only to prevent its inclusion in the measurement of vessels.