Abstract
The extraction of structural information from the vascular network captured in a retinal image is an essential component of computer-aided diagnosis for many ophthalmological, cardiovascular, and systemic disorders. Although several methods have been reported in the past to tackle this problem, ensuring clarity and high accuracy while segmenting various objects from a retinal image still poses a challenge. In this work, we have proposed a novel technique to extract the underlying structure of blood vessels from a retinal image that includes segmentation of optic disc region and identification of veins, arteries, and bifurcation points in the vascular network. Unlike previous approaches, the proposed method relies mostly on the processing of digital-geometric features and integrates them with conventional image analysis for effective segmentation of various objects in the vascular network. The method outperforms several prior work in terms of segmentation accuracy, and experiments on several retinal images reveal encouraging results. The performance of the proposed technique is evaluated by comparing clinically-assessed ground-truth with automated findings.
Notes
No potential conflict of interest was reported by the authors.
A preliminary version of this paper appeared in the Proceedings, IWCIA, LNCS, vol. 9448, pp. 261–275, 2015.