An Active Contour Model for Segmenting and Measuring Retinal Vessels
Top Cited Papers
- 24 March 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 28 (9), 1488-1497
- https://doi.org/10.1109/tmi.2009.2017941
Abstract
This paper presents an algorithm for segmenting and measuring retinal vessels, by growing a ldquoRibbon of Twinsrdquo active contour model, which uses two pairs of contours to capture each vessel edge, while maintaining width consistency. The algorithm is initialized using a generalized morphological order filter to identify approximate vessels centerlines. Once the vessel segments are identified the network topology is determined using an implicit neural cost function to resolve junction configurations. The algorithm is robust, and can accurately locate vessel edges under difficult conditions, including noisy blurred edges, closely parallel vessels, light reflex phenomena, and very fine vessels. It yields precise vessel width measurements, with subpixel average width errors. We compare the algorithm with several benchmarks from the literature, demonstrating higher segmentation sensitivity and more accurate width measurement.Keywords
This publication has 25 references indexed in Scilit:
- REVIEW - A reference data set for retinal vessel profiles2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2008
- Measurement of Retinal Vessel Widths From Fundus Images Based on 2-D ModelingIEEE Transactions on Medical Imaging, 2004
- An efficient algorithm for extraction of anatomical structures in retinal imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Identifying vascular features with orientation specific filters and B-spline snakesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Vessel tracking by template string in angiographyPublished by SPIE-Intl Soc Optical Eng ,2001
- Computer algorithms for the automated measurement of retinal arteriolar diametersBritish Journal of Ophthalmology, 2001
- Locating blood vessels in retinal images by piecewise threshold probing of a matched filter responseIEEE Transactions on Medical Imaging, 2000
- Automated Grading of Venous BeadingComputers and Biomedical Research, 1995
- The detection and quantification of retinopathy using digital angiogramsIEEE Transactions on Medical Imaging, 1994
- Theoretical relations between light streak characteristics and optical properties of retinal vesselsActa Ophthalmologica, 1986