An Active Contour Model for Segmenting and Measuring Retinal Vessels

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.

[1]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[2]  Bram van Ginneken,et al.  Comparative study of retinal vessel segmentation methods on a new publicly available database , 2004, SPIE Medical Imaging.

[3]  Morton H. Friedman,et al.  Vessel tracking by template string in angiography , 2001, International Symposium on Multispectral Image Processing and Pattern Recognition.

[4]  P. Gregson,et al.  Automated grading of venous beading. , 1995, Computers and biomedical research, an international journal.

[5]  Xiaoyi Jiang,et al.  Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  F. Sutter,et al.  Familial retinal arteriolar tortuosity: a review. , 2003, Survey of ophthalmology.

[7]  R. Klein,et al.  The relation of systemic hypertension to changes in the retinal vasculature: the Beaver Dam Eye Study. , 1997, Transactions of the American Ophthalmological Society.

[8]  Olaf Brinchmann-Hansen,et al.  Theoretical relations between light streak characteristics and optical properties of retinal vessels , 1986 .

[9]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[10]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[11]  Andrew Hunter,et al.  A ribbon of twins for extracting vessel boundaries , 2005 .

[12]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[13]  A. Bharath,et al.  Computer algorithms for the automated measurement of retinal arteriolar diameters , 2001, The British journal of ophthalmology.

[14]  A. K. Klein,et al.  Identifying vascular features with orientation specific filters and B-spline snakes , 1994, Computers in Cardiology 1994.

[15]  R. Klein,et al.  Hypertension and retinopathy, arteriolar narrowing, and arteriovenous nicking in a population. , 1994, Archives of ophthalmology.

[16]  Liang Zhou,et al.  The detection and quantification of retinopathy using digital angiograms , 1994, IEEE Trans. Medical Imaging.

[17]  Steve R. Gunn,et al.  A Robust Snake Implementation; A Dual Active Contour , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Guoliang Fan,et al.  An efficient algorithm for extraction of anatomical structures in retinal images , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[19]  Ivan Laptev,et al.  Automatic extraction of roads from aerial images based on scale space and snakes , 2000, Machine Vision and Applications.

[20]  José L. Marroquín,et al.  Robust parametric active contours: the Sandwich Snakes , 2001, Machine Vision and Applications.

[21]  Andrew Hunter,et al.  Multiple object tracking using a neural cost function , 2009, Image Vis. Comput..

[22]  Maged Habib,et al.  REVIEW - A reference data set for retinal vessel profiles , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[23]  O. Chutatape,et al.  Retinal blood vessel detection and tracking by matched Gaussian and Kalman filters , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[24]  Andrew Hunter,et al.  Optic nerve head segmentation , 2004, IEEE Transactions on Medical Imaging.

[25]  Andrew Hunter,et al.  Measurement of retinal vessel widths from fundus images based on 2-D modeling , 2004, IEEE Transactions on Medical Imaging.

[26]  Andrew Hunter,et al.  Tram-Line filtering for retinal vessel segmentation , 2005 .

[27]  Maged Habib,et al.  Joining retinal vessel segments , 2008, 2008 8th IEEE International Conference on BioInformatics and BioEngineering.

[28]  Jerry L. Prince,et al.  Snakes, shapes, and gradient vector flow , 1998, IEEE Trans. Image Process..