Hypertensive Retinopathy Diagnosis from Fundus Images by Estimation of Avr.

Abstract Hypertensive retinopathy is a disease that damages the retina of the eye and results in loss of vision and is closely associated with high blood pressure. Severe case of hypertensive retinopathy causes systematic aliments that may cause cardiovascular diseases, heart and renal failure, loss of vision and finally death. Thus the timely diagnosis and treatment of the disease is vital. Arteriovenous ratio is used to diagnose hypertensive retinopathy. In this paper we proposed an algorithm in which, the blood vessels are segmented out initially, from the pre processed retinal images. Gray level and moment based features are extracted to classify the detected pixels as belonging to the blood vessel class or not. Intensity variation and colour information is used to classify the vessel as arteries or veins. Vessel width estimation method is used to measure the arteriovenous ratio from which various stages of hypertensive retinopathy can be identified. Retinal images were obtained from the VICAVR database, along with images collected form Deepam eye hospital Chennai. From the images that were collected 25 were normal images and 76 images of hypertensive retinopathy

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

[2]  Pascale Massin,et al.  Automatic detection of microaneurysms in color fundus images , 2007, Medical Image Anal..

[3]  Mohammed Al-Rawi,et al.  An improved matched filter for blood vessel detection of digital retinal images , 2007, Comput. Biol. Medicine.

[4]  C. Sinthanayothin,et al.  Automated detection of diabetic retinopathy on digital fundus images , 2002, Diabetic medicine : a journal of the British Diabetic Association.

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

[6]  Michael H. Goldbaum,et al.  Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels , 2003, IEEE Transactions on Medical Imaging.

[7]  Alfredo Ruggeri,et al.  A divide et impera strategy for automatic classification of retinal vessels into arteries and veins , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[8]  C. Sinthanayothin,et al.  Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images , 1999, The British journal of ophthalmology.

[9]  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).

[10]  Ana Maria Mendonça,et al.  Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction , 2006, IEEE Transactions on Medical Imaging.

[11]  Frédéric Zana,et al.  Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation , 2001, IEEE Trans. Image Process..

[12]  Yannis A. Tolias,et al.  A fuzzy vessel tracking algorithm for retinal images based on fuzzy clustering , 1998, IEEE Transactions on Medical Imaging.

[13]  Thomas Walter,et al.  Segmentation of Color Fundus Images of the Human Retina: Detection of the Optic Disc and the Vascular Tree Using Morphological Techniques , 2001, ISMDA.

[14]  Elisa Ricci,et al.  Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification , 2007, IEEE Transactions on Medical Imaging.

[15]  Di Wu,et al.  On the adaptive detection of blood vessels in retinal images , 2006, IEEE Transactions on Biomedical Engineering.