Classification of Fundus Photographs using Full Width Half Maximum Algorithm

Abstract

A computerized semiautomatic system has been presented for classification of fundus photographs. This classification is based on feature vectors obtained from twin Gaussian Intensity Distribution and full width half maximum algorithm for vasculature diameter measurement. Diagnostic performance with overall sensitivity of 75% and accuracy of 93% has been achieved using k-NN classifier and neural network both. The performance is evaluated using DRIVE database and fundus photographs from the hospital.

Reference

• James Lowell,Andrew Hunter,David Steel, “Measurement of retinal vessel widths from fundus images based on 2-D modeling”, IEEE Transactions on Medical Imaging, Vol.23, no,10, pp.1196-1204, October 2004.
• Divyanjali Satyarthi, B.A.N Raju, S. Dandapat, “ Detection of Diabetic Retinopathy in Fundus images using Vector Quantization Technique”, Anual IEEE Conference,pp.1-4 September,2006.
• L. Pedersen et al., “Quantitative measurement of changes in retinal vessel diameter in ocular fundus images,” Pattern Recogn. Lett., vol. 21, pp. 1215–1223, 2000.
• Chisako Muramatsu, Yuji Hatanaka, Eatsuhiko Iwase, “Automated Detection and Classification of major Retinal Vessels for Determination of Diameter Ratio of Arteries and Veins”, in the Proc. Of SPIE, Medical Imaging 2010: Computer Aided Diagnosis.
• Huiqi Li, Wynne Hsu. Et al., “A piecewise Gaussian Model for profiling and Differentiating Retinal Vessels”, in the Proceedings of IEEE Image Processing, pp.14-17, Sept.2003.
• Di wu, Ming Zhang,Jyh-Charn Liu, “Communications – on the adaptive detection of blood vessels in retinal images”, IEEE Transactions on Biomedical Engineering, Vol.53, no,2, pp.341-343, February, 2006.
• Joao B. Soares, Jorge J.G Leandro, “Retinal Vessel Segmentation Using the 2-D Morlet Wavelet and Supervised Classification”, IEEE Transactions on Medical Imaging, vol.25, Issue. 9, pp. 1214-1222,May 2006.
• Joes Staal et al., “Ridge Based Vessel Segmentation in Color Images of the Retina”, IEEE Transactions on Medical Imaging, vol.23,no.4,April 2004
• Renzo Perfetti, Elisa Ricci, Daniele Casalib, “ Cellular Neural Networks with Virtual Template Expansion for Retinal Vessel segmentation”, IEEE Transactions on Circuits and Systems II- Express Briefs, vol.54,no.2,China 2007
• Shuying Huang and Erthu Zhang , “A Method for Segmentation of Retinal Image Vessels”, in the Proceedings of the 6th World Congress on Intelligent Control and Automation, June 21-23,China 2006.
• Giribabu Kande, T. Satya Savithri, P.V. Subbaiah, “Segmentation of Vessels in Fundus Images using Spatially Weighted Fuzzy c-Means Clustering Algorithm”, IJCSNS International Journal of Computer Science and Network Security, vol.7, no. 12, December 2007.
• Frederic Zana and Jean Claude klein, “Segmentation of Vessel like Patterns using Mathematical Morphology and Curvature Evaluation”, IEEE Transactions on Image Processing, vol. 10, no.7, July 2001.
• Adam Hoover, Valentina Kouzvetsova and Michael Goldbaum, “Locating Blood Vessels in Retinal Images by Piecewise Threshold Probing of a Matched Filter Response”, IEEE Transactions on Medical Imaging , vol.19,no.3,March 2000. Forman, G. 2003.
• I Sun, "Automated identification of vessel contours in contrary arteriograms by an adaptive tracking algorithm," IEEE transactions on Medical Imaging, vol. 8, pp.78-88, March 1989
• Chang Hua Wu, Gady Agam, Peter Stanchev , “A general framework for vessel segmentation in retinal images”, in the Proceedings of the IEEE Internation
• al symposium on Computational Intelligence in Robotics and Automation , pp. 20-23, June 2007.
• S.Jerald Jeba Kumar, M. Madheswaran,"Automated Thickness Measurement of Retinal Blood Vessels for Implementation of Clinical Decision Support Systems in Diagnostic Diabetic Retinopathy" in the Proceedings of World Academy of Science, Engineering and Technology 2010 ,no.64, pp.393-397
• Sumeet Dua,Naveen kandiraju et al., “ Design and Implementation of a Unique Blood Vessel Detection algorithm towards Early Diagnosis of Diabetic Retinopathy”, in the Proceedings of the IEEE International Conference on Information Technology: Coding and Computing 2005
• Lili Xu, Shuqian Luo, “A novel method for blood vessel detection from retinal images”, Bimedical Engineering Online, pp.9-14,2010
• K.G.Goh, W.Hsu, “ADRIS: An automatic Diabetic Retinal image screening system”, Medical data mining and knowledge discovery, Springer-Verlag 2000
• Gregson, P. H; et al, “Automated grading of venous beading”, Fundus photographic risk factors for progression of diabetic retinopathy,” in Ophthalmology: : Early treatment diabetic retinopathy study research group, 1991, vol. 98, pp. 823–833.vol. 98, pp. 823–833.
• R. Sharrett et al., “Retinal arteriolar diameters and elevated blood pressure: The atherosclerosis risk in communities study,” Amer. J. Epidemiol., vol. 150, pp. 263–270, 1999.
• T. Y. Wong et al., “Retinal microvascular abnormalities and their relationship with hypertension, cardiovascular disease and mortality,” Survey Ophthalmol., vol. 46, no. 59–80, 2001
• Xiaohong W. Gao, Anil Bharath et al., “Quantification and Characterization of arteries in Retinal Images”, Computer Methods and Programs in Biomedicine, vol.63, pp. 133-146, 2000.
• O. Brinchmann-Hansen and O. Engvold, Microphotometry of the blood column and light streak on retinal vessels in fundus photographs,”Acta Ophthalmologica, Suppl., vol. 179, pp. 9–19, 1986.
• O. Brinchmann-Hansen and H. Heier, “Theoretical relationships between light streak characteristics and optical properties of retinal vessels”,Acta Ophthalmologica, Suppl., vol. 179, pp. 33–37, 1986.
• O. Chutatape, Liu Zheng, “ Retinal Blood Vessel Detection and Tracking by Matched Gaussian and Kalman filters”, in the proceedings of annual IEEE International Conference, vol.6, pp. 3144-3149,Nov. 1998.

Index Terms

Key words