Automated vessel segmentation of 35mm colour non-mydriatic images in a community health screening project

• Autorzy: Jelinek H. F.
• Języki publikacji: EN

Abstrakty

EN

Proliferative diabetic retinopathy is a complication of diabetes that can eventually lead to blindness. Early identification of this complication reduces the risk of blindness so that timely treatment can be initiated. In rural and remote regions, widespread population screening is practically impossible due to the lack of ophthalmologists and the cost associated with rural visits by specialists. Several methods for vessel segmentation have been discussed in the literature, but none have used non-mydriatic colour images obtained from community screening initiatives. Rural screening clinics currently use either 35mm or Polaroid photography. In addition, the quality of the images is often much lower. Scanning images at 300dpi provides very low resolution images which combined with the low quality requires a robust algorithm to identify vessels with high accuracy. Visual inspection by an ophthalmologist judged 46 images (88%) to represent an acceptable level of segmentation. Despite the low resolution and quality of images, the Gabor wavelet provided vessel segmentation results that were usable in rural community screening projects and in some cases identified vessels obscured by haemorrhages better than the expert observer.

Słowa kluczowe

EN

vessel segmentation; wavelet transform; non-mydriatic; diabetic retinopathy

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2008
• Tom: Vol. 17, No. 1/2
• Strony: 57--68
• Opis fizyczny: Bibliogr. 63 poz., rys.

Twórcy

autor

Jelinek H. F.

• School of Community Health, Charles Sturt University, Albury, 2640, Australia,

Bibliografia

• [1] Doft B. H. and Blankenship G.: Retinopathy risk factor regression after laser panretinal photocoagulation for proliferative diabetic retinopathy. Ophthalmology 91: 1453-1457, 1984.
• [2] Grossmann A.: Wavelet transforms and edge detection. In: Albeverio S, Blanchard P, Hazewinkel M. and Streit L., Eds.: Stochastic processes in physics and engineering. Reidel Publishing Company, Dordrecht. 149-157, 1988.
• [3] Chaudhuri S., et al.: Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE TMI 8 (3): 263-269, 1989.
• [4] Taylor R., et al.: Comparison of non-mydriatic retinal photography with Ophthalmology in 2159 patients: Mobile retinal camera study. British Medical Journal 301: 1243-1247, 1990.
• [5] ETDRS: Early treatment diabetic retinopathy study research group: Grading diabetic retinopathy from stereoscopic color fundus photographs - an extension of the modified Airlie house classification. ETDRS Report Number 10. Ophthalmology 98: 786-806, 1991.
• [6] Rioul O. and Vetterli M.: Wavelets and signal processing. IEEE Signal Processing Magazine: 14-89, 1991.
• [7] Antoine J. P., et al.: Image analysis with two-dimensional wavelet transform. Signal Processing 31: 241-272, 1993.
• [8] Ferris F. L.: How effective are treatments for diabetic retinopathy. Journal of American Medical Association 269: 1290-1291, 1993.
• [9] Antoine J. P. and Murenzi R.: Two-dimensional wavelet analysis in image processing. Physicalia Magazine 16: 105-134, 1994.
• [10] Murray J. D.: Use and abuse of fractal theory in neuroscience. The Journal of Comparative Neurology 361: 369-371, 1995.
• [11] Ariyasu R., et al.: Sensitivity, specificity and predictive values of screening tests for eye conditions in a clinic-based population. Ophthalmology 103: 1751-1760, 1996.
• [12] Cree M. J., et al. : Automated microaneurysms detection. IEEE International Conference on Image Processing, Lausanne, Switzerland, IEEE Press, 1996.
• [13] Gardner G., et al.: Automatic detection of diabetic retinopathy using an artificial neural network: A screening tool. British Journal of Ophthalmology 80: 940-944 Machine GRAPHICS & VISION vol. 17, no. 1/2, pp. 57-68, 1996.
• [14] Goldbaum M., et al.: Automated diagnosis and image understanding with object extn object classification and inferencing in retinal images. IEEE International Conference on Image Processing, IEEE Press, 1996.
• [15] Landini G.: Applications of fractal geometry in pathology. In: lannaccone PM and Khi M, Eds. Fractal geometry in biological systems. CRC Press, Amsterdam. 205-245, 1996.
• [16] Antoine J. P., et al.: Shape characterization with the wavelet transform. Signal Processing 62 (3): 265-290, 1997.
• [17] Icks A., et al.: Blindness due to diabetes: Population-based age- and sex-specific incidencerates. Diabetic Medicine 14: 571-575, 1997.
• [18] NHMRC : National health and medical research council. Management of diabetic retinopathy clinical practice guidelines. Australian Government Publishing Service. Canberra, 1997.
• [19] Chutatape O., et al.: Retinal blood vessel detection and tracking by matched Gaussian Kalman filters. Proceedings of the 20th Annual International Conference. IEEE Transactions in Medicine and Biology: 3144-3149, 1998.
• [20] Harper C. A., et al.: Screening for diabetic retinopathy using a non-mydriatic camera in rural Victoria. Aust NZ J Ophthalmol 28: 135-139, 1998.
• [21] Pinz A., et al. (1998) Mapping the retina. IEEE TMI 17 (4): 606-619, 1998.
• [22] Hubbard L. D., et al.: Methods for the evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the atherosclerosis risk in communities study. Ophthalmlogy, 106: 2269-2280, 1999.
• [23] Martmez-Perez M. E., et al.: Retinal blood vessel segmentation by means of scale-space analysis and region growing. Medical Image Computing and Computer-assisted Intervention - MICCAI, IEEE Press, 1999.
• [24] Sinthanayothin C., et al.: Automated localisation of the optic disc, fovea and retinal blood vessels from digital colour fundus images. British Journal of Ophthalmology 83 (8): 902-912, 1999.
• [25] Theodoridis S.: Pattern recognition. Academic Press, Baltimore, 1999.
• [26] Arneodo A., et al.: A wavelet-based method for multifractal image analysis. I. Methodology and test applications on isotropic and anisotropic random rough surfaces. Eur. Phys. Journal B 15: 567-600, 2000.
• [27] Gao X. W., et al.: Quantification and characterisation of arteries in retinal images. Computer Methods and Programs in Biomedicine 63 (2): 133-146, 2000.
• [28] Hoover A, et al.: Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Engineering on Medical Imaging 19 (3): 203-210, 2000.
• [29] Zana F. and Klein J-C.: Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation. IEEE Transactions on Image Processing 10 (7): 1010-1019, 2000.
• [30] CERA: National visual impairment program. Victorian retinopathy screening project. Centre for Eye Research Australia. Melbourne, 2001.
• [31] Costa L. F. and Cesar Jr R. M.: Shape analysis and classification: Theory and practice. CRC Press, 2001.
• [32] Forracchia M., et al.: Extraction and quantitative description of vessel features in hypertensive retinopathy fundus images. CAFIA 2001.
• [33] Goa X., et al.: A method of vessel tracking for vessel diameter measurement on retinal images Proceedings of ICIP, IEEE, 2001.
• [34] Jones C. L. and Jelinek H. F.: Wavelet packet fractal analysis of neuronal morphology. Methods 24 (4): 347-358, 2001.
• [35] Leandro J. J. G., et al.: Blood vessels segmentation in retina: Preliminary assessment of the mathematical morphology and of the wayelet transform techniques. SIBGRAPI-01, Florianopolis-SC, IEEE Computer Society Press, 2001.
• [36] Lee S. J., et al.: Costs of mobile screening for diabetic retinopathy: A practical framework for rural populations. Australian Journal of Rural Health 9: 186-192, 2001a.
• [37] Lee S. J., et al.: Program for the early detection of diabetic retinopathy: A two-year follow-up. Clinical and Experimental Ophthalmology 29: 12-25, 2001b.
• [38] Prasad S., et al.: Effectiveness of optometrist screening for diabetic retinopathy using slit-lamp biomicroscopy. Eye 15 (Pt 5): 595-601, 2001.
• [39] Stellingwerf C., et al.: Two-field photography can identify patients with vision-threatening diabetic retinopathy: A screening approach in the primary care setting. Diabetes Care 24 (12): 2086-2090, 2001.
• [40] Taylor H. R. and Keeffe J. E.: World blindness: A 21st century perspective. British Journal of Ophthalmology 85: 261-266, 2001.
• [41] Chapman N., et al.: Peripheral vascular disease is associated with abnormal arteriolar diameter relationships at bifurcations in the human retina. Clinical Science 103: 111-116, 2002.
• [42] Cummings M.: Screening for diabetic retinopathy. Practical Diabetes International 19 (1): 5, 2002.
• [43] Chanwimaluang T and Fan G.: An efficient algorithm for the extraction of anatomical structures in retinal images. Proceedings of ICIP, IEEE Press, 2003.
• [44] Jelinek H. F., et al.: Exploring wavelet transforms for morphological differentiation between functionally different cat retinal ganglion cells. Brain and Mind 4: 67-90, 2003.
• [45] Jelinek H. F., et al.: Automated characterisation of diabetic retinopathy using mathematical morphology: A pilot study for community health. 2nd Annual NSW Primary Health Care Research and Evaluation Conference, Sydney, 2003.
• [46] Leandro J. J, G., et al.: Blood vessel segmentation of non-mydriatic images using wavelets and statistical classifiers. Proceedings of the Brazilian Conference on Computer Graphics, Image Processing and Vision (Sibgrapi03), Sao Paulo, Brazil, IEEE Computer Society Press, 2003.
• [47] Leung H., et al.: Relationships between age, blood pressure, and retinal vessel diameters in an older population. IOVS 44 (0): 1-5, 2003.
• [48] Scanlon P. H., et al.: The effectiveness of screening for diabetic retinopathy by digital imaging photography and technician ophthalmoscopy. Diabetic Medicine 20 (6): 467-474, 2003.
• [49] Sharp P. F., et al.: The value of digital imaging in diabetic retinopathy. Health Technology Assessment, 2003.
• [50] Masters B. R.: Fractal analysis of the vascular tree in the human retina. Annual Rev. Biomed. Eng. 6: 427-452, 2004.
• [51] Osborne N. N., et al.: Retinal ischemia: Mechanisms of damage and potential therapeutic strategies. Progress in Retinal and Eye Research 23 (1): 91-147, 2004.
• [52] Staal J., et al.: Ridge-based vessel segmentation in color images of the retina. IEEE TMI 23 (4): 501-509, 2004.
• [53] Abramoff M. D.: Web-based screening for diabetic retinopathy in a primary care population: The eyecheck project. Telemed e-Health 11 (6): 668-674, 2005.
• [54] Cree M. J., et al.: Vessel segmentation and tracking using a 2-dimensional model. IVCNZ 05, Otago, New Zealand, 2005.
• [55] Cree M. J., et al.: Comparison of various methods to delineate blood vessels in retinal images. Proceedings of the 16th Australian Institute of Physics Congress, Canberra, 2005.
• [56] Kuo H. K., et al.: Screening for diabetic retinopathy by one-field, non-mydriatic, 45 degrees digital photography is inadequate. Ophthalmologica 219 (5): 292-296, 2005.
• [57] Schiffman R. M., et al.: Comparison of a digital retinal imaging system and seven-field stereo color fundus photography to detect diabetic retinopathy in the primary care environment. Ophthalmic Surgery, Lasers & Imaging 36 (1): 46-56, 2005.
• [58] Jelinek H. F., et al.: An automated microaneurysm detector as a tool for Identification of diabetic retinopathy in a rural optometry practice. Clin. Exp. Optom 89 (5): 299-305, 2006.
• [59] Patton N., et al.: Retinal image analysis: Concepts, applications and potential. Progress in Retinal and Eye Research 25 (1): 99-127, 2006.
• [60] Phiri R., et al.: Comparative study of the Polaroid and digital non-mydriatic cameras in the detection of referrable diabetic retinopathy in Australia. Diabetic Medicine 23 (8): 867-872, 2006.
• [61] Soares J. V. B., et al.: Retinal vessel segmentation using the 2-d Gabor wavelet and supervised classification. IEEE TMI 25 (9): 1214-1222, 2006.
• [62] Stosie T. and Stosie B. D .: Multifractal analysis of human retinal vessels. IEEE TMI 25 (8): 1101, 2006.
• [63] Martinez-Perez M. E., et al.: Segmentation of blood vessels from red-free and fluorescein retinal images. Medical Image Analysis 11 (1): 47-61, 2007.