Abstract
Diabetic retinopathy (DR) is one of the most important causes of visual impairment. Automatic recognition of DR lesions, like hard exudates (EXs), in retinal images can contribute to the diagnosis and screening of the disease. The aim of this study was to automatically detect these lesions in fundus images. To achieve this goal, each image was normalized and the candidate EX regions were segmented by a combination of global and adaptive thresholding. Then, a group of features was extracted from image regions and the subset which best discriminated between EXs and retinal background was selected by means of logistic regression (LR). This optimal subset was subsequently used as input to a radial basis function (RBF) neural network. To improve the performance of the proposed algorithm, some noisy regions were eliminated by an innovative postprocessing of the image. The main novelty of the paper is the use of LR in conjunction with RBF and the proposed postprocessing technique. Our database was composed of 117 images with variable color, brightness and quality. The database was divided into a training set of 50 images (from DR patients) and a test set of 67 images (40 from DR patients and 27 from healthy retinas). Using a lesion-based criterion (pixel resolution), a mean sensitivity of 92.1% and a mean positive predictive value of 86.4% were obtained. With an image-based criterion, a mean sensitivity of 100%, mean specificity of 70.4% and mean accuracy of 88.1% were achieved. These results suggest that the proposed method could be a diagnostic aid for ophthalmologists in the screening for DR.
Similar content being viewed by others
References
Akita, K., and H. Kuga. A computer method of understanding ocular fundus images. Pattern Recognit. 15:431–443, 1982. doi:10.1016/0031-3203(82)90022-X.
Bishop, C. M. Neural Networks for Pattern Recognition. Oxford: Oxford University Press, 482 pp., 1995.
Bonner, A., and H. Liu. Comparison of discrimination methods for peptide classification in tandem mass spectrometry. In: Proceedings of the IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, La Jolla, EEUU, 2004, pp. 160–167.
Chen, C. M., Y. H. Chou, K. C. Han, G. S. Hung, C. M. Tiu, H. J. Chiou, and S. Y. Chiou. Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks. Radiology 226(2): 504–514, 2003. doi:10.1148/radiol.2262011843.
Chen, S., C. F. N. Cowan, and P. M. Grant. Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans. Neural Netw. 2:302–309, 1991. doi:10.1109/72.80341.
Cree, M. J., J. A. Olson, K. C. McHardy, P. F. Sharp, and J. V. Forrester. The preprocessing of retinal images for the detection of fluorescein leakage. Phys. Med. Biol. 44:293–308, 1999. doi:10.1088/0031-9155/44/1/021.
Ege, B. M., O. K. Hejlesen, O. V. Larsen, K. Møller, B. Jennings, D. Kerr, and D. A. Cavan. Screening for diabetic retinopathy using computer based image analysis and statistical classification. Comput. Methods Programs Biomed. 62:165–175, 2000. doi:10.1016/S0169-2607(00)00065-1.
Fong, D. S., L. Aiello, T. W. Gardner, G. L. King, G. Blankenship, J. D. Cavallerano, F. L. Ferris, and R. Klein. Diabetic retinopathy. Diabetes Care 26:226–229, 2003. doi:10.2337/diacare.26.1.226.
Foracchia, M., E. Grisan, and A. Ruggeri. Luminosity and contrast normalization in retinal images. Med. Image Anal. 9:179–190, 2005. doi:10.1016/j.media.2004.07.001.
García, M., R. Hornero, C. I. Sánchez, M. I. López, and A. Díez. Feature extraction and selection for the automatic detection of hard exudates in retinal images. In: Proceedings of the 29th Ann. Int. Conf. of the IEEE EMBS, Lyon, France, 2007, pp. 4969–4972.
García, M., C. I. Sánchez, M. I. López, D. Abásolo and R. Hornero. Neural network based detection of hard exudates in retinal images. Comput. Methods Programs Biomed. 93: 9–19, 2009. doi:10.1016/j.cmpb.2008.07.006.
Gardner, G. G., D. Keating, T. H. Williamson, and A. T. Elliot. Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool. Br. J. Ophthalmol. 80:940–944, 1996. doi:10.1136/bjo.80.11.940.
González, R. C., and R. E. Woods. Digital Image Processing. New Jersey: Prentice Hall, 793 pp., 1995.
Grisan, E., and A. Ruggeri. A hierarchical Bayesian classification for non-vascular lesions detection in fundus images. In: Proceedings of the Third European Medical and Biological Engineering Conference, Prague, Czech Republic, Vol. 11, 2005.
Grisan, E., and A. Ruggeri. Segmentation of candidate dark lesions in fundus images based on local thresholding and pixel density. In: Proceedings of the 29th Ann. Int. Conf. of the IEEE EMBS, Lyon, France, 2007, pp. 6735–6738.
Haykin, S. Neural Networks: A Comprehensive Foundation. Upper Saddle River: Prentice-Hall International, 842 pp., 1999.
Holz, H. J., and M. H. Loew. Multi-class classifier-independent feature analysis. Pattern Recognition Lett. 18:1219–1224, 1997.
Hosmer, D. W., and S. Lemeshow. Applied Logistic Regression. New York: John Wiley, 307 pp., 1989.
Jain, A. K. Fundamentals of Digital Image Processing. Englewood Cliffs: Prentice Hall, 569 pp., 1989.
Javitt, J. C., J. K. Canner, R. G. Frank, D. M. Steinwachs, and A. Sommer. Detecting and treating retinopathy in patients with type I diabetes mellitus. A health policy model. Ophthalmology. 97:483–494, 1990.
Jobson, J. D. Applied Multivariate Data Analysis Vol. 2: Categorical and Multivariate Methods. New York: Springer, 731 pp., 1992.
Klein, R., B. E. Klein, S. E. Moss, M. D. Davis, and D. L. DeMets. The Wisconsin epidemiologic study of diabetic retinopathy VII. Diabetic nonproliferative retinal lesions. Ophthalmology. 94:1389–1400, 1987.
Li, H., and O. Chutatape. Fundus image features extraction. In: Proceedings of the 22th Ann. Int. Conf. of the IEEE EMBS, Chicago, USA, 2000, pp. 3071–3073.
Li, H., and O. Chutatape. Automated feature extraction in color retinal images by a model based approach. IEEE Trans. Biomed. Eng. 51:246–254, 2004. doi:10.1109/TBME.2003.820400.
Lin, D. Y., M. S. Blumenkranz, S. J. Brothers, and D. M. Grosvenor. The sensitivity and specificity of single-field nonmydriatic monochromatic digital fundus photography with remote image interpretation for diabetic retinopathy screening: a comparison with ophthalmoscopy and standardized mydriatic color photography. Am. J. Ophthalmol. 134(2): 204–213, 2002. doi:10.1016/S0002-9394(02)01522-2.
Loew, M. H. “Feature extraction.” In: Handbook of medical imaging, edited by M. Sonka and J. M. Fitzpatrick. Bellingham: SPIE Press, 2000, pp. 273–341.
Moody, J. “Prediction risk and architecture selection for neural networks.” In: From statistics to neural networks: theory and pattern recognition applications, edited by V. Cherkassky, J. H. Friedman and H. Wechsler. Berlin: Springer-Verlag, 1994, pp. 147–165.
Nadler, M., and E. Smith. Pattern recognition engineering. New York: John Wiley, 1993.
Niemeijer, M., M. Abràmoff, and B. van Ginneken. Automatic detection of the presence of bright lesions in color fundus photographs. In: Proceedings of the Third European Medical and Biological Engineering Conference, Prague, Czech Republic, Vol. 11, 2005.
Niemeijer, M., B. van Ginneken, S. R. Russell, M. S. A. Suttorp-Schulten, and M. Abràmoff. Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis. Invest. Ophthalmol. Vis. Sci. 48(5): 2260–2267, 2007. doi:10.1167/iovs.06-0996.
Ong, G. L., L. G. Ripley, R. S. Newsom, M. Cooper, and A. G. Casswell. Screening for sight-threatening diabetic retinopathy: comparison of fundus photography with automated color contrast threshold test. Am. J. Ophthalmol.17:445–452, 2004. doi:10.1016/j.ajo.2003.10.021.
Osareh, A. Automated identification of diabetic retinal exudates and the optic disc. Ph.D. thesis, Bristol, 2004.
Phillips, R., J. Forrester, and P. Sharp. Automated detection and quantification of retinal exudates. Graefes Arch. Clin. Exp. Ophthalmol. 231:90–94, 1993. doi:10.1007/BF00920219.
Pohar, M., M. Blas, and S. Turk. Comparison of logistic regression and linear discriminant analysis: a simulation study. Metodološki zvezki. 1: 143–161, 2004.
Pratt, W. K. Digital Image processing. New Jersey: Wiley-Interscience, 782 pp., 2007.
Sánchez, C. I., R. Hornero, M. I. López, M. Aboy, J. Poza, and D. Abásolo. A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis. Med. Eng. Phys. 30: 350–357, 2007. doi:10.1016/j.medengphy.2007.04.010.
Sánchez, C. I., A. Mayo, M. García, M. I. López, and R. Hornero. Automatic image processing algorithm to detect hard exudates based on mixture models. In: Proceedings of the 28th Ann. Int. Conf. of the IEEE EMBS, New York, USA, 2006, pp. 4453–4456.
Sleigh, J. W., D. A. Steyn-Ross, M. L. Steyn-Ross, C. Grant, and G. Ludbrook. Cortical entropy changes with general anaesthesia: theory and experiment. Physiol. Meas. 25:921–934, 2004. doi:10.1088/0967-3334/25/4/011.
Sonka, M., V. Hlavac, and R. Boyle. Image Processing, Analysis and Machine Vision. London: International Thomson Computer Press, 555 pp., 1996.
Teng, T., M. Lefley, and D. Claremont. Progress towards automated diabetic ocular screening: A review of image analysis and intelligent systems for diabetic retinopathy. Med. Biol. Eng. Comput. 40:2–13, 2002. doi:10.1007/BF02347689.
Tikhonov, N. On solving incorrectly posed problems and method of regularization. Dokl. Akad. Nauk. 151:501–504, 1963.
Walter, T., J.-C. Klein, P. Massin, and A. Erginay. A contribution of image processing to the diagnosis of diabetic retinopathy—Detection of exudates in color fundus images of the human retina. IEEE Trans. Med. Imaging. 21:1236–1243, 2002. doi:10.1109/TMI.2002.806290.
Wang, H., W. Hsu, K. G. Goh, and M. L. Lee. An effective approach to detect lesions in color retinal images. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Singapore, 2000, pp. 181–186.
Ward, N.P., S. Tomlinson, and C. J. Taylor. Image analysis of fundus photographs. The detection and measurement of exudates associated with diabetic retinopathy. Ophthalmology. 96:80–86, 1989.
Working Party of the British Diabetic Association. Retinal Photography Screening for Diabetic Eye Disease. A British Diabetic Association Report, London, 1997.
World Health Organisation. Prevention of Blindness from Diabetes Mellitus: Report of a WHO Consultation in Geneva, Switzerland. WHO Library Cataloguing-in-Publication Data, Switzerland, 2005.
Zahlman, G., B. Kochner, I. Ugi, D. Schuhmann, B. Lisenfeld, A. Wegner, M. Obermaier, and M. Mertz. Hybrid fuzzy image processing for situation assessment: A knowledge-based system for early detection of diabetic retinopathy. IEEE Eng. Med. Biol. Mag. 19:76–83, 2000. doi:10.1109/51.816246.
Zhang, X., and O. Chutatape. Top-down and bottom-up strategies in lesion detection of background diabetic retinopathy. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Singapore, 2005, pp. 422–428.
Zhao, R., X. Guowang, B. Yue, H. M. Liebich, and Y. Zhang. Artificial neural network classification based on capillary electrophoresis of urinary nucleosides for the clinical diagnosis of tumors. J. Chromatogr. A.828: 489–496, 1998. doi:10.1016/S0021-9673(98)00589-5.
Acknowledgments
This work has been partially supported by the grant project GSR 236/A/08 from “Consejería de Sanidad de la Junta de Castilla y León” and by the “Ministerio de Ciencia e Innovación” under grant TEC2008-02241.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
García, M., Sánchez, C.I., Poza, J. et al. Detection of Hard Exudates in Retinal Images Using a Radial Basis Function Classifier. Ann Biomed Eng 37, 1448–1463 (2009). https://doi.org/10.1007/s10439-009-9707-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10439-009-9707-0