根據世界衛生組織統計，預估2030年糖尿病患者將會成長至366百萬人，其中因糖尿病而引發的糖尿病視網膜病變是成年人致盲主因之一，其病變特徵有微血管瘤、出血、滲出物等。本研究發展出一套糖尿病視網膜病變眼底影像量化評估系統，擷取視網膜病變特徵，並以支援向量機進行病變的分類與識別，可以辨識並計算病變的區域面積與成長趨勢等量化資訊，其正確率可達94％。

According to the World Health Organization, the total number of diabetic patients will grow to 366 million in 2030. One of serious complications caused by diabetes is retinopathy which will lead to blindness. The symptoms of retinopathy include microaneurysms, hemorrhages, and exudates. This paper proposes a quantitative evaluation system for diabetic retinopathy fundus image. The system extracts retinal lesion features and uses support vector machine for lesion classification. The system achieves an average of 94% of accuracy for lesion identification.

Athanasopoulos, A., Dimou, A., Mezaris, V., & Kompatsiaris, I. (2011). GPU acceleration for support vector machines. Paper presented at International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), Delft, Netherlands.
Badea, P., Danciu, D., & Davidescu, L. (2008). Preliminary results on using an extension of gradient method for detection of red lesions on eye fundus photographs. Paper presented at Automation, Quality and Testing, Robotics (AQTR), Cluj-Napoca, Romania.
Chang, C. C., & Lin, C. J. (2011). LIBSVM : a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST), 2(2), 27-54.
Chaudhuri, S., Chatterjee, S., Katz, N., Nelson, M., & Goldbaum, M. (1989). Detection of blood vessels in retinal images using two-dimensional matched filters. Medical Imaging, 8(3), 263-269.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20, 273-597.
Garcia, M., Sanchez, C. I., Lopez, M. I., Diez, A., & Hornero, R. (2008, August). Automatic detection of red lesions in retinal images using a multilayer perceptron neural network. Paper presented at Engineering in Medicine and Biology Society (EMBS), Vancouver, Canada.
Ghadiri, F., Pourreza, H., Banaee, T., & Delgir, M. (2011, December). Retinal vessel tortuosity evaluation via Circular Hough Transform. Paper presented at Iranian Conference on BioMedical Engineering (ICBME), Tehran, Iran.
Giancardo, L., Meriaudeau, F., Karnowski, T. P., Li, Y., Tobin, K. W., & Chaum, E. (2011, March). Automatic retina exudates segmentation without a manually labelled training set. Paper presented at International Symposium on Biomedical Imaging: From Nano to Macro (ISBI), Chicago, USA.
Hafez, M., & Azeem, S. A. (2002, May). Using adaptive edge technique for detecting microaneurysms in fluorescein angiograms of the ocular fundus. Paper presented at Electrotechnical Conference (MELECON), Cairo, Egypt.
Jaafar, H. F., Nandi, A. K., & Al-Nuaimy, W. (2010, August). Detection of exudates in retinal images using a pure splitting technique. Paper presented at Engineering in Medicine and Biology Society (EMBS), Buenos Aires, Argentina.
Jaafar, H. F., Nandi, A. K., & Al-Nuaimy, W. (2011, August). Automated detection of red lesions from digital colour fundus photographs. Paper presented at Engineering in Medicine and Biology Society (EMBS), Boston, USA.
Kande, G. B., Savithri, T. S., Subbaiah, P. V., & Tagore, M. R. M. (2009, June). Detection of red lesions in digital fundus images. Paper presented at Biomedical Imaging: From Nano to Macro (ISBI), Boston, USA.
Kauppi, T., Kalesnykiene, V., Kamarainen, J. K., Lensu, L., Sorri, I., Uusitalo, H., Kälviäinen, H., & Pietil, J. (2006). DIARETDB0: evaluation database and methodology for diabetic retinopathy algorithms. Lappeenranta: Lappeenranta University of Technology.
Niemeijer, M., Ginneken, B. V., Staal, J., Maria, S. A., & Michael, D. (2005, May). Automatic detection of red lesions in digiital color fundus photographs. Transactions on medical imaging, 14(5), 584-592.
Otsu, N. (1979). A trreshold selection method from gray-level histogreams. IEEE transactions on systems, man, and cybernetics, 9(1), 62-66.
Rocha, A., Carvalho, T., Jelinek, H. F., Goldenstein, S., & Wainer, J. (2012). Points of interest and visual dictionaries for automatic retinal lesion Detection. Biomedical Engineering, IEEE Transactions on, 59(8), 2244-2253.
Selvathi, D., & Balagopal, N. (2012, March). Detection of retinal blood vessels using curvelet transform. Paper presented at International Conference on Devices, Circuits and Systems (ICDCS), Coimbatore, India.
Tamilarasi, M., & Duraiswamy, K. (2013, January). Genetic based fuzzy seeded region growing segmentation for diabetic retinopathy images, Paper presented at International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, India.
Verma, K., Deep, P., & Ramakrishnan, A. G. (2011, December). Detection and classification of diabetic retinopathy using retinal images. Paper presented at India Conference (INDICON), Hyderabad, India.
Wild, S., Roglic, G., Green, A., Sicree, R., & King, H. (2004). Global prevalence of diabetes estimates for year 2000 and projections for 2030. Diabetes Care, 27(5), 1047–1053.
Wu, D., Zhang, M., Liu, J. C., & Bauman, W. (2006). On the adaptive detection of blood vessels in retinal images. Biomedical Engineering, 53(2), 341-343.
Zhang, X. H., & Chutatape, A. (2004, October). Detection and classification of bright lesions in color fundus images, Paper presented at International Conference on Image Processing (ICIP), Singapore.