Diabetic retinopathy detection through artificial intelligent techniques: a review and open issues

  • Uzair Ishtiaq
  • Sameem Abdul Kareem
  • Erma Rahayu Mohd Faizal Abdullah
  • Ghulam Mujtaba
  • Rashid Jahangir
  • Hafiz Yasir Ghafoor


Diabetic Retinopathy (DR) is the disease caused by uncontrolled diabetes that may lead to blindness among the patients. Due to the advancements in artificial intelligence, early detection of DR through an automated system is more beneficial over the manual detection. At present, there are several published studies on automated DR detection systems through machine learning or deep learning approaches. This study presents a review on DR detection techniques from five different aspects namely, datasets, image preprocessing techniques, machine learning-based approaches, deep learning-based approaches, and performance measures. Moreover, it also presents the authors’ observation and significance of the review findings. Furthermore, we also discuss nine new research challenges in DR detection. After a rigorous selection process, 74 primary publications were selected from eight academic databases for this review. From the selected studies, it was observed that many public datasets are available in the field of DR detection. In image preprocessing techniques, contrast enhancement combined with green channel extraction contributed the most in classification accuracy. In features, shape-based, texture-based and statistical features were reported as the most discriminative in DR detection. The Artificial Neural Network was proven eminent classifier compared to other machine learning classifiers. In deep learning, Convolutional Neural Network outperformed compared to other deep learning networks. Finally, to measure the classification performance, accuracy, sensitivity, and specificity metrics were mostly employed. This review presents a comprehensive summary of DR detection techniques and will be proven useful for the community of scientists working in the field of automated DR detection techniques.


Diabetic retinopathy Convolutional neural network DIARETDB1 Image preprocessing Artificial neural network Transfer learning 



  1. 1.
    Abbas Q et al (2017) Automatic recognition of severity level for diagnosis of diabetic retinopathy using deep visual features. Med Biol Eng Comput 55(11):1959–1974CrossRefGoogle Scholar
  2. 2.
    Abdel-Hakim AE, Farag AA (2006) CSIFT: A SIFT descriptor with color invariant characteristics. Comput Vision Pattern Recogn, 2006 IEEE Comput Soc Conf. IEEEGoogle Scholar
  3. 3.
    Abramoff MD et al (2016) Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest Ophthalmol Vis Sci 57(13):5200–5206CrossRefGoogle Scholar
  4. 4.
    Aiello LP et al (1998) Diabetic retinopathy. Diabetes Care 21(1):143–156CrossRefGoogle Scholar
  5. 5.
    Al-Jarrah MA, Shatnawi H (2017) Non-proliferative diabetic retinopathy symptoms detection and classification using neural network. J Med Eng Technol 41(6):498–505CrossRefGoogle Scholar
  6. 6.
    Almotiri J, Elleithy K, Elleithy A (2018) Retinal vessels segmentation techniques and algorithms: a survey. Applied Sciences-Basel 8(2):31Google Scholar
  7. 7.
    Amin J, Sharif M, Yasmin M (2016) A review on recent developments for detection of diabetic retinopathy. Scientifica: 20Google Scholar
  8. 8.
    Antal B, Hajdu A (2014) An ensemble-based system for automatic screening of diabetic retinopathy. Knowl-Based Syst 60:20–27CrossRefGoogle Scholar
  9. 9.
    Arunkumar R, Karthigaikumar P (2017) Multi-retinal disease classification by reduced deep learning features. Neural Comput & Applic 28(2):329–334CrossRefGoogle Scholar
  10. 10.
    Bala MP, Vijayachitra S (2014) Early detection and classification of microaneurysms in retinal fundus images using sequential learning methods. Int J Biomed Eng Technol 15(2):128–143CrossRefGoogle Scholar
  11. 11.
    Barkana BD, Saricicek I, Yildirim B (2017) Performance analysis of descriptive statistical features in retinal vessel segmentation via fuzzy logic, ANN, SVM, and classifier fusion. Knowl-Based Syst 118:165–176CrossRefGoogle Scholar
  12. 12.
    Biyani RS, Patre BM, IEEE (2016) A clustering approach for exudates detection in screening of diabetic retinopathy. 2016 International Conference on Signal and Information Processing. IEEE, New YorkGoogle Scholar
  13. 13.
    Budak U et al (2017) A novel microaneurysms detection approach based on convolutional neural networks with reinforcement sample learning algorithm. Health Inform Sci Syst 5:10CrossRefGoogle Scholar
  14. 14.
    Bui T, et al (2017) Detection of cotton wool for diabetic retinopathy analysis using neural network. 2017 Ieee 10th International Workshop on Computational Intelligence and Applications. IEEE, New York, pp. 203-206Google Scholar
  15. 15.
    Carrera EV, Gonzalez A, Carrera R (2017) Automated detection of diabetic retinopathy using SVMGoogle Scholar
  16. 16.
    Chen X, He F, Yu H (2018) A matting method based on full feature coverage. Multimed Tools Appl: 1–29Google Scholar
  17. 17.
    Chen G et al (2009) Measuring agreement of administrative data with chart data using prevalence unadjusted and adjusted kappa. BMC Med Res Methodol 9:5–5CrossRefGoogle Scholar
  18. 18.
    Choi JY et al (2017) Multi-categorical deep learning neural network to classify retinal images: a pilot study employing small database. PLoS One 12(11):16Google Scholar
  19. 19.
    Chudzik P et al (2018) Microaneurysm detection using fully convolutional neural networks. Comput Methods Prog Biomed 158:185–192CrossRefGoogle Scholar
  20. 20.
    Cigizoglu HK, Alp M (2006) Generalized regression neural network in modelling river sediment yield. Adv Eng Softw 37(2):63–68CrossRefGoogle Scholar
  21. 21.
    Dasgupta A, Singh S (2017) A fully convolutional neural network based structured prediction approach towards the retinal vessel segmentationGoogle Scholar
  22. 22.
    Doshi D, et al (2016) Diabetic retinopathy detection using deep convolutional neural networks. in 2016 International Conference on Computing, Analytics and Security Trends (CAST)Google Scholar
  23. 23.
    Fong DS et al (2004) Diabetic retinopathy. Diabetes Care 27(10):2540–2553CrossRefGoogle Scholar
  24. 24.
    Franklin SW, Rajan SE (2014) Computerized screening of diabetic retinopathy employing blood vessel segmentation in retinal images. Biocybernet Biomed Eng 34(2):117–124CrossRefGoogle Scholar
  25. 25.
    Fraz MM et al (2017) Multiscale segmentation of exudates in retinal images using contextual cues and ensemble classification. Biomedical Signal Processing and Control 35:50–62CrossRefGoogle Scholar
  26. 26.
    Ganesan K et al (2014) Computer-aided diabetic retinopathy detection using trace transforms on digital fundus images. Med Biol Eng Comput 52(8):663–672CrossRefGoogle Scholar
  27. 27.
    Gargeya R, Leng T (2017) Automated identification of diabetic retinopathy using deep learning. Ophthalmology 124(7):962–969CrossRefGoogle Scholar
  28. 28.
    Gegundez-Arias ME et al (2017) A tool for automated diabetic retinopathy pre-screening based on retinal image computer analysis. Comput Biol Med 88(C):100–109CrossRefGoogle Scholar
  29. 29.
    Ghosh R, Ghosh K, Maitra S (2017) Automatic detection and classification of diabetic retinopathy stages using CNNGoogle Scholar
  30. 30.
    Gondal WM et al (2017) Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images. 2017 IEEE Int Conf Image Process (ICIP)Google Scholar
  31. 31.
    Group, E.T.D.R.S.R (1991) Grading diabetic retinopathy from stereoscopic color fundus photographs—an extension of the modified Airlie House classification: ETDRS report number 10. Ophthalmology 98(5):786–806CrossRefGoogle Scholar
  32. 32.
    Guerra L et al (2011) Comparison Between Supervised and Unsupervised Classifications of Neuronal Cell Types: A Case Study. Dev Neurobiol 71(1):71–82CrossRefGoogle Scholar
  33. 33.
    Gulshan V et al (2016) Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. Jama-J Am Med Assoc 316(22):2402–2410CrossRefGoogle Scholar
  34. 34.
    Hanúsková V et al (2013) Diabetic retinopathy screening by bright lesions extraction from fundus images. J Electr Eng 64(5):311–316Google Scholar
  35. 35.
    Hemanth DJ, Anitha J, Indumathy A (2016) Diabetic retinopathy diagnosis in retinal images using hopfield neural network. IETE J Res 62(6):893–900CrossRefGoogle Scholar
  36. 36.
    Jaya T, Dheeba J, Singh NA (2015) Detection of hard exudates in colour fundus images using fuzzy support vector machine-based expert system. J Digit Imaging 28(6):761–768CrossRefGoogle Scholar
  37. 37.
    Jia Y et al (2014) Caffe: Convolutional architecture for fast feature embedding. Proc 22nd ACM Int Conference on Multimedia. ACMGoogle Scholar
  38. 38.
    Jiang Y, Wu H, Dong J (2017) Automatic screening of diabetic retinopathy images with convolution neural network based on caffe framework. Proc 1st Int Conf Med Health Inform 2017. ACM: Taichung City: 90–94Google Scholar
  39. 39.
    Jordan KC et al (2017) A review of feature-based retinal image analysis. Expert Rev Ophthalmol 12(3):207–220CrossRefGoogle Scholar
  40. 40.
    Joshi S, Karule PT (2018) A review on exudates detection methods for diabetic retinopathy. Biomed Pharmacother 97:1454–1460CrossRefGoogle Scholar
  41. 41.
    Kavitha M, Palani S (2014) Hierarchical classifier for soft and hard exudates detection of retinal fundus images. J Intell Fuzzy Syst 27(5):2511–2528Google Scholar
  42. 42.
    Kolb H (1995) Simple anatomy of the retina. In: Kolb H, Fernandez E, Nelson R (eds) Webvision: the organization of the retina and visual system. University of Utah Health Sciences Center Copyright: (c) 2018 Webvision, Salt Lake CityGoogle Scholar
  43. 43.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systemsGoogle Scholar
  44. 44.
    Kusakunniran W et al (2018) Hard exudates segmentation based on learned initial seeds and iterative graph cut. Comput Methods Prog Biomed 158:173–183CrossRefGoogle Scholar
  45. 45.
    LeCun Y et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRefGoogle Scholar
  46. 46.
    Li G, Zheng S, Li X (2018) Exudate detection in fundus images via convolutional neural network: 193–202Google Scholar
  47. 47.
    Li X, et al (2017) Convolutional neural networks based transfer learning for diabetic retinopathy fundus image classification. in 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)Google Scholar
  48. 48.
    Mahendran G, Dhanasekaran R (2015) Investigation of the severity level of diabetic retinopathy using supervised classifier algorithms. Comput Electr Eng 45:312–323CrossRefGoogle Scholar
  49. 49.
    Mane VM, Jadhav DV, Shirbahadurkar SD (2017) Hybrid classifier and region-dependent integrated features for detection of diabetic retinopathy. J Intell Fuzzy Syst 32(4):2837–2844CrossRefGoogle Scholar
  50. 50.
    Mansour RF (2018) Deep-learning-based automatic computer-aided diagnosis system for diabetic retinopathy. Biomed Eng Lett 8(1):41–57CrossRefGoogle Scholar
  51. 51.
    Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 27(10):1615–1630CrossRefGoogle Scholar
  52. 52.
    Mo J, Zhang L (2017) Multi-level deep supervised networks for retinal vessel segmentation. Int J Comput Assist Radiol Surg 12(12):2181–2193CrossRefGoogle Scholar
  53. 53.
    Mumtaz R et al (2018) Automatic detection of retinal hemorrhages by exploiting image processing techniques for screening retinal diseases in diabetic patients. Int J Diab Dev Countries 38(1):80–87CrossRefGoogle Scholar
  54. 54.
    Naqvi SAG, Zafar MF, ul Haq I (2015) Referral system for hard exudates in eye fundus. Comput Biol Med 64:217–235CrossRefGoogle Scholar
  55. 55.
    Nijalingappa P, Sandeep B (2016) Machine learning approach for the identification of diabetes retinopathy and its stagesGoogle Scholar
  56. 56.
    Omar M, Khelifi F, Tahir MA (2016) Detection and classification of retinal fundus images exudates using region based multiscale LBP texture approachGoogle Scholar
  57. 57.
    Orlando JI et al (2018) An ensemble deep learning based approach for red lesion detection in fundus images. Comput Methods Prog Biomed 153(C):115–127CrossRefGoogle Scholar
  58. 58.
    Ouyang W, et al (2014) Deepid-net: multi-stage and deformable deep convolutional neural networks for object detection. arXiv preprint arXiv:1409.3505Google Scholar
  59. 59.
    Paing MP, Choomchuay S, Rapeeporn Yodprom MD (2017) Detection of lesions and classification of diabetic retinopathy using fundus imagesGoogle Scholar
  60. 60.
    Perdomo O, Arevalo J, Gonzalez FA (2017) Convolutional network to detect exudates in eye fundus images of diabetic subjectsGoogle Scholar
  61. 61.
    Ponnibala M, Vijayachitra S (2014) A sequential learning method for detection and classification of exudates in retinal images to assess diabetic retinopathy. J Biol Syst 22(3):16CrossRefGoogle Scholar
  62. 62.
    Pratt H et al (2016) Convolutional neural networks for diabetic retinopathy. Proc Comput Sci 90:200–205CrossRefGoogle Scholar
  63. 63.
    Prentasic P, Loncaric S (2014) Weighted ensemble based automatic detection of exudates in fundus photographs. Conf Proc IEEE Eng Med Biol Soc 2014:138–141Google Scholar
  64. 64.
    Prentašić P, Lončarić S (2015) Detection of exudates in fundus photographs using convolutional neural networks. 2015 9th Int Sym Image Signal Process Anal (ISPA)Google Scholar
  65. 65.
    Prentasic P, Loncaric S (2016) Detection of exudates in fundus photographs using deep neural networks and anatomical landmark detection fusion. Comput Methods Prog Biomed 137:281–292CrossRefGoogle Scholar
  66. 66.
    Quellec G et al (2017) Deep image mining for diabetic retinopathy screening. Med Image Anal 39:178–193CrossRefGoogle Scholar
  67. 67.
    Rahim SS et al (2016) Automatic detection of microaneurysms in colour fundus images for diabetic retinopathy screening. Neural Comput Applic 27(5):1149–1164CrossRefGoogle Scholar
  68. 68.
    Rahimy E (2018) Deep learning applications in ophthalmology. Curr Opin Ophthalmol 29(3):254–260CrossRefGoogle Scholar
  69. 69.
    Reshma Chand CP, Dheeba J (2015) Automatic detection of exudates in color fundus retinopathy images. Ind J Sci Technol 8(26)Google Scholar
  70. 70.
    Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. Int Conf Med Image Comput Computer-Assist Interven. SpringerGoogle Scholar
  71. 71.
    Roy P, et al (2017) A novel hybrid approach for severity assessment of diabetic retinopathy in colour fundus images. 2017 Ieee 14th Int Sym Biomed Imaging. IEEE, New York: 1078–1082Google Scholar
  72. 72.
    Santhi D et al (2016) Segmentation and classification of bright lesions to diagnose diabetic retinopathy in retinal images. Biomed Engineering-Biomedizinische Technik 61(4):443–453MathSciNetCrossRefGoogle Scholar
  73. 73.
    Shan J, Li L, IEEE (2016) A deep learning method for microaneurysm detection in fundus images. 2016 Ieee First International Conference on Connected Health: Applications, Systems and Engineering Technologies. IEEE, New York, 357-358Google Scholar
  74. 74.
    Shirbahadurkar SD, Mane VM, Jadhav DV (2018) Early stage detection of diabetic retinopathy using an optimal feature set: 15–23Google Scholar
  75. 75.
    Shu Wei Ting D et al (2017) Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA: J Am Med Assoc 318(22):2211–2223CrossRefGoogle Scholar
  76. 76.
    Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556Google Scholar
  77. 77.
    Simó-Servat O, Hernández C, Simó R (2013) Genetics in Diabetic Retinopathy: Current Concepts and New Insights. Curr Genom 14(5):289–299CrossRefGoogle Scholar
  78. 78.
    Sinthanayothin C et al (2002) Automated detection of diabetic retinopathy on digital fundus images. Diabet Med 19(2):105–112CrossRefGoogle Scholar
  79. 79.
    Sisodia DS, Nair S, Khobragade P (2017) Diabetic retinal fundus images: preprocessing and feature extraction for early detection of diabetic retinopathy. Biomed Pharmacol J 10(2):615–626CrossRefGoogle Scholar
  80. 80.
    Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manag 45(4):427–437CrossRefGoogle Scholar
  81. 81.
    Somasundaram SK, Alli P (2017) A machine learning ensemble classifier for early prediction of diabetic retinopathy. J Med Syst 41(12):1–12Google Scholar
  82. 82.
    Sopharak A, Uyyanonvara B, Barman S (2013) Automated microaneurysm detection algorithms applied to diabetic retinopathy retinal images. Maejo Int J Sci Technol 7(2):294–314Google Scholar
  83. 83.
    Srivastava R et al (2017) Detecting retinal microaneurysms and hemorrhages with robustness to the presence of blood vessels. Comput Methods Prog Biomed 138:83–91CrossRefGoogle Scholar
  84. 84.
    Szegedy C, et al (2015) Going deeper with convolutions. CVPRGoogle Scholar
  85. 85.
    Szegedy C, et al (2015) Going deeper with convolutions. Proc IEEE Conf Comput Vision Pattern RecognGoogle Scholar
  86. 86.
    Takahashi H et al (2017) Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy. PLoS One 12(6):e0179790CrossRefGoogle Scholar
  87. 87.
    Tan JH et al (2017) Automated segmentation of exudates, haemorrhages, microaneurysms using single convolutional neural network. Inf Sci 420:66–76CrossRefGoogle Scholar
  88. 88.
    Tan JH et al (2017) Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network. J Comput Sci 20:70–79Google Scholar
  89. 89.
    van Grinsven M et al (2016) Fast convolutional neural network training using selective data sampling: application to hemorrhage detection in color fundus images. IEEE Trans Med Imaging 35(5):1273–1284CrossRefGoogle Scholar
  90. 90.
    Vanithamani R, Renee Christina R (2018) Exudates in detection and classification of diabetic retinopathy: 252–261Google Scholar
  91. 91.
    Vashist P et al (2011) Role of early screening for diabetic retinopathy in patients with diabetes mellitus: an overview. Ind J Commun Med: Off Publ Indian Assoc Prev Social Med 36(4):247–252CrossRefGoogle Scholar
  92. 92.
    Vega R et al (2015) Retinal vessel extraction using lattice neural networks with dendritic processing. Comput Biol Med 58:20–30CrossRefGoogle Scholar
  93. 93.
    Wang SL et al (2015) Hierarchical retinal blood vessel segmentation based on feature and ensemble learning. Neurocomputing 149:708–717CrossRefGoogle Scholar
  94. 94.
    Wang S et al (2017) Localizing microaneurysms in fundus images through singular spectrum analysis. IEEE Trans Biomed Eng 64(5):990–1002CrossRefGoogle Scholar
  95. 95.
    Wong TY, Bressler NM (2016) Artificial intelligence with deep learning technology looks into diabetic retinopathy screening. Jama 316(22):2366–2367CrossRefGoogle Scholar
  96. 96.
    Wu JY, et al (2015) New hierarchical approach for microaneurysms detection with matched filter and machine learning. 2015 37th Annual International Conference of the Ieee Engineering in Medicine and Biology Society. IEEE, New York: 4322–4325Google Scholar
  97. 97.
    Xiao ZT et al (2017) Automatic non-proliferative diabetic retinopathy screening system based on color fundus image. Biomed Eng Online 16:19CrossRefGoogle Scholar
  98. 98.
    Xiao D, et al (2017) Retinal hemorrhage detection by rule-based and machine learning approachGoogle Scholar
  99. 99.
    Xu KL, Feng DW, Mi HB (2017) Deep convolutional neural network-based early automated detection of diabetic retinopathy using fundus image. Molecules 22(12):7Google Scholar
  100. 100.
    Yang Y, et al (2017) Lesion detection and grading of diabetic retinopathy via two-stages deep convolutional neural networks: 533–540Google Scholar
  101. 101.
    Youden WJ (1950) Index for rating diagnostic tests. Cancer 3(1):32–35CrossRefGoogle Scholar
  102. 102.
    Yu H, He F, Pan Y (2018) A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation. Multimed Tools Appl: 1-20Google Scholar
  103. 103.
    Yu H, He F, Pan Y (2018) A novel region-based active contour model via local patch similarity measure for image segmentation. Multimed Tools Appl: 1–23Google Scholar
  104. 104.
    Yu S, Xiao D, Kanagasingam Y (2017) Exudate detection for diabetic retinopathy with convolutional neural networksGoogle Scholar
  105. 105.
    Zhou W et al (2017) Automatic microaneurysm detection using the sparse principal component analysis-based unsupervised classification method. IEEE Access 5:2563–2572CrossRefGoogle Scholar
  106. 106.
    Zhou W et al (2017) Automatic microaneurysms detection based on multifeature fusion dictionary learning. Comput Math Methods Med 2017Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Uzair Ishtiaq
    • 1
    • 2
  • Sameem Abdul Kareem
    • 1
  • Erma Rahayu Mohd Faizal Abdullah
    • 1
  • Ghulam Mujtaba
    • 3
  • Rashid Jahangir
    • 1
    • 2
  • Hafiz Yasir Ghafoor
    • 1
    • 2
  1. 1.Department of Artificial Intelligence, Faculty of Computer Science and Information TechnologyUniversity of MalayaKuala LumpurMalaysia
  2. 2.Department of Computer ScienceCOMSATS University IslamabadVehariPakistan
  3. 3.Department of Computer ScienceSukkur IBA UniversitySukkurPakistan

Personalised recommendations