Efficient hybrid approach to segment and classify exudates for DR prediction

  • Muhammad Sharif
  • Javeria Amin
  • Mussarat YasminEmail author
  • Amjad Rehman


Diabetic retinopathy (DR) is initiated due to the severity of diabetes which can finally lead to an incurable blindness. It is a significant reason for optical damage that may cause blindness permanently. There are no main symptoms of DR appearing initially but its quantity and severity rises with the passage of time. Initial screening and diagnosis of DR may help to stop vision loss. Exudates (EXs) are one of the primary clinical symptoms of DR. In this manuscript, a computerized technique is proposed for DR detection based on EXs. The proposed system is consisting of four major steps. The first step is enhancement of region of interest using median filter and adaptive contrast enhancement method. After that, local variance and global threshold methods are utilized for candidate lesions segmentation. Moreover, texture features with multiple classifiers are applied for classification. The proposed method is evaluated in terms of sensitivity, specificity, accuracy and area under curve on DIARETDB1, MESSIDOR and local data sets.


Green channel Median filter Global threshold Local binary pattern (LBP) Histogram orientation gradient (HOG) 



This work is supported by Department of Computer Science, COMSATS University Islamabad, Wah Campus Pakistan. We are thankful to COMSATS for providing a strong research platform, fully equipped labs and other research facilities to make this work possible.


  1. 1.
    Acharya UR, Ng EY-K, Tan J-H, Sree SV, Ng K-H (2012) An integrated index for the identification of diabetic retinopathy stages using texture parameters. J Med Syst 36(3):2011–2020CrossRefGoogle Scholar
  2. 2.
    Acharya UR et al (2017) Automated diabetic macular edema (DME) grading system using DWT, DCT features and maculopathy index. Comput Biol Med 84:59–68CrossRefGoogle Scholar
  3. 3.
    Agurto C et al (2010) 14 Multiscale AM-FM methods for diabetic retinopathy lesion detection. IEEE Trans Med Imaging 29(2):502–512CrossRefGoogle Scholar
  4. 4.
    Akram MU, Khalid S, Tariq A, Khan SA, Azam F (2014) Detection and classification of retinal lesions for grading of diabetic retinopathy. Comput Biol Med 45:161–171CrossRefGoogle Scholar
  5. 5.
    Ali H, Lali M, Nawaz M, Sharif M, Saleem B (2017) Symptom based automated detection of citrus diseases using color histogram and textural descriptors. Comput Electron Agric 138:92–104CrossRefGoogle Scholar
  6. 6.
    J. Amin, M. Sharif, and M. Yasmin (2016) A review on recent developments for detection of diabetic retinopathy. Scientifica 2016Google Scholar
  7. 7.
    Amin J, Sharif M, Yasmin M, Ali H, Fernandes SL (2017) A method for the detection and classification of diabetic retinopathy using structural predictors of bright lesions. J Comput Sci 19:153–164CrossRefGoogle Scholar
  8. 8.
    Ashraf A, Akram MU, Sheikh SA (2015) Detection of retinal whitening, cotton wool spots and retinal Hemorrhages for diagnosis of Malarial Retinopathy. In: TENCON 2015-2015 IEEE Region 10 Conference, pp. 1-5: IEEEGoogle Scholar
  9. 9.
    Bala GJ (2016) Developing a Novel Technique to Match Composite Sketches with Images Captured by Unmanned Aerial Vehicle. Procedia Computer Science 78:248–254CrossRefGoogle Scholar
  10. 10.
    Benzamin A, Chakraborty C (2018) Detection of Hard Exudates in Retinal Fundus Images using Deep LearningGoogle Scholar
  11. 11.
    Bokhari F, Syedia T, Sharif M, Yasmin M, Fernandes SL (2018) Fundus Image Segmentation and Feature Extraction for the Detection of Glaucoma: A New Approach. Current Medical Imaging Reviews 14(1):77–87CrossRefGoogle Scholar
  12. 12.
    Capdehourat G, Corez A, Bazzano A, Alonso R, Musé P (2011) Toward a combined tool to assist dermatologists in melanoma detection from dermoscopic images of pigmented skin lesions. Pattern Recogn Lett 32(16):2187–2196CrossRefGoogle Scholar
  13. 13.
    Colomer A, Naranjo V, Janvier T, Mossi JM (2018) Evaluation of fractal dimension effectiveness for damage detection in retinal background. J Comput Appl Math 337:341–353MathSciNetCrossRefGoogle Scholar
  14. 14.
    Cuspidi C, Sala C, Grassi G (2015) Updated classification of hypertensive retinopathy: which role for cardiovascular risk stratification? J Hypertens 33(11):2204–2206CrossRefGoogle Scholar
  15. 15.
    Dai B, Bu W, Wang K, Wu X (2016) Fundus lesion detection based on visual attention model. In: International Conference of Young Computer Scientists, Engineers and Educators, pp. 384-394: SpringerGoogle Scholar
  16. 16.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1, pp. 886-893: IEEEGoogle Scholar
  17. 17.
    B. Dashtbozorg, J. Zhang, F. Huang, and B. M. ter Haar Romeny (2016) 28 Automatic optic disc and fovea detection in retinal images using super-elliptical convergence index filters," in International Conference Image Analysis and Recognition. Springer, pp. 697-706Google Scholar
  18. 18.
    Ege BM et al (2000) Screening for diabetic retinopathy using computer based image analysis and statistical classification. Comput Methods Prog Biomed 62(3):165–175CrossRefGoogle Scholar
  19. 19.
    Faust O, Acharya R, Ng EY-K, Ng K-H, Suri JS (2012) Algorithms for the automated detection of diabetic retinopathy using digital fundus images: a review. J Med Syst 36(1):145–157CrossRefGoogle Scholar
  20. 20.
    Fernandes SL, Bala JG (2015) Study on MACE Gabor filters, Gabor wavelets, DCT-neural network, hybrid spatial feature interdependence matrix, fusion techniques for face recognition. Recent Patents on Engineering 9(1):29–36CrossRefGoogle Scholar
  21. 21.
    Fernandes SL, Bala JG (2017) A novel decision support for composite sketch matching using fusion of probabilistic neural network and dictionary matching. Current Medical Imaging Reviews 13(2):176–184CrossRefGoogle Scholar
  22. 22.
    Fernandes SL, Chakraborty B, Gurupur VP, Prabhu G (2016) Early skin cancer detection using computer aided diagnosis techniques. J Integr Des Process Sci 20(1):33–43CrossRefGoogle Scholar
  23. 23.
    Fernandes SL, Gurupur VP, Lin H, Martis RJ (2017) A Novel fusion approach for early lung cancer detection using computer aided diagnosis techniques. Journal of Medical Imaging and Health Informatics 7(8):1841–1850CrossRefGoogle Scholar
  24. 24.
    Ganesan K, Acharya RU, Chua CK, Laude AJP o t I o ME (2014) Identification and Localization of Fovea on Colour Fundus Images using Blur Scales. Part H: Journal of Engineering in Medicine 228(9):962–970Google Scholar
  25. 25.
    García M, Sánchez CI, López MI, Abásolo D, Hornero R (2009) Neural network based detection of hard exudates in retinal images. Comput Methods Prog Biomed 93(1):9–19CrossRefGoogle Scholar
  26. 26.
    Issac A, Dutta MK, Travieso CM (2018) Automatic computer vision-based detection and quantitative analysis of indicative parameters for grading of diabetic retinopathy. Neural Computing and Applications, pp. 1-11Google Scholar
  27. 27.
    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
  28. 28.
    Kaur J, Mittal D (2018) A generalized method for the segmentation of exudates from pathological retinal fundus images. Biocybernetics and Biomedical Engineering 38(1):27–53CrossRefGoogle Scholar
  29. 29.
    Kaur I, Singh LM (2016) A method of disease detection and segmentation of retinal blood vessels using fuzzy C-means and neutrosophic approach. Imperial Journal of Interdisciplinary Research 2(6)Google Scholar
  30. 30.
    Khan MW, Sharif M, Yasmin M, Fernandes SL (2016) A new approach of cup to disk ratio based glaucoma detection using fundus images. J Integr Des Process Sci 20(1):77–94CrossRefGoogle Scholar
  31. 31.
    Kolman S, van Sijl A, van der Sluijs F, van de Ree M (2017) Consideration of hypertensive retinopathy as an important end-organ damage in patients with hypertension. J Hum Hypertens 31(2):121–125CrossRefGoogle Scholar
  32. 32.
    Kumar S, Jain N, Fernandes SL (2017) Rough set based effective technique of image watermarking. J Comput Sci 19:121–137CrossRefGoogle Scholar
  33. 33.
    Kusakunniran W, Wu Q, Ritthipravat P, Zhang J (2018) Hard exudates segmentation based on learned initial seeds and iterative graph cut. Computer Methods and Programs in BiomedicineGoogle Scholar
  34. 34.
    Lahmiri S, Boukadoum M (2014) Automated detection of circinate exudates in retina digital images using empirical mode decomposition and the entropy and uniformity of the intrinsic mode functions. Biomedical Engineering/Biomedizinische Technik 59(4):357–366Google Scholar
  35. 35.
    Li H, Chutatape O (2004) 15 Automated feature extraction in color retinal images by a model based approach. IEEE Trans Biomed Eng 51(2):246–254CrossRefGoogle Scholar
  36. 36.
    Lim JI, LaBree L, Nichols T, Cardenas I (2000) A comparison of digital nonmydriatic fundus imaging with standard 35-millimeter slides for diabetic retinopathy. Ophthalmology 107(5):866–870CrossRefGoogle Scholar
  37. 37.
    Margineantu DD, Dietterich TG (1997) Pruning adaptive boosting. ICML 97:211–218Google Scholar
  38. 38.
    Marin D et al (2018) An exudate detection method for diagnosis risk of diabetic macular edema in retinal images using feature-based and supervised classification. Medical & Biological Engineering & Computing, pp. 1-12Google Scholar
  39. 39.
    Moghaddam B, Yang M (2002) Learning gender with support faces. IEEE Trans Pattern Anal Mach Intell 24(5):707–711CrossRefGoogle Scholar
  40. 40.
    Mumtaz R, Hussain M, Sarwar S, Khan K, Mumtaz S, Mumtaz M (2017) Automatic detection of retinal hemorrhages by exploiting image processing techniques for screening retinal diseases in diabetic patients. International Journal of Diabetes in Developing Countries, pp. 1-8Google Scholar
  41. 41.
    Naqi S, Sharif M, Yasmin M, Fernandes SL (2018) Lung nodule detection using polygon approximation and hybrid features from CT images. Current Medical Imaging Reviews 14(1):108–117CrossRefGoogle Scholar
  42. 42.
    Nasir M, Attique Khan M, Sharif M, Lali IU, Saba T, Iqbal T (2018) An improved strategy for skin lesion detection and classification using uniform segmentation and feature selection based approach. Microscopy research and techniqueGoogle Scholar
  43. 43.
    Qureshi I, Sharif M, Yasmin M, Raza M, Javed MY (2016) Computer aided systems for diabetic retinopathy detection using digital fundus images: a survey. Current Medical Imaging Reviews 12(4):234–241CrossRefGoogle Scholar
  44. 44.
    Ranjan R, Arya R, Fernandes SL, Sravya E, Jain V (2018) A Fuzzy Neural Network approach for automatic K-complex detection in sleep EEG signal. Pattern Recognition LettersGoogle Scholar
  45. 45.
    Liao Y, Rao V, Vemuri A (2002) Use of k-nearest neighbor classifier for intrusion detection. Comput Secur 21(5):439–448CrossRefGoogle Scholar
  46. 46.
    Reza AW, Eswaran C, Dimyati K (2011) Diagnosis of diabetic retinopathy: automatic extraction of optic disc and exudates from retinal images using marker-controlled watershed transformation. J Med Syst 35(6):1491–1501CrossRefGoogle Scholar
  47. 47.
    Shabbir B, Sharif M, Nisar W, Yasmin M, Fernandes SL (2016) Automatic cotton wool spots extraction in retinal images using texture segmentation and gabor wavelet. J Integr Des Process Sci 20(1):65–76CrossRefGoogle Scholar
  48. 48.
    Soille P (2013) Morphological image analysis: principles and applications. Springer Science & Business MediaGoogle Scholar
  49. 49.
    Sopharak A, Uyyanonvara B, Barman S, Williamson TH (2008) Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods. Comput Med Imaging Graph 32(8):720–727CrossRefGoogle Scholar
  50. 50.
    Thomas A, Sreekumar K (2014) A survey on image feature descriptors-color, shape and texture. International Journal of Computer Science and Information Technologies 5(6):7847–7850Google Scholar
  51. 51.
    Wong TY, McIntosh R (2005) Hypertensive retinopathy signs as risk indicators of cardiovascular morbidity and mortality. Br Med Bull 73(1):57–70CrossRefGoogle Scholar
  52. 52.
    Wu J et al (2018) Hemorrhage detection in fundus image based on 2D Gaussian fitting and human visual characteristics. Optics & Laser TechnologyGoogle Scholar
  53. 53.
    Xiaohui Z, Chutatape A (2004) Detection and classification of bright lesions in color fundus images. In: Image Processing, 2004. ICIP'04. 2004 International Conference on, vol. 1, pp. 139-142: IEEEGoogle Scholar
  54. 54.
    Yasmin M, Sharif M, Irum I, Mehmood W, Fernandes SL (2016) Combining multiple color and shape features for image retrieval. IIOAB J 7(32):97–110Google Scholar
  55. 55.
    Yazid H, Arof H, Isa HM (2012) Automated identification of exudates and optic disc based on inverse surface thresholding. J Med Syst 36(3):1997–2004CrossRefGoogle Scholar
  56. 56.
    Youssef D, Solouma NH (2012) Accurate detection of blood vessels improves the detection of exudates in color fundus images. Comput Methods Prog Biomed 108(3):1052–1061CrossRefGoogle Scholar
  57. 57.
    Zhang X et al (2014) Exudate detection in color retinal images for mass screening of diabetic retinopathy. Med Image Anal 18(7):1026–1043CrossRefGoogle Scholar
  58. 58.
    Zhao Q-Y, Pan B-C, Pan J-J, Tang Y-Y (2008) Facial expression recognition based on fusion of Gabor and LBP features. In: Wavelet Analysis and Pattern Recognition, 2008. ICWAPR'08. International Conference on, vol. 1, pp. 362-367, IEEEGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Muhammad Sharif
    • 1
  • Javeria Amin
    • 2
  • Mussarat Yasmin
    • 1
    Email author
  • Amjad Rehman
    • 3
  1. 1.Department of Computer ScienceCOMSATS University IslamabadWah CanttPakistan
  2. 2.Department of Computer ScienceUniversity of WahWah CanttPakistan
  3. 3.College of Computer and Information SystemsAl Yamamah UniversityRiyadhSaudi Arabia

Personalised recommendations