Skip to main content
SpringerLink
Log in

Automated grading of diabetic retinopathy using CNN with hierarchical clustering of image patches by siamese network

  • Scientific Paper
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

Diabetic retinopathy (DR) is a progressive vascular complication that affects people who have diabetes. This retinal abnormality can cause irreversible vision loss or permanent blindness; therefore, it is crucial to undergo frequent eye screening for early recognition and treatment. This paper proposes a feature extraction algorithm using discriminative multi-sized patches, based on deep learning convolutional neural network (CNN) for DR grading. This comprehensive algorithm extracts local and global features for efficient decision-making. Each input image is divided into small-sized patches to extract local-level features and then split into clusters or subsets. Hierarchical clustering by Siamese network with pre-trained CNN is proposed in this paper to select clusters with more discriminative patches. The fine-tuned Xception model of CNN is used to extract the global-level features of larger image patches. Local and global features are combined to improve the overall image-wise classification accuracy. The final support vector machine classifier exhibits 96% of classification accuracy with tenfold cross-validation in classifying DR images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. (2019) The world report on vision. Available at https://www.who.int/publications/i/item/world-report-on-vision

  2. (2020) Prevention and screening for DR. Available at https://www.idf.org/aboutdiabetes/prevention.html

  3. Wu B, Zhu W, Shi F, Zhu S, Chen X (2017) Automatic detection of microaneurysms in retinal fundus images. Comput Med Imaging Graph 55:106–112

    Article  PubMed  Google Scholar 

  4. ETDRSR Group et al (1985) Photocoagulation for diabetic macular edema. Arch Ophthalmol 103:1796–1806

    Article  Google Scholar 

  5. Lazar I, Hajdu A (2013) Retinal microaneurysm detection through local rotating cross-section profile analysis. IEEE Trans Med Imaging 32(2):400–407

    Article  PubMed  Google Scholar 

  6. Roychowdhury S, Koozekanani DD, Parhi KK (2014) Dream: diabetic retinopathy analysis using machine learning. IEEE J Biomed Health 18(5):1717–1728

    Article  Google Scholar 

  7. James J, Sharifahmadian E, Shih L (2018) Automatic severity level classification of diabetic retinopathy. Int J Comput Appl 975:30–35

    Google Scholar 

  8. Colomer A, Igual J, Naranjo V (2020) Detection of early signs of diabetic retinopathy based on textural and morphological information in fundus images. Sensors 20(4):1005

    Article  PubMed Central  Google Scholar 

  9. Sikder N, Masud M, Bairagi AK, Arif ASM, Nahid AA, Alhumyani HA (2021) Severity classification of diabetic retinopathy using an ensemble learning algorithm through analyzing retinal images. Symmetry 13(4):670

    Article  Google Scholar 

  10. Mukti FA, Eswaran C, Hashim N, Ching HC, Ayoobkhan MUA (2018) An automated grading system for diabetic retinopathy using curvelet transform and hierarchical classification. Int J Eng Sci Technol 7(2.15):154–157

    Google Scholar 

  11. Gayathri S, Krishna AK, Gopi VP, Palanisamy P (2020) Automated binary and multiclass classification of diabetic retinopathy using haralick and multiresolution features. IEEE Access 8:57497–57504

    Article  Google Scholar 

  12. Gayathri S, Gopi VP, Palanisamy P (2020) Automated classification of diabetic retinopathy through reliable feature selection. Phys Eng Sci Med 43(3):927–945

    Article  CAS  PubMed  Google Scholar 

  13. Deepa V, Kumar CS, Andrews SS (2021) Fusing dual-tree quaternion wavelet transform and local mesh based features for grading of diabetic retinopathy using extreme learning machine classifier. Int J Imaging Syst Technol 31(3):1625–1637

    Article  Google Scholar 

  14. Seo Y, Shin K (2019) Hierarchical convolutional neural networks for fashion image classification. Expert Syst Appl 116:328–339

    Article  Google Scholar 

  15. Mittal S (2020) Ensemble of transfer learnt classifiers for recognition of cardiovascular tissues from histological images. Phys Eng Sci Med 43(2):691

    Article  PubMed  Google Scholar 

  16. Boggavarapu LPK, Manoharan P (2020) A new framework for hyperspectral image classification using Gabor embedded patch based convolution neural network. Infrared Phys Technol 110:103455

    Article  CAS  Google Scholar 

  17. Guo N, Gu K, Qiao J, Bi J (2021) Improved deep CNNs based on nonlinear hybrid attention module for image classification. Neural Netw 140:158–166

    Article  PubMed  Google Scholar 

  18. Su WT, Hsu CC, Huang Z, Lin CW, Cheung G (2018) Joint pairwise learning and image clustering based on a Siamese CNN. In: 2018 25th IEEE international conference on image processing (ICIP). IEEE, Athens, pp 1992–1996

    Chapter  Google Scholar 

  19. Li Y, Wu J, Wu Q (2019) Classification of breast cancer histology images using multi-size and discriminative patches based on deep learning. IEEE Access 7:21400–21408

    Article  Google Scholar 

  20. Mehmood A, Maqsood M, Bashir M, Shuyuan Y (2020) A deep Siamese convolution neural network for multi-class classification of Alzheimer disease. Brain Sci 10(2):84

    Article  PubMed Central  Google Scholar 

  21. Wan S, Liang Y, Zhang Y (2018) Deep convolutional neural networks for diabetic retinopathy detection by image classification. Comput Electr Eng 72:274–282

    Article  Google Scholar 

  22. Lam C, Yi D, Guo M, Lindsey T (2018) Automated detection of diabetic retinopathy using deep learning. AMIA Jt Summits Transl Sci Proc 2018:147

    PubMed Central  Google Scholar 

  23. Rehman MU, Khan SH, Abbas Z, Danish Rizvi SM (2019) Classification of diabetic retinopathy images based on customised CNN architecture. In: 2019 Amity International Conference on Artificial Intelligence (AICAI). IEEE, Dubai, pp 244–248

    Chapter  Google Scholar 

  24. Liu YP, Li Z, Xu C, Li J, Liang R (2019) Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network. Artif Intell Med 99:101694

    Article  PubMed  Google Scholar 

  25. Samanta A, Saha A, Satapathy SC, Fernandes SL, Zhang YD (2020) Automated detection of diabetic retinopathy using convolutional neural networks on a small dataset. Pattern Recognit Lett 135:293–298

    Article  Google Scholar 

  26. Hacisoftaoglu RE, Karakaya M, Sallam AB (2020) Deep learning frameworks for diabetic retinopathy detection with smartphone-based retinal imaging systems. Pattern Recognit Lett 135:409–417

    Article  PubMed  PubMed Central  Google Scholar 

  27. Saeed F, Hussain M, Aboalsamh HA (2021) Automatic diabetic retinopathy diagnosis using adaptive fine-tuned convolutional neural network. IEEE Access 9:41344–41359

    Article  Google Scholar 

  28. Khan Z, Khana FG, Khan A, Rehman ZU, Shah S, Qummar S, Ali F, Pack S (2021) Diabetic retinopathy detection using VGG-NIN a deep learning architecture. IEEE Access 9:61408–61416

    Article  Google Scholar 

  29. Jagan Mohan N, Murugan R, Goel T, Mirjalili S, Roy P (2021) A novel four-step feature selection technique for diabetic retinopathy grading. Phys Eng Sci Med 44(4):1351–1366

    Article  CAS  PubMed  Google Scholar 

  30. Deepa V, Kumar CS, Cherian T (2021) Automated detection of diabetic retinopathy images using pre-trained convolutional neural network. In: International conference on communication, control and information sciences (ICCISc). IEEE, Piscataway, pp 1–5

    Google Scholar 

  31. Deepa V, Kumar CS, Andrews SS (2019) Automated detection of microaneurysms using Stockwell transform and statistical features. IET Image Process 13(8):1341–1348

    Article  Google Scholar 

  32. Kauppi T, Kamarainen JK, Lensu L, Kalesnykiene V, Sorri I, Uusitalo H, Kalviainen H (2007) DIARETDB1 diabetic retinopathy database and evaluation protocol. Lappeenranta University of Technology, Lappeenranta

    Book  Google Scholar 

  33. Hoover A (2004) STARE database. Available at http://www.ces.clemson.edu/ahoover/stare

  34. Zhang X, Thibault G, Decencière E, Marcotegui B, Laÿ B, Danno R, Cazuguel G, Quellec G, Lamard M, Massin P et al (2014) Exudate detection in color retinal images for mass screening of diabetic retinopathy. Med Image Anal 18(7):1026–1043

    Article  PubMed  Google Scholar 

  35. Niemeijer M, van Ginneken B, Cree MJ, Mizutani A, Quellec G, Sánchez CI et al (2010) Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs. IEEE Trans Med Imag 29(1):185–195

    Article  Google Scholar 

  36. (2014) Kaggle database. Available at https://www.kaggle.com/c/diabetic-retinopathy-detection

  37. Zhu X, Yao J, Zhu F, Huang J (2017) Wsisa: making survival prediction from whole slide histopathological images. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Piscataway, pp 7234–7242

    Google Scholar 

  38. Chollet F (2017) Xception: deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Piscataway, pp 1251–1258

    Google Scholar 

  39. Hur AB, Horn D, Siegelmann HT, Vapnik V (2001) Support vector clustering. J Mach Learn Res 2(2):125–137

    Google Scholar 

  40. Zhang C, Pan X, Li H, Gardiner A, Sargent I, Hare J, Atkinson PM (2018) A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS J Photogramm Remote Sens 140:133–144

    Article  CAS  Google Scholar 

  41. Ying C, Qi-Guang M, Jia-Chen L, Lin G (2013) Advance and prospects of Adaboost algorithm. Acta Autom Sin 39(6):745–758

    Google Scholar 

  42. Paul A, Mukherjee DP, Das P, Gangopadhyay A, Chintha AR, Kundu S (2018) Improved random forest for classification. IEEE Trans Image Process 27(8):4012–4024

    Article  PubMed  Google Scholar 

  43. Yamashita R, Nishio M, Do RKG, Togashi K (2018) Convolutional neural networks: an overview and application in radiology. Insights Imaging 9(4):611–629

    Article  PubMed  PubMed Central  Google Scholar 

  44. Lydia A, Francis S (2019) Adagrad—an optimizer for stochastic gradient descent. Int J Inf Comput Sci 6(5):566–568

    Google Scholar 

  45. Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manag 45(4):427–437

    Article  Google Scholar 

  46. Akram MU, Khalid S, Tariq A, Javed MY (2013) Detection of neovascularization in retinal images using multivariate m-mediods based classifier. Comput Med Imag Graph 37(5–6):346–357

    Article  Google Scholar 

Download references

Funding

The authors have not disclosed any funding.

Author information

Authors and Affiliations

  1. Department of Electrical and Electronics Engineering, Rajiv Gandhi Institute of Technology, Kottayam, India

    V. Deepa

  2. APJ Abdul Kalam Technological University, Thiruvananthapuram, India

    V. Deepa & C. Sathish Kumar

  3. Department of Electronics and Communication Engineering, Rajiv Gandhi Institute of Technology, Kottayam, India

    C. Sathish Kumar

  4. Department of Retina, Little Flower Hospital and Research Centre, Angamaly, Ernakulam, India

    Thomas Cherian

Authors
  1. V. Deepa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. C. Sathish Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Thomas Cherian
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to V. Deepa.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Deepa, V., Sathish Kumar, C. & Cherian, T. Automated grading of diabetic retinopathy using CNN with hierarchical clustering of image patches by siamese network. Phys Eng Sci Med 45, 623–635 (2022). https://doi.org/10.1007/s13246-022-01129-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-022-01129-z

Keywords

Search

Navigation