Skip to main content
SpringerLink
Log in

Automatic severity grade classification of diabetic retinopathy using deformable ladder Bi attention U-net and deep adaptive CNN

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Long-term exposure to diabetes mellitus leads to the formation of diabetic retinopathy (DR), which can cause vision loss in working-age adults. Early stage diagnosis of DR is highly essential for preventing vision loss and preserving vision in people with diabetes. The motivation behind the severity grade classification of DR is to develop an automated system that can assist ophthalmologists and healthcare professionals in the diagnosis and management of DR. However, existing methods suffer from variability in image quality, similar structures of the normal and lesion regions, high dimensional features, variability in disease manifestations, small datasets, high training loss, model complexity, and overfitting, which leads to high misclassification errors in the severity grading system. Hence, there is a need to develop an automated system using improved deep learning techniques to provide a reliable and consistent grading of DR severity with high classification accuracy using fundus images. To solve these issues, we proposes a Deformable Ladder Bi attention U-shaped encoder-decoder network and Deep Adaptive Convolutional Neural Network (DLBUnet-DACNN) for accurate severity classification of DR. The DLBUnet performs lesion segmentation that can be divided into three parts: the encoder, the central processing module and the decoder. In the encoder part, deformable convolution is used instead of convolution to learn different shapes of the lesion by understanding the offset location. Afterwards, Ladder Atrous Spatial Pyramidal Pooling (LASPP) using variable dilation rates is introduced in the central processing module. LASPP enhance the tiny lesion features and variable dilation rates avoid gridding effects and can learn better global context information. Then the decoder part uses a bi-attention layer contains spatial and channel attention, which can learn contour and edges of the lesion accurately. Finally, the severity of DR is classified using a DACNN by extracting the discriminative features from the segmentation results. Experiments are conducted on the Messidor-2, Kaggle, and Messidor datasets. Our proposed method DLBUnet-DACNN achieves better results in terms of accuracy of 98.2, recall of 0.987, kappa coefficient of 0.993, precision of 0.98, F1-score of 0.981, Matthews Correlation Coefficient (MCC) of 0.93 and Classification Success Index (CSI) of 0.96 when compared to existing methods.

Graphical Abstract

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. Gadekallu TR, Khare N, Bhattacharya S, Singh S, Maddikunta PKR, Srivastava G (2020) Deep neural networks to predict diabetic retinopathy. J Ambient Intell Humanized Comput 14(5):5407–5420

    Article  Google Scholar 

  2. Bandello F, Toni D, Porta M, Varano M (2020) Diabetic retinopathy, diabetic macular edema, and cardiovascular risk: the importance of a long-term perspective and a multidisciplinary approach to optimal intravitreal therapy. Acta Diabetol 57(5):513–526

    Article  PubMed  Google Scholar 

  3. Rathmann W, Kostev K (2015) Fracture risk in patients with newly diagnosed type 2 diabetes: a retrospective database analysis in primary care. J Diabetes Complications 29(6):766–770

    Article  PubMed  Google Scholar 

  4. Sun Y, Roumelioti ME, Ganta K, Glew RH, Gibb J, Vigil D, Tzamaloukas AH (2020) Dialysis-associated hyperglycemia: manifestations and treatment. Int Urol Nephrol 52(3):505–517

    Article  CAS  PubMed  Google Scholar 

  5. Bhardwaj C, Jain S, Sood M (2021) Hierarchical severity grade classification of non-proliferative diabetic retinopathy. J Ambient Intell Humanized Comput 12(2):2649–2670

    Article  Google Scholar 

  6. Zeng Y, Cao D, Yang D, Zhuang X, Hu Y, He M, Zhang L (2020) Retinal vasculature–function correlation in non-proliferative diabetic retinopathy. Doc Ophthalmol 140(2):129–138

    Article  PubMed  Google Scholar 

  7. 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 

  8. Gouder MJ (2020) Retinal testing and imaging. In: The Retina. Springer, Cham, pp 9-21

  9. Behera MK, Chakravarty S (2020) Diabetic retinopathy image classification using support vector machine. In: 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA). IEEE, Gunupur, India, pp 1–4

  10. Osman AH, Aljahdali HMA (2020) An effective of ensemble boosting learning method for breast cancer virtual screening using neural network model. IEEE Access 8:39165–39174

    Article  Google Scholar 

  11. Balakrishnan N, Nisi K (2020) A deep analysis on optimization techniques for appropriate PID tuning to incline efficient artificial pancreas. Neural Comput Appl 32(12):7587–7596

    Article  Google Scholar 

  12. Raja JB, Pandian SC (2020) PSO-FCM based data mining model to predict diabetic disease. Comput Methods Programs Biomed 196:105659

    Article  PubMed  Google Scholar 

  13. Asiri N, Hussain M, Al Adel F, Alzaidi N (2019) Deep learning based computer-aided diagnosis systems for diabetic retinopathy: a survey. Artif Intell Med 99:101701

    Article  PubMed  Google Scholar 

  14. Islam MR, Abdulrazak LF, Nahiduzzaman M, Goni MO, Anower MS, Ahsan M, Haider J, Kowalski M (2022) Applying supervised contrastive learning for the detection of diabetic retinopathy and its severity levels from fundus images. Comput Biol Med 146:105602

    Article  PubMed  Google Scholar 

  15. Berbar MA (2022) Features extraction using encoded local binary pattern for detection and grading diabetic retinopathy. Health Inf Sci Syst 10(1):1–3

    Article  Google Scholar 

  16. Nahiduzzaman M, Islam MR, Islam SR, Goni MO, Anower MS, Kwak KS (2021) Hybrid CNN-SVD based prominent feature extraction and selection for grading diabetic retinopathy using extreme learning machine algorithm. IEEE Access 9:152261–152274

    Article  Google Scholar 

  17. Yang Y, Shang F, Wu B, Yang D, Wang L, Xu Y, Zhang W, Zhang T (2021) Robust collaborative learning of patch-level and image-level annotations for diabetic retinopathy grading from fundus image. IEEE Trans Cybern 52:11407

    Article  Google Scholar 

  18. Gangwar AK, Ravi V (2021) Diabetic retinopathy detection using transfer learning and deep learning. In: Evolution in Computational Intelligence. Springer, Singapore, pp 679–689

  19. Sridhar S, PradeepKandhasamy J, Sinthuja M, Minish TS (2021) Diabetic retinopathy detection using convolutional nueral networks algorithm. Mater Today: Proc 14(9):1932. https://doi.org/10.3390/sym14091932

  20. Kalyani G, Janakiramaiah B, Karuna A, Prasad LVN (2021) Diabetic retinopathy detection and classification using capsule networks. Complex Intell Syst 9:2651–2664

    Article  Google Scholar 

  21. Badgujar RD, Deore PJ (2019) Hybrid nature inspired SMO-GBM classifier for exudate classification on fundus retinal images. IRBM 40(2):69–77

    Article  Google Scholar 

  22. Dong B, Wang X, Qiang X, Du F, Gao L, Wu Q, Cao G, Dai C (2022) A multi-branch convolutional neural network for screening and staging of diabetic retinopathy based on wide-field optical coherence tomography angiography. IRBM 43(6):614–620

    Article  Google Scholar 

  23. Han J, Wang Y, Gong H (2022) Fundus retinal vessels image segmentation method based on improved U-Net. IRBM 43(6):628–639

    Article  Google Scholar 

  24. Novitasari DC, Fatmawati F, Hendradi R, Rohayani H, Nariswari R, Arnita A, Hadi MI, Saputra RA, Primadewi A (2022) Image fundus classification system for diabetic retinopathy stage detection using hybrid CNN-DELM. Big Data Cogn Comput 6(4):146

    Article  Google Scholar 

  25. Barua PD, Chan WY, Dogan S, Baygin M, Tuncer T, Ciaccio EJ, Islam N, Cheong KH, Shahid ZS, Acharya UR (2021) Multilevel deep feature generation framework for automated detection of retinal abnormalities using OCT images. Entropy 23(12):1651

    Article  PubMed  PubMed Central  Google Scholar 

  26. Kobat SG, Baygin N, Yusufoglu E, Baygin M, Barua PD, Dogan S, Yaman O, Celiker U, Yildirim H, Tan RS, Tuncer T (2022) Automated diabetic retinopathy detection using horizontal and vertical patch division-based pre-trained DenseNET with digital fundus images. Diagnostics 12(8):1975

    Article  PubMed  PubMed Central  Google Scholar 

  27. Zulfahmi R, Noviyanti DS, Utami GR, Harison AN, Agung PS (2019) Improved image quality retinal fundus with contrast limited adaptive histogram equalization and filter variation. In2019 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) (pp. 49–54). IEEE

  28. Abdelmaksoud E, El-Sappagh S, Barakat S, Abuhmed T, Elmogy M (2021) Automatic diabetic retinopathy grading system based on detecting multiple retinal lesions. IEEE Access 9:15939–15960

    Article  Google Scholar 

  29. Li M, Lian F, Guo S (2021) Automatic pancreas segmentation using double adversarial networks with pyramidal pooling module. IEEE Access 9:140965–140974

    Article  Google Scholar 

  30. Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation.  arXiv:1706.05587. https://doi.org/10.48550/arXiv.1706.05587

  31. Jie F, Nie Q, Li M, Yin M, Jin T (2021) Atrous spatial pyramid convolution for object detection with encoder-decoder. Neurocomputing 464:107–118

    Article  Google Scholar 

  32. Gegundez-Arias ME, Marin-Santos D, Perez-Borrero I, Vasallo-Vazquez MJ (2021) A new deep learning method for blood vessel segmentation in retinal images based on convolutional kernels and modified U-Net model. Comput Methods Programs Biomed 205:106081

    Article  PubMed  Google Scholar 

  33. Kaggle Dataset (2015). https://www.kaggle.com/c/diabetic-retinopathy-detection/data

  34. Messidor Dataset (2014). https://www.adcis.net/en/third-party/messidor/

  35. Messidor 2 Dataset (2021). https://www.adcis.net/en/third-party/messidor2/

  36. Bock S, Goppold J, Weiß M (2018) An improvement of the convergence proof of the ADAM-Optimizer. arXiv preprint arXiv:1804.10587

Download references

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Udaya School of Engineering, Vellamodi, India

    D. Binny Jeba Durai

  2. Department of Electronics and Communication Engineering, C.S.I. Institute of Technology, Thovalai, India

    T. Jaya

Authors
  1. D. Binny Jeba Durai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. T. Jaya
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All the authors have participated in writing the manuscript and have revised the final version. All authors read and approved the final manuscript. All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Binny Jeba Durai D and Jaya T. The first draft of the manuscript was written by Binny Jeba Durai D and all authors commented on previous versions of the manuscript. Conceptualization: Binny Jeba Durai D; Methodology: Binny Jeba Durai D; Formal analysis and investigation: Binny Jeba Durai D, Jaya T; Writing—original draft preparation: Binny Jeba Durai D; Writing—review and editing: Jaya T; Supervision: Jaya T.

Corresponding author

Correspondence to D. Binny Jeba Durai.

Ethics declarations

Ethical approval

This article does not contain any studies with human participants and/or animals performed by any of the authors.

Informed consent

There is no informed consent for this study.

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Durai, D.B.J., Jaya, T. Automatic severity grade classification of diabetic retinopathy using deformable ladder Bi attention U-net and deep adaptive CNN. Med Biol Eng Comput 61, 2091–2113 (2023). https://doi.org/10.1007/s11517-023-02860-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-023-02860-9

Keywords

Search

Navigation