A DEEP TRANSFER LEARNING FRAMEWORK for the STAGING of DIABETIC RETINOPATHY

Abstract

Diabetes is a highly prevalent and increasingly common health disorder, resulting in health complications such as vision loss. Diabetic retinopathy (DR) is the most common form of diabetes-caused eye disease. Early diagnosis and treatment are crucial to prevent vision loss. DR is a progressive disease composed of five stages. The accurate diagnosis of DR stages is highly important in guiding the treatment process. In this study, we propose a deep transfer learning framework for automatic detection of DR stages. We examine our proposed model by comparing different convolutional neural networks architectures: VGGNet19, DenseNet201, and ResNet152. Our results demonstrate better accuracy after applying transfer learning and hyper-parameter tuning to classify the fundus images. When the general test accuracy and the performance evaluations are compared, the DenseNet201 model is observed with the highest test accuracy of 82.7%. Among the classification algorithms, the highest AUC value is 94.1% obtained with RestNet152.

Keywords

• Convolutional neural networks
• CNNs
• Deep learning
• Diabetic retinopathy
• Transfer learning

References

1. [1] Roglic, G. (2016), WHO global report on diabetes: a summary. International Journal of Noncommunicable Diseases, 1(1), 3.
2. [2] Lynch, S.K. and M.D. Abràmoff. (2017), Diabetic retinopathy is a neurodegenerative disorder. Vision research, 139, 101-107.
3. [3] Benson, W.E., Blodi, B.A., Boldt, H.C., Olsen, T.W., Regillo, C.D., Scott, I.U., et al. (2008), Prepared by the American Academy of Ophthalmology Retina/Vitreous Panel Members.
4. [4] Mohammadpoory, Z., Nasrolahzadeh, M., Mahmoodian N., and Haddadnia, J. (2019), Automatic identification of diabetic retinopathy stages by using fundus images and visibility graph method. Measurement, 140, 133-141.
5. [5] Biyani, R. and Patre, B. (2018), Algorithms for red lesion detection in diabetic retinopathy: a review. Biomedicine & Pharmacotherapy, 107, 681-688.
6. [6] Neffati, S., Ben Abdellafou, K., Taouali, O. and Bouzrara, K. (2020), Enhanced SVM–KPCA method for brain MR image classification. The Computer Journal, 63(3), 383-394.
7. [7] Sugeno, A., Ishikawa, Y., Ohshima, T. and Muramatsu, R. (2021), Simple methods for the lesion detection and severity grading of diabetic retinopathy by image processing and transfer learning. Computers in Biology and Medicine, 137, 104795.
8. [8] Bhardwaj, C., Jain, S. and Sood, M. (2021), Hierarchical severity grade classification of non-proliferative diabetic retinopathy. Journal of Ambient Intelligence and Humanized Computing, 12(2), 2649-2670.

9. [9] Shaban, M., Ogur, Z., Mahmoud, A., Switala, A., Shalaby, A., Abu Khalifeh, H., et al. (2020), A convolutional neural network for the screening and staging of diabetic retinopathy. Plos one, 15(6).
10. [10] De La Torre, J., Valls, A. and Puig, D. (2020), A deep learning interpretable classifier for diabetic retinopathy disease grading. Neurocomputing, 396, 465-476.
11. [11] Zhao, L., Ren, H., Zhang, J., Cao, Y., Wang, Y., Meng, D., et al. (2020), Diabetic retinopathy, classified using the lesion-aware deep learning system, predicts diabetic end-stage renal disease in Chinese patients. Endocrine Practice, 26(4), 429-443.
12. [12] Kermany, D.S., Goldbaum, M., Cai, W., Valentim, C.C., Liang, H., Baxter, S.L., et al. (2018), Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5), 1122-1131.
13. [13] Wang, Y. and Shan, S. (2018), Accurate disease detection quantification of iris based retinal images using random implication image classifier technique. Microprocessors and Microsystems, 80, 103350.
14. [14] Wang, X., Lu, Y., Wang, Y. and Chen., W. (2018), Diabetic retinopathy stage classification using convolutional neural networks. IEEE International Conference on Information Reuse and Integration (IRI).
15. [15] Sarki, R., Michalska, S., Ahmed, K., Wang, H. and Zhang, Y. (2019), Convolutional neural networks for mild diabetic retinopathy detection: an experimental study. bioRxiv, 763136.
16. [16] Xiao, D., Yu, S., Vignarajan, J., An, D., Tay-Kearney, M.-L. and Kanagasingam, Y. (2017), Retinal hemorrhage detection by rule-based and machine learning approach. 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).
17. [17] Wan, S., Liang, Y. and Zhang, Y. (2018), Deep convolutional neural networks for diabetic retinopathy detection by image classification. Computers & Electrical Engineering, 72, 274-282.
18. [18] Molina-Casado, J.M., Carmona, E.J. and García-Feijoó, J. (2017), Fast detection of the main anatomical structures in digital retinal images based on intra-and inter-structure relational knowledge. Computer methods and programs in biomedicine, 149, 55-68.
19. [19] Ur Rehman, M., Abbas, Z., Khan, S.H., and Ghani, S.H. (2018), Diabetic retinopathy fundus image classification using discrete wavelet transform. 2nd International Conference on Engineering Innovation.
20. [20] Jiang, Y., Wu, H. and Dong, J. (2017), Automatic screening of diabetic retinopathy images with convolution neural network based on caffe framework. Proceedings of the 1st International Conference on Medical and Health Informatics.
21. [21] Gao, Z., Li, J., Guo, J., Chen, Y., Yi, Z. and Zhong, J. (2018), Diagnosis of diabetic retinopathy using deep neural networks. IEEE Access, 7, 3360-3370.
22. [22] Asia Pacific Tele-Ophthalmology Society “APTOS”. (2019), Accessed april 2022. [Online]. Available: https://www.kaggle.com/c/aptos2019-blindness-detection
23. [23] Pratt, H., Coenen, F., Broadbent, D.M., Harding, S.P. and Zheng, Y. (2016), Convolutional neural networks for diabetic retinopathy. Procedia computer science, 90, 200-205.
24. [24] Deng, J., Dong, W., Socher, R., Li, L.-J., Li K. and Fei-Fei, L. (2009), Imagenet: A large-scale hierarchical image database. IEEE conference on computer vision and pattern recognition.
25. [25] LeCun, Y., Bengio, Y. and Hinton, G. (2015), Deep learning. Nature, 521, 7553, 436-444.
26. [26] He, K., Zhang, X., Ren, S. and Sun, J. (2016), Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition.
27. [27] Huang, G., Liu, Z., Van Der Maaten, L. and Weinberger, K.Q. (2017), Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition.
28. [28] Simonyan, K. and Zisserman, A. (2014), Very deep convolutional networks for large-scale image recognition. arXiv preprint, 1409-1556.
29. [29] Patil, S.B. and Patil, B. (2020), Retinal fundus image enhancement using adaptive CLAHE methods. Journal of Seybold Report, (1533), 9211.
30. [30] Khalifa, N.E.M., Loey, M., Taha, M.H.N. and Mohamed., H.N.E.T. (2019), Deep transfer learning models for medical diabetic retinopathy detection. Acta Informatica Medica, 27(5), 327.
31. [31] Lam, C. , Yi, D., Guo, M. and Lindsey, T. (2018), Automated detection of diabetic retinopathy using deep learning, AMIA summits on translational science proceedings, 147.
32. [32] Kumar, G., Chatterjee, S.K. and Chattopadhyay, C. (2020), Drdnet: Diagnosis of diabetic retinopathy using capsule network (Workshop Paper), IEEE Sixth International Conference on Multimedia Big Data (BigMM), 379-385.
33. [33] Lahmar, C., and Ali, I. (2022), Deep hybrid architectures for diabetic retinopathy classification. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 1-19.
34. [34] Anoop, B.K. (2022), Binary classification of DR-diabetic retinopathy using CNN with fundus colour images. Materials Today: Proceedings 58, 212-216.
35. [35] Mungloo-Dilmohamud, Z., Heenaye-Mamode Khan, M., Jhumka, K., Beedassy, B.N., Mungloo, N.Z. and Peña-Reyes, C. (2022), Balancing data through data augmentation improves the generality of transfer learning for diabetic retinopathy classification. Applied Sciences 12(11), 5363.