ResNet-34/DR: A Residual Convolutional Neural Network for the Diagnosis of Diabetic Retinopathy

Noor M. Al-Moosawi M. Al-Moosawi, Raidah Salim Khudeyer

Abstract


Diabetic retinopathy (DR) is an eye complication associated with diabetes, resulting in blurred vision or blindness. The early diagnosis and treatment of DR can decrease the risk of vision loss dramatically. However, such diagnosis is a tedious and complicated task due to the variability of retinal changes across the stages of the diseases, and due to the high number of undiagnosed and untreated DR cases. In this paper, we develop a computationally efficient and scalable deep learning model using convolutional neural networks (CNN), for diagnosing DR automatically. Various preprocessing algorithms are utilized to improve accuracy, and a transfer learning strategy is adopted to speed up the process. Our experiment used the fundus image set available on online Kaggle datasets. As an ultimate conclusion of applicable performance metrics, our computational simulation achieved a relatively-high F1 score of 93.2% for stage-based DR classification.


Full Text:

PDF

References


W. H. O. and Others(2020), Diabetic retinopathy screening: a short guide. World Health Organization. Regional Office for Europe.

M. T. Islam, H. R. H. Al-Absi, E. A. Ruagh, and T. Alam(2021), “DiaNet: A Deep Learning Based Architecture to Diagnose Diabetes Using Retinal Images only,” IEEE Access, vol. 9, pp. 15686–15695,doi: 10.1109/ACCESS.2021.3052477.

R. Sarki, K. Ahmed, H. Wang, and Y. Zhang(2020), “Automatic Detection of Diabetic Eye Disease through Deep Learning Using Fundus Images: A Survey,” IEEE Access, vol. 8, pp. 151133–151149, doi: 10.1109/ACCESS.2020.3015258.

J. J. Gómez-Valverde et al.(2019), “Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning,” Biomed. Opt. Express, vol. 10, no. 2, p. 892, doi: 10.1364/boe.10.000892.

X. Ma et al.(2021), “Understanding adversarial attacks on deep learning based medical image analysis systems,” Pattern Recognit., vol. 110, doi: 10.1016/j.patcog.2020.107332.

Feizi, A. (2019), "Convolutional gating network for object tracking." International Journal of Engineering 32.7: 931-939.

Sezavar, A., H. Farsi, and Sajad Mohamadzadeh(2019). "A modified grasshopper optimization algorithm combined with cnn for content based image retrieval." International Journal of Engineering 32.7: 924-930.

S. Long, J. Chen, A. Hu, H. Liu, Z. Chen, and D. Zheng(2020), “Microaneurysms detection in color fundus images using machine learning based on directional local contrast,” Biomed. Eng. Online, vol. 19, no. 1, pp. 1–23, doi: 10.1186/s12938-020-00766-3.

Y. Tong, W. Lu, Y. Yu, and Y. Shen(2020), “Application of machine learning in ophthalmic imaging modalities,” Eye Vis., vol. 7, no. 1, pp. 1–15, doi: 10.1186/s40662-020-00183-6.

Z. Wang and J. Yang(2017), “Diabetic Retinopathy Detection via Deep Convolutional Networks for Discriminative Localization and Visual Explanation,” [Online]. Available: http://arxiv.org/abs/1703.10757.

M. T. Hagos and S. Kant(2019), “Transfer learning based detection of Diabetic Retinopathy from small dataset,” arXiv.

M. Shaban et al(2020)., “A convolutional neural network for the screening and staging of diabetic retinopathy,” PLoS One, vol. 15, no. 6 June, pp. 1–13, doi: 10.1371/journal.pone.0233514.

I. Namatēvs(2018), “Deep Convolutional Neural Networks: Structure, Feature Extraction and Training,” Inf. Technol. Manag. Sci., vol. 20, no. 1, pp. 40–47, doi: 10.1515/itms-2017-0007.

M. Al-Smadi, M. Hammad, Q. B. Baker, and S. A. Al-Zboon(2021), “A transfer learning with deep neural network approach for diabetic retinopathy classification,” Int. J. Electr. Comput. Eng., vol. 11, no. 4, pp. 3492–3501,, doi: 10.11591/ijece.v11i4.pp3492-3501.

B. K. Triwijoyo, B. S. Sabarguna, W. Budiharto, and E. Abdurachman(2020), "Deep learning approach for classification of eye diseases based on color fundus images". Elsevier Inc.

S. N. Chakravarthy, “DR-NET : A Stacked Convolutional Classifier Framework for Detection of Diabetic Retinopathy,” no. 1.

P. K. V. Warkar(2021), “A Survey on Multiclass Image Classification based on Inception-v3 Transfer Learning Model,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 9, no. 2, pp. 169–172, doi: 10.22214/ijraset.2021.33018.

M. A. Morid, A. Borjali, and G. Del Fiol(2021), “A scoping review of transfer learning research on medical image analysis using ImageNet,” Comput. Biol. Med., vol. 128, no. 408, 2021, doi: 10.1016/j.compbiomed.2020.104115.

A. K. Gangwar and V. Ravi(2021), Diabetic Retinopathy Detection Using Transfer Learning and Deep Learning, vol. 1176. Springer Singapore.

A. Jain, A. Jalui, J. Jasani, Y. Lahoti, and R. Karani(2019), “Deep Learning for Detection and Severity Classification of Diabetic Retinopathy,” Proc. 1st Int. Conf. Innov. Inf. Commun. Technol. ICIICT 2019, pp. 1–6, doi: 10.1109/ICIICT1.2019.8741456.

Lam, C., Yi, D., Guo, M., Lindsey(2018), "T.: Automated detection of diabetic retinopathy using deep learning". AMIA Summits Transl. Sci. Proc. 2017, 147 .

M. Gao, D. Qi, H. Mu, and J. Chen(2021), “A Transfer Residual Neural Network Based on ResNet-34 for Detection of Wood Knot Defects”.

S. Wu, S. Zhong, and Y. Liu(2017), “Deep residual learning for image Recognition,” Multimed. Tools Appl., pp. 1–17, doi: 10.1007/s11042-017-4440-4.

K. Simonyan, A. Zisserman(2014), “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556.

F. Chollet(2017), ‘‘Xception: Deep learning with depthwise separable convolutions,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jul. , pp. 1251–1258.

Y. Chai, H. Liu, and J. Xu(2017), “Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models” Knowledge-Based Syst., vol. 161, no. December 2017, pp. 147–156, 2018, doi: 10.1016/j.knosys.2018.07.043.

“APTOS 2019 Blindness Detection.” [Online]. Available: https://www.kaggle.com/c/aptos2019-blindness-detection/.

P. Prasanna, P. Samiksha, K. Ravi, K. Manesh, D. Girish, S. Vivek, and M. Fabrice. (2018). Indian Diabetic Retinopathy Image Dataset (IDRiD), doi: 10.21227/H25W98.

colab.research.google.com/notebooks/ welcome.ipynb#.

B. Graham(2015), “Kaggle Diabetic Retinopathy Detection competition report,” pp. 1–9.




DOI: https://doi.org/10.31449/inf.v45i7.3774

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.