Advancing Diabetic Retinopathy Detection and Severity Classification using Dynamic SwishNet-181

Authors

  • K. Kayathri Ph.D Research Scholar, Department of Computer Science, Mother Teresa Women’s University, Kodaikanal, TN, India
  • K. Kavitha Assistant Professor, Department of Computer Science, Mother Teresa Women’s University, Kodaikanal, Tamil Nadu, India

Keywords:

Diabetic Retinopathy Detection, Dynamic SwishNet-181, Image Preprocessing Techniques, Deep Learning Evaluation Metrics, Vision Impairment Prevention

Abstract

Timely detection of Diabetic Retinopathy (DR) is critical in preventing vision impairment among diabetic individuals. This research introduces Dynamic SwishNet-181, a novel neural network architecture tailored for classifying DR severity levels (ranging from 0 for No DR to 4 for Proliferative DR). Unique to this study is the integration of Contrast Limited Adaptive Histogram Equalization (CLAHE) and Anisotropic Diffusion Filtering (ADF) as preprocessing techniques, refining retinal images by enhancing contrast and reducing noise. The evaluation of Dynamic SwishNet-181 includes a comparison against established CNN models such as VGG16, EfficientNET, and RESNET using performance metrics like accuracy, precision, recall, and F1-score. This comprehensive analysis aims to empower medical professionals by providing a reliable and accurate tool for diagnosing DR efficiently. By merging advanced deep learning models with image enhancement methods, this research offers a promising approach for accessible and dependable DR screening, potentially preventing vision loss in diabetic patients.

Downloads

Download data is not yet available.

References

Riaz, H.; Park, J.; Choi, H.; Kim, H.; Kim, J. Deep and Densely Connected Networks for Classification of Diabetic Retinopathy. Diagnostics 2020, 10, 24.

Gulshan, V., Peng, L., Coram, M., Stumpe, M.C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J. and Kim, R., 2019. "Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs." JAMA, 316(22), pp.2402-2410.

Singh, A., Dutta, M.K. and Raman, B., 2019. "Contrast limited adaptive histogram equalization for medical image processing." Procedia computer science, 132, pp.370-378.

Martinez, J.A., Galan, S., Aguilar, M., Seoane, J.A. and Cudeiro, J., 2019. "Anisotropic diffusion filtering in retinal image enhancement." In Biomedical Visualisation (BioMedVis), 2019 IEEE Pacific Visualization Symposium (PacificVis) (pp. 1-5). IEEE.

Lee, S., Yoon, Y., Kim, Y., Park, J., Lee, S.W. and Lee, S., 2020. "A comparative study of preprocessing techniques for diabetic retinopathy detection." Computer methods and programs in biomedicine, 187, p.105231.

Chen, Y., Cao, Z., Wang, T., Jiang, X., Yang, Z., Liu, C., Lu, J. and Chen, Q., 2021. "Evaluation of deep learning models for diabetic retinopathy classification." IEEE Access, 9, pp.13059-13068.

Hacisoftaoglu, R.E.; Karakaya, M.; Sallam, A.B. Deep learning frameworks for diabetic retinopathy detection with smartphone-based retinal imaging systems. Pattern Recognit. Lett. 2020, 135, 409–417.

Mohanty, C.; Mahapatra, S.; Acharya, B.; Kokkoras, F.; Gerogiannis, V.C.; Karamitsos, I.; Kanavos, A. Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy. Sensors 2023, 23, 5726.

Zang, P.; Hormel, T.T.; Guo, Y.; Wang, X.; Flaxel, C.J.; Bailey, S.; Hwang, T.S.; Jia, Y. Deep-learning-aided Detection of Referable and Vision Threatening Diabetic Retinopathy based on Structural and Angiographic Optical Coherence Tomography. Invest. Ophthalmol. Vis. Sci. 2021, 62, 2116.

Bora, A.; Balasubramanian, S.; Babenko, B.; Virmani, S.; Venugopalan, S.; Mitani, A.; Marinho, G.D.O.; Cuadros, J.; Ruamviboonsuk, P.; Corrado, G.S.; et al. Predicting the risk of developing diabetic retinopathy using deep learning. Lancet Digit. Health 2021, 3, e10–e19.

Skariah, S.M.; Arun, K.S. A Deep learning-based Approach for Automated Diabetic Retinopathy Detection and Grading. In Proceedings of the 2021 4th Biennial International Conference on Nascent Technologies in Engineering (ICNTE), Mumbai, India, 15–16 January 2021; pp. 1–6.

V. Vipparthi, D. R. Rao, S. Mullu and V. Patlolla, "Diabetic Retinopathy Classification using Deep Learning Techniques," 2022 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 2022, pp. 840-846.

S. Kumar and R. Rani, "Advances in Diabetic Retinopathy Classification using Deep Learning: The Last 5 Years Review," 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), IEEE, Jalandhar, India, 2023, pp. 373-378.

Chen, PN., Lee, CC., Liang, CM. et al. General deep learning model for detecting diabetic retinopathy. BMC Bioinformatics 22 (Suppl 5), Springer, 84 (2021).

S. W. Aditi, F. Kabir and P. C. Shill, "Diagnosis of Diabetic Retinopathy Using Deep Learning Techniques," 2021 5th International Conference on Electrical Information and Communication Technology (EICT), IEEE, Khulna, Bangladesh, 2021, pp. 1-6.

P. Patra and T. Singh, "Diabetic Retinopathy Detection using an Improved ResNet 50-InceptionV3 and hybrid DiabRetNet Structures," 2022 OITS International Conference on Information Technology (OCIT), IEEE, Bhubaneswar, India, 2022, pp. 140-145.

I. Giroti, J. K. A. Das, N. M. Harshith and G. Thahniyath, "Diabetic Retinopathy Detection & Classification using Efficient Net Model," 2023 International Conference on Artificial Intelligence and Applications (ICAIA) Alliance Technology Conference (ATCON-1), IEEE, Bangalore, India, 2023, pp. 1-6.

K. S. Reddy and M. Narayanan, "An Efficiency way to analyse Diabetic Retinopathy Detection and Classification using Deep Learning Techniques," 2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), IEEE, Greater Noida, India, 2023, pp. 1388-1392.

Downloads

Published

24.03.2024

How to Cite

Kayathri, K. ., & Kavitha, K. . (2024). Advancing Diabetic Retinopathy Detection and Severity Classification using Dynamic SwishNet-181. International Journal of Intelligent Systems and Applications in Engineering, 12(20s), 61–77. Retrieved from https://www.ijisae.org/index.php/IJISAE/article/view/5119

Issue

Vol. 12 No. 20s (2024)

Section

Research Article

License

Copyright (c) 2024 K. Kayathri, K. Kavitha

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.