Enhancing Diabetic Retinopathy Detection Using Optimized Deep Learning Techniques with ResNet
DOI:
https://doi.org/10.26438/ijcse/v13i4.5967Keywords:
Diabetic Retinopathy, Deep Learning, ResNet-50, Retinal Fundus Images, ClassificationAbstract
Diabetic retinopathy (DR) is an extreme complication of diabetes and a main reason of vision impairment worldwide. Early detection is essential for powerful treatment and prevention of blindness. In this paper, we gift a deep learning approach for the automatic detection of DR the use of ResNet, a convolutional neural network (CNN) architecture known for its intensity and excessive performance in photo reputation obligations. Our examine utilizes a big dataset of retinal fundus pictures, which undergo preprocessing and augmentation to beautify the version’s robustness. The ResNet model is exceptional-tuned to classify specific stages of DR with an excessive diploma of accuracy. The consequences exhibit that our version achieves a class accuracy of 94.3%, appreciably enhancing detection competencies as compared to standard techniques. This paper explores using switch getting to know and optimization techniques to cope with demanding situations along with overfitting and dataset imbalance, in the end offering a green, scalable solution for computerized diabetic retinopathy screening.
References
[1] Neha Tamboli, G.S. Malande, “Proliferative Diabetic Retinopathy Detection Using Machine Learning”, International Journal of Computer Sciences and Engineering, Vol.8, Issue.6, pp.106-111, 2020.
[2] Saurabh. S. Athalye, Gaurav Vijay, “Survey of Automatic Detection of Diabetic Retinopathy using digital image processing”, International Journal of Computer Sciences and Engineering, Vol.7, Issue.3, pp.352-355, 2019.
[3] K.K. Faisal , C.M. Deepa, S.M. Nisha, G. Gopi, “Study on Diabetic Retinopathy Detection Techniques”, International Journal of Computer Sciences and Engineering, Vol.4 , Issue.11, pp.137-140, 2016.
[4] Rajesh I.S., Bharathi Malakreddy A., Maithri C., Manjunath Sargur Krishnamurthy, Shashidhara M.S, “Automatic Detection of Optic Disc and Its Center in Color Retinal Images: A Review”, International Journal of Computer Sciences and Engineering, Vol.12, Issue.4, pp.81-85, 2024.
[5] Kaveri Devi, Arshdeep Kaur, “MSVM Based Technique Used To Detect Diabetic Retinopathy at Early Stage” , International Journal of Computer Sciences and Engineering, Vol.9, Issue.3, pp.34-40, 2021.
[6] Ruthran Baskar, Emmanuel Sabu, Claudia Mazo, “Deep CNNs for Diabetic Retinopathy Classification: A Transfer Learning Perspective”, 2024 IEEE International Symposium on Biomedical Imaging, 2024.
[7] Aryan Kokane,Gourhari Sharma, Akash Raina, Shubham Narole, Prof. Pramila M. Chawan. “Detection of Diabetic Retinopathy using Machine Learning”, International Research Journal of Engineering and Technology, Vol.7, Issue.11, pp.663-637, 2020.
[8] R. Gargeya and T. Leng, “Automated Identi fi cation of Diabetic Retinopathy Using Deep Learning,” Ophthalmology, pp.1–8, 2017.
[9] M. D. Abr„amoff, M. K. Garvin, and M. Sonka, “Retinal imaging and picture analysis,” IEEE Reviews in Medicine Engineering, Vol.3, pp.169–208, 2010
[10] V. Ramya, “SVM Based Detection for Diabetic Retinopathy,” Iccad, Vol.5, No.1, pp.11–13, 2018.
[11] MN. Abrmoff, M. Niemeijer, MS. Suttorp-Schulten, MA. Viergever, SR. Russell, B. Van Ginneken , “Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes”, Diabetes Care; Vol.31, Issue.2, pp.193–205, 2008.
[12] J. Nayak, PS. Bhat, R. Acharya, CM. Lim, M. Kagathi, “Automated identification of different stages of diabetic retinopathy using digital fundus images”, J Med Syst; Vol.32, Issue.2, pp.107–115, 2008.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
