METHODS FOR PRE-PROCESSING AND ANALYSIS OF FUND IMAGES FOR DETECTION OF DIABETIC RETINOPATHY

This work is intended to study methods for pre-processing and analysis of fundus images for the detection of diabetic retinopathy. Diabetic retinopathy (DR) is a common eye disease in patients with diabetes, and its early diagnosis allows you to prevent vision loss. During the study, modern methods for processing and analyzing fundus images were used, including the EfficientNetB0 architecture based on Deep Learning. Image augmentation (rotation, scaling, cropping, contrast enhancement) and normalization methods were introduced for pre-processing. When using the EfficientNetB0 architecture, two approaches were tested: training the base layers and additional adaptation (fine-tuning) by opening the upper layers. The results were evaluated by metrics. The precision for the test set in the first method was 65%, and for the second method 75%. The accuracy of the validation set in the first method was 63%, and in the second method it reached 71%. The recall metric showed 60% for the test set in the first method, and 74% in the second method. In general, the fine-tuning method showed high performance. The use of these methods allows to improve the quality of image processing and classification for effective diagnosis of diabetic retinopathy.

The novelty of the study is the analysis of various methods of using and adapting the highly efficient EfficientNetB0 architecture. The results obtained allow to improve the quality of automated systems in DR diagnostics and increase the energy efficiency of the model. The proposed methods have high potential for early detection of eye diseases.

1. Mehmet, Şahin., Omer, Faruk, Beyca.Diabetic Retinopathy Diagnosis with Image Processing (2024). https://doi.org/10.1109/siu61531.2024.10601116.

2. Nikita, S., Demin., N., Yu., Ilyasova., Rustam, Paringer. Automatic Selection of the Optimal Zone for Laser Exposure According to the Fundus Images for Laser Coagulation (2023). https://doi.org/10.18287/jbpe23.09.040308.

3. Agnieszka, Cisek., Karolina, Korycinska., Leszek, Pyziak., Marzena, Malicka.,Tomasz, Wiecek., Grzegorz, Gruzel., K., Szmuc., Jozef, Cebulski., Mariusz, Spyra. Algorithm-based diagnostic application for diabetic retinopathy detection. arXiv.org.abs/2312.00529 (2023). https://doi.org/10.48550/arxiv.2312.00529.

4. Balaji, S., Karthik, B., Gokulakrishnan D. Prediction of Diabetic Retinopathy using Deep Learning with Preprocessing. EAI Endorsed Transactions on Pervasive Health and Technology, 10 (2024). https://doi.org/10.4108/eetpht.10.5183.

5. Rubina, Sarki, Khandakar, Ahmed, Hua, Wang… Yanchun, Zhang… Jiangang, Ma., Kate, N., Wang. Image Preprocessing in Classification and Identification of Diabetic Eye Diseases. Data Science and Engineering, 6(4), 1–17 (2021). https://doi.org/10.1007/S41019-021-00167-Z.

6. Onesinus, Saut, Parulian, Jufriadif, Na’am. Advanced Filtering and Enhancement Techniques for Diabetic Retinopathy Image Analysis. Journal Medical Informatics Technology, 69–75 (2024). https://doi.org/10.37034/medinftech.v2i3.40.

7. Imtiyaz, Ahmad, Vibhav, Prakash, Singh, Manoj, Madhava, Gore. Detection of Diabetic Retinopathy Using Discrete Wavelet-Based Center-Symmetric Local Binary Pattern and Statistical Features. Deleted Journal (2024). https://doi.org/10.1007/s10278-024-01243-2.

8. Sagar, Zanjad. Diabetic Retinopathy Detection from Retinal Images. Indian Scientific Journal Of Research In Engineering And Management, 08(06), 1–5 (2024). https://doi.org/10.55041/ijsrem35218.

9. Mage, Usha, U., Subburaj, T., Hemanth, K.J. Innovative AI Solution for Diabetic Retinopathy Health. International Journal of Advanced Research in Science, Communication and Technology, 10–13 (2024). https://doi.org/10.48175/ijarsct-19003.

10. Kalindhu Navanjana De Silva, K., Sanduni Kumari Lanka Fernando, T., Lakshan Sandaruwan Jayasinghe, L.D., Dinuka Sandaruwan Jayalath, M.H., Kasun Karunanayake, B.A.P. Madhuwantha. Towards Accurate Detection of Diabetic Retinopathy Using Image Processing and Deep Learning. International Journal of Advanced Computer Science and Applications, 15(9) (2024). https://doi.org/10.14569/ijacsa.2024.0150986.

11. Mahesh, M.R., Rohith, S. Analysis of Diabetic Retinopathy in Retinal Fundus Images, 1–5 (2024). https://doi.org/10.1109/ickecs61492.2024.10616880.

12. Balaji., S., Karthik, B., Gokulakrishnan, D. Prediction of Diabetic Retinopathy using Deep Learning with Preprocessing. EAI Endorsed Transactions on Pervasive Health and Technology, 10 (2024). https://doi.org/10.4108/eetpht.10.5183.

13. Shrimali, S. Image Filtering and Utilization of Deep Learning Algorithms to Detect the Severity of Diabetic Retinopathy. International Conference on Communication Systems and Network Technologies, 202– 207 (2023). https://doi.org/10.1109/CSNT57126.2023.10134680.

14. Mamyrbayev, O.Zh., Pavlov, S.V., Momynzhanova, K.R. Development of an expert system based on fuzzy logic for early diagnosis of glaucoma. Herald of the Kazakh-British technical university, 21(3), 37–47 (2024) (In Kazakh). https://doi.org/10.55452/1998-6688-2024-21-3-37-47.

15. Imane, Mehidi. Pre-processing Techniques: A Review for Retinal Image Segmentation (2024). https://doi.org/10.1109/iceeac61226.2024.10576331.

16. Thirawat, Saengarun, Niwat, Angkawisittpan, Adisorn, Nuan-On., Guifen, Lyu, Xiaoli, Fu., Sivarit, Sultornsanee. The Development for Diabetic Retinopathy Lesion Detection on Fundus Photography (2024). https://doi.org/10.1109/ieecon60677.2024.10537869.

17. Surmayanti, Sumijan, Sumijan, Saiful, Bukhori. Identification of Diabetic Retinopathy Using the Extraction Method on Fundus Images, 333–340 (2024). https://doi.org/10.1109/icoict61617.2024.10698276.

18. Pranoti, Nage, Sanjay, Shitole. Analysis of Image Processing Techniques for Retinal Fundus Images in Detection of Ophthalmic Disease Screening, 1–4 (2023). https://doi.org/10.1109/icccnt56998.2023.10306704.

19. Vignesh., R., Muthukumaran, N. Detection of Diabetic Retinopathy Image Analysis using Convolution Graph Neural Network, 921–929 (2023). https://doi.org/10.1109/ICICT57646.2023.10134388.

20. Abisha, J., Jeba, P.S. Detection of Diabetic Retinopathy by Using Convolutional Neural Network (2023). https://doi.org/10.59544/mine9624/ngcesi23p89.

21. Farzaneh, Nikbakhtsarvestani, Shahryar, Rahnamayan, Mehran, Ebrahimi. Opposition-based Multi-Objective ADAM Optimizer (OMAdam) for Training ANNs, 1–10 (2024). https://doi.org/10.1109/cec60901.2024.10612083.

22. Alexandra de Raadt, Matthijs J. Warrens., Roel Bosker, Henk, A.L., Kiers. Kappa Coefficients for Missing Data. Educational and Psychological Measurement, 79(3), 558–576 (2019). https://doi.org/10.1177/0013164418823249.