Advancing Diabetic Retinopathy Detection: Integrating Deep Learning and Texture Analysis for Enhanced Lesion Identification
Keywords:
Convolutional Neural Network, Diabetes Mellitus, Diabetic Retinopathy, Gray-Level Co-occurrence Matrix, Neighborhood Component Analysis, Support Vector Machine
Abstract
The proposed work intends to automate the detection and classification of diabetic retinopathy from retinal fundus image which is very important in ophthalmology. Most of the existing methods use handcrafted features and those are fed to the classifier for detection and classification purpose. Recently convolutional neural network (CNN) is used for this classification problem but the architecture of CNN is manually designed. This paper proposes a novel methodology that combines deep learning techniques with texture analysis to enhance the accuracy of retinal lesion detection. The proposed methodology integrates Convolutional Neural Network (CNN)-based deep features extraction with Gray-Level Co-occurrence Matrix (GLCM) texture features extraction. Additionally, a feature fusion process and Neighborhood Component Analysis (NCA)-based feature selection are employed to optimize the feature representation. The classification stage utilizes Support Vector Machine (SVM) to classify retinal images based on the extracted features. Simulation results and discussions on the DRIVE dataset demonstrate the effectiveness of the proposed methodology, achieving an accuracy of 99.07% and demonstrating superior performance compared to previous research works.
References
1. Agarwal, S. and Bhat, A., 2023. A survey on recent developments in diabetic retinopathy detection through integration of deep learning. Multimedia Tools and Applications, 82(11), pp.17321-17351.
2. Tassew, W.C., Birhan, N. and Zewdu, Y., 2023. Incidence and Predictors of Diabetic Retinopathy among Newly Diagnosed Type 2 Diabetic Patients at Chronic Follow-Up Clinic of University of Gondar Specialized Hospital: A Retrospective Follow-Up Study. Int J Diabetes Clin Res, 10, p.169.
3. Tan, T.E. and Wong, T.Y., 2023. Diabetic retinopathy: Looking forward to 2030. Frontiers in Endocrinology, 13, p.1077669.
4. Curran, K., Piyasena, P., Congdon, N., Duke, L., Malanda, B. and Peto, T., 2023. Inclusion of diabetic retinopathy screening strategies in national-level diabetes care planning in low-and middle-income countries: a scoping review. Health Research Policy and Systems, 21(1), p.2.
5. Currie, C.J., 2024. The descriptive epidemiology of type 2 diabetes in the United Kingdom from 2004 to 2021. medRxiv, pp.2024-03.
6. Özbay, E., 2023. An active deep learning method for diabetic retinopathy detection in segmented fundus images using artificial bee colony algorithm. Artificial Intelligence Review, 56(4), pp.3291-3318.
7. Vij, R. and Arora, S., 2023. A systematic review on diabetic retinopathy detection using deep learning techniques. Archives of Computational Methods in Engineering, 30(3), pp.2211-2256.
8. Nadeem, M.W., Goh, H.G., Hussain, M., Liew, S.Y., Andonovic, I. and Khan, M.A., 2022. Deep learning for diabetic retinopathy analysis: A review, research challenges, and future directions. Sensors, 22(18), p.6780.
9. Qomariah, D.U.N. and Tjandrasa, H., 2022, October. Exudate detection in retinal fundus images using combination of mathematical morphology and Renyi entropy thresholding. In 2022 11th International Conference on Information & Communication Technology and System (ICTS) (pp. 31-36). IEEE.
10. Qomariah, D.U.N., Tjandrasa, H. and Fatichah, C., 2023, July. Classification of diabetic retinopathy and normal retinal images using CNN and SVM. In 2023 12th International Conference on Information & Communication Technology and System (ICTS) (pp. 152-157). IEEE.
11. Putra, R.E., Tjandrasa, H., Suciati, N. and Wicaksono, A.Y., 2022, October. Non-proliferative diabetic retinopathy classification based on hard exudates using combination of frcnn, morphology, and anfis. In 2022 Third international conference on vocational education and electrical engineering (ICVEE) (pp. 1-6). IEEE.
12. Sahu, S., Singh, A.K., Ghrera, S.P. and Elhoseny, M., 2023. An approach for de-noising and contrast enhancement of retinal fundus image using CLAHE. Optics & Laser Technology, 110, pp.87-98.
13. Solhi, M., Yazdi, M. and Sharzehei, M., 2022. Fusion of Synthetic Aperture Radar Images and Optical Images Using Curvelet Transform and Retina model. Journal of Radar and Optical Remote Sensing and GIS, 3(2), pp.34-52.
14. Rehman, A., Harouni, M., Karimi, M., Saba, T., Bahaj, S.A. and Awan, M.J., 2022. Microscopic retinal blood vessels detection and segmentation using support vector machine and K‐nearest neighbors. Microscopy research and technique, 85(5), pp.1899-1914.
15. Asiri, N., Hussain, M., Adel, F.A. and Aboalsamh, H., 2021. A deep learning-based unified framework for red lesions detection on retinal fundus images. arXiv preprint arXiv:2109.05021.
16. Bhardwaj, C., Jain, S. and Sood, M., 2023. Diabetic retinopathy lesion discriminative diagnostic system for retinal fundus images. Advanced Biomedical Engineering, 9, pp.71-82.
17. Javidi, M., Harati, A. and Pourreza, H., 2021. Retinal image assessment using bi-level adaptive morphological component analysis. Artificial intelligence in medicine, 99, p.101702.
18. Das, S. and Majumder, S., 2022. Overview and Analysis of Present-Day Diabetic Retinopathy (DR) Detection Techniques. Approaches and Applications of Deep Learning in Virtual Medical Care, pp.52-80.
19. Datta, N.S., Dutta, H.S., Majumder, K., Chatterjee, S. and Wasim, N.A., 2022. An improved method for automated identification of hard exudates in diabetic retinopathy disease. IETE Journal of Research, 68(1), pp.611-621.
20. Senapati, R.K., 2022. Bright lesion detection in color fundus images based on texture features. Bulletin of Electrical Engineering and Informatics, 5(1), pp.92-100.
21. Wan, S., Liang, Y. and Zhang, Y., 2021. Deep convolutional neural networks for diabetic retinopathy detection by image classification. Computers & Electrical Engineering, 72, pp.274-282.
22. Chowdhury, A.R., Chatterjee, T. and Banerjee, S., 2019. A random forest classifier-based approach in the detection of abnormalities in the retina. Medical & biological engineering & computing, 57, pp.193-203.
2. Tassew, W.C., Birhan, N. and Zewdu, Y., 2023. Incidence and Predictors of Diabetic Retinopathy among Newly Diagnosed Type 2 Diabetic Patients at Chronic Follow-Up Clinic of University of Gondar Specialized Hospital: A Retrospective Follow-Up Study. Int J Diabetes Clin Res, 10, p.169.
3. Tan, T.E. and Wong, T.Y., 2023. Diabetic retinopathy: Looking forward to 2030. Frontiers in Endocrinology, 13, p.1077669.
4. Curran, K., Piyasena, P., Congdon, N., Duke, L., Malanda, B. and Peto, T., 2023. Inclusion of diabetic retinopathy screening strategies in national-level diabetes care planning in low-and middle-income countries: a scoping review. Health Research Policy and Systems, 21(1), p.2.
5. Currie, C.J., 2024. The descriptive epidemiology of type 2 diabetes in the United Kingdom from 2004 to 2021. medRxiv, pp.2024-03.
6. Özbay, E., 2023. An active deep learning method for diabetic retinopathy detection in segmented fundus images using artificial bee colony algorithm. Artificial Intelligence Review, 56(4), pp.3291-3318.
7. Vij, R. and Arora, S., 2023. A systematic review on diabetic retinopathy detection using deep learning techniques. Archives of Computational Methods in Engineering, 30(3), pp.2211-2256.
8. Nadeem, M.W., Goh, H.G., Hussain, M., Liew, S.Y., Andonovic, I. and Khan, M.A., 2022. Deep learning for diabetic retinopathy analysis: A review, research challenges, and future directions. Sensors, 22(18), p.6780.
9. Qomariah, D.U.N. and Tjandrasa, H., 2022, October. Exudate detection in retinal fundus images using combination of mathematical morphology and Renyi entropy thresholding. In 2022 11th International Conference on Information & Communication Technology and System (ICTS) (pp. 31-36). IEEE.
10. Qomariah, D.U.N., Tjandrasa, H. and Fatichah, C., 2023, July. Classification of diabetic retinopathy and normal retinal images using CNN and SVM. In 2023 12th International Conference on Information & Communication Technology and System (ICTS) (pp. 152-157). IEEE.
11. Putra, R.E., Tjandrasa, H., Suciati, N. and Wicaksono, A.Y., 2022, October. Non-proliferative diabetic retinopathy classification based on hard exudates using combination of frcnn, morphology, and anfis. In 2022 Third international conference on vocational education and electrical engineering (ICVEE) (pp. 1-6). IEEE.
12. Sahu, S., Singh, A.K., Ghrera, S.P. and Elhoseny, M., 2023. An approach for de-noising and contrast enhancement of retinal fundus image using CLAHE. Optics & Laser Technology, 110, pp.87-98.
13. Solhi, M., Yazdi, M. and Sharzehei, M., 2022. Fusion of Synthetic Aperture Radar Images and Optical Images Using Curvelet Transform and Retina model. Journal of Radar and Optical Remote Sensing and GIS, 3(2), pp.34-52.
14. Rehman, A., Harouni, M., Karimi, M., Saba, T., Bahaj, S.A. and Awan, M.J., 2022. Microscopic retinal blood vessels detection and segmentation using support vector machine and K‐nearest neighbors. Microscopy research and technique, 85(5), pp.1899-1914.
15. Asiri, N., Hussain, M., Adel, F.A. and Aboalsamh, H., 2021. A deep learning-based unified framework for red lesions detection on retinal fundus images. arXiv preprint arXiv:2109.05021.
16. Bhardwaj, C., Jain, S. and Sood, M., 2023. Diabetic retinopathy lesion discriminative diagnostic system for retinal fundus images. Advanced Biomedical Engineering, 9, pp.71-82.
17. Javidi, M., Harati, A. and Pourreza, H., 2021. Retinal image assessment using bi-level adaptive morphological component analysis. Artificial intelligence in medicine, 99, p.101702.
18. Das, S. and Majumder, S., 2022. Overview and Analysis of Present-Day Diabetic Retinopathy (DR) Detection Techniques. Approaches and Applications of Deep Learning in Virtual Medical Care, pp.52-80.
19. Datta, N.S., Dutta, H.S., Majumder, K., Chatterjee, S. and Wasim, N.A., 2022. An improved method for automated identification of hard exudates in diabetic retinopathy disease. IETE Journal of Research, 68(1), pp.611-621.
20. Senapati, R.K., 2022. Bright lesion detection in color fundus images based on texture features. Bulletin of Electrical Engineering and Informatics, 5(1), pp.92-100.
21. Wan, S., Liang, Y. and Zhang, Y., 2021. Deep convolutional neural networks for diabetic retinopathy detection by image classification. Computers & Electrical Engineering, 72, pp.274-282.
22. Chowdhury, A.R., Chatterjee, T. and Banerjee, S., 2019. A random forest classifier-based approach in the detection of abnormalities in the retina. Medical & biological engineering & computing, 57, pp.193-203.
Published
2023-11-26
How to Cite
Shubhi Shrivastava, Dr. Shanti Rathore, Dr. Rahul Gedam, & Dr. Sharda Pratap Shrivas. (2023). Advancing Diabetic Retinopathy Detection: Integrating Deep Learning and Texture Analysis for Enhanced Lesion Identification. Revista Electronica De Veterinaria, 24(4), 366 - 381. https://doi.org/10.69980/redvet.v24i4.723
Issue
Section
Articles
