A Novel Approach for Diabetic Retinopathy Detection Using Sine Cosine Algorithm-Optimized Neural Network Classifier
Keywords:
Diabetic Retinopathy, HOG, LBP, Neural Network, Sine Cosine AlgorithmAbstract
This research introduces a comprehensive methodology for diabetic retinopathy (DR) detection and classification by integrating advanced image processing techniques with machine learning models. The proposed approach consists of several key stages: image acquisition, contrast enhancement, blood vessel extraction, optic disc extraction, lesion candidate extraction, feature extraction, and classification using an optimized neural network. Initially, retinal images are acquired and enhanced using contrast techniques such as Histogram Equalization to improve visibility. Blood vessel extraction is performed using Gabor filtering, which efficiently highlights vessel structures through multi-scale and multi-orientation filters. After vessel extraction, optic disc extraction is carried out to isolate this key anatomical feature, followed by lesion candidate extraction to detect potential DR-related lesions. Feature extraction is then performed using Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP), capturing gradient and texture information, respectively. Finally, a neural network classifier, optimized using the Sine Cosine Algorithm (SCA), is employed to classify the severity of DR. The methodology is validated using the DRIVE and FIRE datasets, achieving a maximum classification accuracy of 96.83%, demonstrating the superior performance of the SCA-NN approach over traditional neural network models.
Downloads
Metrics
References
Abdel Maksoud, E., Barakat, S., & Elmogy, M. (2022). A comprehensive diagnosis system for early signs and different diabetic retinopathy grades using fundus retinal images based on pathological changes detection. Computers in Biology and Medicine, 126, 104039.
Frazao, L. B., Theera-Umpon, N., & Auephanwiriyakul, S. (2024). Diagnosis of diabetic retinopathy based on holistic texture and local retinal features. Information Sciences, 475, 44–66.
Wu, Z., Shi, G., Chen, Y., Shi, F., Chen, X., Coatrieux, G., Yang, J., Luo, L., & Li, S. (2022). Coarse- to-fine classification for diabetic retinopathy grading using convolutional neural network. Artificial Intelligence in Medicine, 108(January), 101936.
Momeni Pour, A., Seyedarabi, H., Abbasi Jahromi, S. H., & Javadzadeh, A. (2022). Automatic Detection and Monitoring of Diabetic Retinopathy Using Efficient Convolutional Neural Networks and Contrast Limited Adaptive Histogram Equalization. IEEE Access, 8, 136668– 136673.
Saxena, G., Verma, D. K., Paraye, A., Rajan, A., & Rawat, A. (2022). Improved and robust deep learning agent for preliminary detection of diabetic retinopathy using public datasets. Intelligence-Based Medicine, 3–4(June), 100022.
Katada, Y., Ozawa, N., Masayoshi, K., Ofuji, Y., Tsubota, K., & Kurihara, T. (2022). Automatic screening for diabetic retinopathy in interracial fundus images using artificial intelligence. Intelligence-Based Medicine, 3–4(July), 100024.
Nguyen, Q. H., Muthuraman, R., Singh, L., Sen, G., Tran, A. C., Nguyen, B. P., & Chua, M. (2022). Diabetic Retinopathy Detection using Deep Learning. Proceedings of the 4th International Conference on Machine Learning and Soft Computing, 16(3), 103–107.
Dutta, S., Manideep, B. C. S., Basha, S. M., Caytiles, R. D., & Iyengar, N. C. S. N. (2023). Classification of Diabetic Retinopathy Images by Using Deep Learning Models. International Journal of Grid and Distributed Computing, 11(1), 99–106.
R C, K., Ankalaki, S., & Majumdar, J. (2022). A Study of Performance Evaluation of Convolution Neural Network for Diabetic Retinopathy. International Journal of Advanced Trends in Computer Science and Engineering, 9(4), 5009–5014.
Zhou, L., Zhao, Y., Yang, J., Yu, Q., & Xu, X. (2023). Deep multiple instance learning for automatic detection of diabetic retinopathy in retinal images. IET Image Processing, 12(4), 563–571.
Sangeethaa, S. N., & Uma Maheswari, P. (2023). An Intelligent Model for Blood Vessel Segmentation in Diagnosing DR Using CNN. Journal of Medical Systems, 42(10), 175.
Li, F., Liu, Z., Chen, H., Jiang, M., Zhang, X., & Wu, Z. (2024). Automatic Detection of Diabetic Retinopathy in Retinal Fundus Photographs Based on Deep Learning Algorithm. Translational Vision Science & Technology, 8(6), 4.
Mobeen-ur-Rehman, Khan, S. H., Abbas, Z., & Rizvi, S. D. (2024). Classification of Diabetic Retinopathy Images Based on Customised CNN Architecture. 2024 Amity International Conference on Artificial Intelligence (AICAI), 244–248.
Butt, M. M., Latif, G., Iskandar, D. N. F. A., Alghazo, J., & Khan, A. H. (2024). Multi-channel Convolutions Neural Network Based Diabetic Retinopathy Detection from Fundus Images. Procedia Computer Science, 163, 283–291.
Afrin, R., & Shill, P. C. (2024). Automatic Lesions Detection and Classification of Diabetic Retinopathy Using Fuzzy Logic. 2024 International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), 527–532.
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.
Chowdhury, A.R., Chatterjee, T. and Banerjee, S., 2024. A random forest classifier-based approach in the detection of abnormalities in the retina. Medical & biological engineering & computing, 57, pp.193-203.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
