Optimizing Convolutional Neural Networks with Nature-Inspired Algorithms for Diabetic Retinopathy Classification

  • Dr. Arunkumar Joshi Dept of CSE, SKSVMACET, Lakshmeshwar
  • Mr. Nagaraj Baradeli Dept of CSE, SKSVMACET, Lakshmeshwar
  • Dr. Arun Kumbi Dept of CSE, SKSVMACET, Lakshmeshwar
  • Dr. Vishruth B Gowda Dept of CSE, SKSVMACET, Lakshmeshwar
  • Dr. Vishruth B Gowda Dept of CSE, SKSVMACET, Lakshmeshwar
Keywords: Diabetic retinopathy detection, vision impairment, early diagnosis, machine learning techniques, medical image processing, nature-inspired optimization, convolutional neural networks, particle swarm optimization, fundus image classification, automated screening systems, deep learning models, clinical evaluation.

Abstract

Diabetic Retinopathy (DR) is a progressive eye disorder caused by prolonged diabetes and is recognized as one of the leading causes of vision impairment and blindness worldwide. The disease affects the small blood vessels of the retina, resulting in structural damage that gradually deteriorates visual capability. Early detection and continuous monitoring of DR are essential to prevent severe complications and permanent vision loss. However, manual examination of retinal fundus images by ophthalmologists is time-consuming and requires significant expertise, especially when dealing with large-scale screening programs. Consequently, automated diagnostic systems based on artificial intelligence have gained considerable attention in recent years. Advancements in medical imaging and machine learning have enabled the development of intelligent models capable of detecting retinal abnormalities with high precision. The classification of DR severity levels from digital fundus images. To further enhance the performance of the CNN model, Nature-Inspired Algorithms (NIAs) are incorporated as optimization techniques. These algorithms mimic natural evolutionary and behavioral processes to improve model parameters and learning efficiency. Several NIAs are investigated in order to identify the most effective optimization strategy for improving classification performance. 

Among the evaluated approaches, Particle Swarm Optimization (PSO) demonstrated superior capability in optimizing the CNN architecture by effectively adjusting network parameters and improving feature learning. The proposed hybrid CNN–PSO model achieved an overall classification accuracy of 98.83%, outperforming several existing state-of-the-art methods reported in the literature. The results highlight the effectiveness of integrating nature-inspired optimization strategies with deep learning frameworks for medical image analysis. This approach offers a reliable and efficient solution for automated DR screening and can significantly support ophthalmologists in early diagnosis and clinical decision-making.

References

[1] Harry Pratta,, Frans Coenenb, Deborah M Broadbentc, Simon P Hardinga,c, Yalin Zhenga, Convolutional Neural Networks for Diabetic Retinopathy, International Conference On Medical Imaging Understanding and Analysis 2016, MIUA 2016,6-8 July 2016, Loughborough, UK
[2] Chazhoor, A.; Sarobin, V.R. Intelligent automation of invoice parsing using computer vision techniques. Multimed. Tools Appl. 2022, 81, 29383–29403
[3] Sanket, S.; Vergin Raja Sarobin, M.; Jani Anbarasi, L.; Thakor, J.; Singh, U. Narayanan, S. Detection of novel coronavirus from chest Xrays using deep convolutional neural networks. Multimed. Tools Appl. 2022, 81, 22263–22288
[4] Kumar, S.L. Predictive Analytics of COVID-19 Pandemic: Statistical Modelling Perspective. Walailak J. Sci. Technol. (WJST) 2021, 18, 15583
[5] Oh, E.; Yoo, T.K.; Park, E.-C. Diabetic retinopathy risk prediction for fundus examination using sparse learning: A cross-sectional study. BMC Med. Inform. Decis. Mak. 2013, 13, 106
[6] Ogunyemi, O.; Kermah, D. Machine Learning Approaches for Detecting Diabetic Retinopathy from Clinical and Public Health Records. AMIA Annu. Symp. Proc. 2015, 2015, 983–990
[7] Ogunyemi, O.I.; Gandhi, M.; Tayek, C. Predictive Models for Diabetic Retinopathy from Non-Image Teleretinal Screening Data. AMIA Jt. Summits Transl. Sci. Proc. 2019, 2019, 472–477
[8] Tsao, H.-Y.; Chan, P.-Y.; Su, E.C.-Y. Predicting diabetic retinopathy and identifying interpretable biomedical features using machine learning algorithms. BMC Bioinform. 2018, 19, 283
[9] Anan Banharnsakun, Kasetsart University (Sriracha Campus), Chonburi, Thailand, Towards improving the convolutional neural networks for deep learning using the distributed artificial bee colony method, June 2019, International Journal of Machine Learning and Cybernetics 10(6)
[10] Yadav, J.; Sharma, M.; Saxena, V. Diabetic retinopathy detection using feedforward neural network. In Proceedings of the Tenth International Conference on Contemporary Computing (IC3), Noida, India, 10–12 August 2017; pp. 1–3
[11] Gadekallu, T.R.; Khare, N.; Bhattacharya, S.; Singh, S.; Maddikunta, P.K.R.; Srivastava, G. Deep neural networks to predict diabetic retinopathy. J. Ambient. Intell. Humaniz.Comput. 2020
[12] Sarki, R, Michalska, S, Ahmed, K, Wang, H, Zhang, Y (2019) Convolutional neural networks for mild diabetic retinopathy detection: an experimental study, bioRxiv, pp.1–18 10.1101/763136
[13] Abdel Maksoud, E.; Barakat, S.; Elmogy, M. Diabetic Retinopathy Grading Based on a Hybrid Deep Learning Model. In Proceedings of the International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), Sakheer,
Bahrain, 26–27 October 2020; pp. 1
[14] Jiang, H.; Yang, K.; Gao, M.; Zhang, D.; Ma, H.; Qian, W. An Interpretable Ensemble Deep Learning Model for Diabetic Retinopathy Disease Classification. In Proceedings of the 41st Annual International
Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 23–27 July 2019; pp. 2045–2048
[15] Amalia, R.; Bustamam, A.; Sarwinda, D. Detection and description generation of diabetic retinopathy using convolutional neural network and long short-term memory. J. Phys. Conf. Ser. 2021, 1722, 12010.
[16] M. A. Habib Raj, M. A. Mamun and M. F. Faruk, "CNN Based Diabetic Retinopathy Status Prediction Using Fundus Images," 2020 IEEE Region 10 Symposium (TENSYMP), Dhaka, Bangladesh, 2020, pp. 190-193, doi: 10.1109/TENSYMP50017.2020.9230974.
[17] U. B. Mahadevaswamy and H. T, "Adaptive Prediction and Classification of Diabetic Retinopathy Using Machine Learning," 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon),
Mysuru, India, 2022, pp. 1-7, doi:
10.1109/MysuruCon55714.2022.9972593
[18] Ghadah Alwakid, Walaa Gouda, […], and Noor Zaman Jhanjhi , Deep learning-enhanced diabetic retinopathy image classification, Aug 2023, https://doi.org/10.1177/20552076231194942
[19] Spoorthi K V, Rekha B S, Diabetic Retinopathy Prediction using Deep learning, 2021 IEEE International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS), DOI:10.1109/CSITSS54238.2021.9683553

[20] Ali Karsaz,A modified convolutional neural network architecture for diabetic retinopathy screening using SVDD,Applied Soft
Computing,Volume 125,2022,109102,ISSN 1568
4946,https://doi.org/10.1016/j.asoc.2022.109102
[21] R., Y.; Raja Sarobin M., V.;Panjanathan, R.; S., G.J.; L., J.A.Diabetic Retinopathy ClassificationUsing CNN and Hybrid Deep Convolutional
Neural Networks.Symmetry 2022, 14, 1932.
https://doi.org/10.3390/sym14091932
[22] Gunasekaran, K., Pitchai, R., Chaitanya, G.K., Selvaraj, D., Annie Sheryl, S., Almoallim, H.S., Tesemma, B.G. (2022). A deep learning framework for earlier prediction of diabetic retinopathy from fundus photographs. BioMed Research International, 2022: Article ID 3163496. https://doi.org/10.1155/2022/3163496
[23] Melin, P., Sánchez, D., Cordero-Martínez, R. (2023). Particle Swarm Optimization of Convolutional Neural Networks for Diabetic
Retinopathy Classification. In: Castillo, O., Melin, P. (eds) Fuzzy Logic and Neural Networks for Hybrid Intelligent System Design. Studies in Computational Intelligence, vol 1061. Springer, Cham. https://doi.org/10.1007/978-3-031-22042-5_14
[24] Anan Banharnsakun, Towards improving the convolutional neural networks for deep learning using the distributed artificial bee colony method, June 2019, International Journal of Machine Learning and
Cybernetics 10(6), DOI:10.1007/s13042-018-0811-z
Published
2026-04-19
How to Cite
Joshi, D. A., Baradeli, M. N., Kumbi, D. A., Gowda, D. V. B., & Gowda, D. V. B. (2026). Optimizing Convolutional Neural Networks with Nature-Inspired Algorithms for Diabetic Retinopathy Classification. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 12(1), 65-71. Retrieved from https://www.asianssr.org/index.php/ajct/article/view/1506

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.