NONE 20260715104056644 wseas/wseas content-registration-form@crossref.org content-registration-form International Journal of Applied Mathematics Computational Science and Systems Engineering 2766-9823 Pooja A Department of Computer Science & Engineering Impact College Of Engineering & Applied Sciences, Affiliated by VTU Bangalore, INDIA Dhananjaya V Department of Computer Science & Engineering Impact College Of Engineering & Applied Sciences, Affiliated by VTU Bangalore, INDIA Diabetes is one of the increasing serious health issues, affecting millions of people. Consequently, the greater portion of individual is affected by diabetes, some of the related issues such as cardiovascular disease, kidney failure, nerve damage, foot problems and vision problems are growing rapidly. Diabetic retinopathy (DR) is a severe complication of diabetes and a leading cause of preventable blindness worldwide. Early detection requires expert evaluation of retinal fundus images, but limited access to specialists delays diagnosis. This work presents an automated DR screening pipeline using pertained Convolutional Neural Networks (CNNs), including VGG16, VGG19, and ResNet50, for five-class DR severity classification. Using 3,662 Kaggle fundus images with systematic preprocessing, augmentation, and class balancing, the proposed approach achieves a highest accuracy of 96.3% and F1-score of 0.898. The model supports improved early diagnosis by enabling scalable, automated retinal image screeningto enhance primary diagnosis and minimizes blindness risk. 07 15 2026 07 15 2026 72 6 https://creativecommons.org/licenses/by/4.0/deed.en_US 10.37394/232026.2026.8.6 https://wseas.com/journals/amcse/2026/a12amcse-006(2026).pdf Y. Yonekawa et al., “Management of Nonproliferative and Proliferative Diabetic Retinopathy without Diabetic Macular Edema,” Journal of Vitreoretinal Diseases, 2020. T. R. Gadekallu et al., “Early Detection of Diabetic Retinopathy Using PCA-Firefly Based Deep Learning Model,” Electronics, 2020. B. Tymchenko et al., “Deep Learning Approach to Diabetic Retinopathy Detection,” arXiv: 2003.02261. A. Samanta et al., “Automated detection of diabetic retinopathy using CNNs,” Pattern Recognition Letters, 2020. C. Bhardwaj et al., “Hierarchical severity of nonproliferative diabetic retinopathy,” Springer, 2020. P. Saranya et al., “Automatic detection of nonproliferative diabetic retinopathy in retinal fundus images,” Springer, 2020. M. S. Sallam et al., “Diabetic Retinopathy Grading Using ResNet CNN,” IEEE, 2020. P. Saranya et al., “Blood vessel segmentation in retinal fundus images,” Springer, 2021. I. Qureshi et al., “Diabetic retinopathy detection and stage classification,” Springer, 2020. S. Karki et al., “Diabetic Retinopathy Classification using EfficientNets,” IEEE, 2021. N. Al-Moosawi et al., “ResNet34/DR for Diagnosis of Diabetic Retinopathy,” 2021. M. Elsharkawy et al., “A Novel CAD System for Early DR Detection,” Diagnostics, 2022. B. Mounirou et al., “Diabetic Retinopathy: An Overview of Treatments,” Indian J. Endocrinol. Metab, 2022. R. Yazid et al., “Detection of Diabetic Retinopathy Using CNN,” 2021. C.-L. Lin et al., “Development of revised ResNet50 for DR detection,” 2021. C. Mohanty et al., “Deep Learning Architectures for DR Detection,” Sensors, 2023. S. Dinesen et al., “Five-Year Incidence of Proliferative DR,” 2023. G. Chondrozoumakis et al., “Retinal Biomarkers in Diabetic Retinopathy,” JCM, 2023.