International Journal of Modern Engineering and Management

Deep Convolutional Neural Network Architectures for Automated Diabetic Retinopathy Grading from Fundus Retinal Images: A Comparative Performance Analysis

Author(s):

Ananya Singh, Vikram Rao Desai, Neeraj Tiwari

Affiliation: Department of Computer Science and Engineering, Uttar Pradesh Technical University Regional Campus, Lucknow, Uttar Pradesh Department of Information Technology, Madan Mohan Malaviya University of Technology, Gorakhpur, Uttar Pradesh

Page No: 38-42-

Volume issue & Publishing Year: Volume 3, Issue 5, 2026/05/10

Journal: International Journal of Modern Engineering and Management | IJMEM

ISSN NO: 3048-8230

DOI: https://doi.org/10.5281/zenodo.20426522

Download PDF Cite this article

Abstract:

Diabetic retinopathy (DR) is the leading cause of preventable blindness in working-age adults globally, affecting an estimated 93 million people worldwide, with India bearing the second-largest absolute burden due to its 77-million-strong diabetic population. Early-stage DR is asymptomatic, making systematic screening of the diabetic population essential for timely intervention. This paper presents a comparative evaluation of four deep learning architectures — a custom 7-layer CNN, VGG-16, ResNet-50, and EfficientNet-B0 — for automated five-class DR grading (No DR, Mild, Moderate, Severe, Proliferative DR) on a 10,000-image fundus dataset curated from three district hospital ophthalmology units in Lucknow and Raipur. Transfer learning with ImageNet pre-training, class-weighted focal loss to address the 8:1 class imbalance between No DR and Proliferative DR, and extensive data augmentation (rotation, horizontal flip, CLAHE contrast enhancement) were applied uniformly across architectures for fair comparison. ResNet-50 achieved the highest test accuracy of 96.8% and macro-averaged F1-score of 95.9%, with AUC of 0.97 on the ROC curve. EfficientNet-B0 showed competitive performance (accuracy 95.4%) with 40% fewer parameters. A confusion matrix analysis reveals that the most clinically significant misclassification — Severe DR predicted as Moderate (false negative rate 8.1%) — warrants human-in-the-loop verification for grades 2–3. The study demonstrates the feasibility of automated DR screening deployment on hospital-grade computing infrastructure in resource-limited settings.

Keywords:

diabetic retinopathy, deep learning, convolutional neural network, ResNet-50, fundus image, transfer learning, medical image classification, ophthalmology screening

Reference:

• [1] Abramoff, M. D., Lavin, P. T., Birch, M., Shah, N., & Folk, J. C. (2018). Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy. NPJ Digital Medicine, 1, 39.

• [2] Acharya, U. R., et al. (2009). Computer-based detection of diabetes retinopathy stages using digital fundus images. Proceedings of the Institution of Mechanical Engineers, Part H, 223(5), 545–553.

• [3] Decenciere, E., et al. (2014). Feedback on a publicly distributed image database: The Messidor database. Image Analysis & Stereology, 33(3), 231–234.

• [4] Gulshan, V., et al. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 316(22), 2402–2410.

• [5] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of CVPR, 770–778.

• [6] International Diabetes Federation (2021). IDF Diabetes Atlas, 10th Edition. Brussels: IDF.

• [7] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097–1105.

• [8] Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. Proceedings of ICCV, 2980–2988.

• [9] Raman, R., et al. (2019). Fundus photograph-based deep learning algorithms in detecting DR. Eye, 33, 97–109.

• [10] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556.

• [11] Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of ICML, 6105–6114.

• [12] Tymchenko, B., Marchenko, P., & Spodarets, D. (2020). Deep learning approach to diabetic retinopathy detection. arXiv:2003.02261.

• [13] World Health Organization (2019). World Report on Vision. Geneva: WHO.