Enhanced Diabetic Retinopathy Identification via EfficientNetB3-Based Convolutional Neural Networks and Transfer Learning
DOI:
https://doi.org/10.3991/ijoe.v22i05.59075Keywords:
Computer vision, classification, CNN, diabetic retinopathyAbstract
Diabetic retinopathy (DR) is one of the most common causes of blindness worldwide, making early detection essential for treating this disease. This research presents the creation and testing of a convolutional neural network (CNN) model based on the EfficientNetB3 architecture to detect signs of DR in typical fundus images. The model was trained with a set of retinal images and tested using metrics such as accuracy, recall, and F1 score. The results show a weighted accuracy of 81%, with high performance in the healthy class (97% accuracy and 98% recall). However, lower accuracy is observed in the advanced stages of DR, mainly attributed to class imbalance in the dataset. It is also necessary to balance the classes and combine the architecture with other models. These findings demonstrate the potential of EfficientNetB3 as a diagnostic support tool and highlight the need to improve data balance and the model for better discrimination of severe cases.
References
[1] O. Iparraguirre-Villanueva, K. Espinola-Linares, R. O. Flores Castañeda, and M. Cabanillas-Carbonell, “Application of Machine Learning Models for Early Detection and Accurate Classification of Type 2 Diabetes,” Diagnostics 2023, Vol. 13, Page 2383, vol. 13, no. 14, p. 2383, Jul. 2023, doi: https://doi.org/10.3390/DIAGNOSTICS13142383.
[2] M. A. dos Reis et al., “Advancing healthcare with artificial intelligence: diagnostic accuracy of machine learning algorithm in diagnosis of diabetic retinopathy in the Brazilian population,” Diabetology and Metabolic Syndrome , vol. 16, no. 1, p. 209, Dec. 2024, doi: https://doi.org/10.1186/s13098-024-01447-0.
[3] IDF, “Diabetes around the world.” Accessed: Sep. 23, 2024. [Online]. Available: https://diabetesatlas.org/
[4] WHO, “World Health Organization (WHO).” Accessed: Sep. 23, 2024. [Online]. Available: https://www.who.int/europe/activities/promoting-diabetic-retinopathy-screening
[5] Z. Liu et al., “Cost-effectiveness of incorporating self-imaging optical coherence tomography into fundus photography-based diabetic retinopathy screening,” Volume 7, Issue 1, vol. 7, no. 1, Jan. 225AD, doi: https://doi.org/10.1038/s41746-024-01222-5.
[6] A. M. Mutawa, K. Al-Sabti, S. Raizada, and S. Sruthi, “A Deep Learning Model for Detecting Diabetic Retinopathy Stages with Discrete Wavelet Transform,” Applied Sciences (Switzerland), vol. 14, no. 11, p. 4428, Jun. 2024, doi: https://doi.org/10.3390/app14114428.
[7] M. Saxena, P. Narra, M. Saxena, and R. Saxena, “Deep learning ensemble framework for multiclass diabetic retinopathy classification,” Telkomnika (Telecommunication Computing Electronics and Control), vol. 22, no. 3, pp. 665–672, Jun. 2024, doi: https://doi.org/10.12928/TELKOMNIKA.v22i3.25794.
[8] P. Kakati, S. G. Quek, G. Selvachandran, T. Senapati, and G. Chen, “Analysis and application of rectified complex t-spherical fuzzy Dombi-Choquet integral operators for diabetic retinopathy detection through fundus images,” Expert Syst Appl, vol. 243, p. 122724, Jun. 2024, doi: https://doi.org/10.1016/j.eswa.2023.122724.
[9] X. Xu, D. Liu, G. Huang, M. Wang, M. Lei, and Y. Jia, “Computer aided diagnosis of diabetic retinopathy based on multi-view joint learning,” Comput Biol Med, vol. 174, p. 108428, May 2024, doi: https://doi.org/10.1016/j.compbiomed.2024.108428.
[10] J. Tang et al., “TSNet: Task-specific network for joint diabetic retinopathy grading and lesion segmentation of ultra-wide optical coherence tomography angiography images,” Visual Computer, vol. 40, no. 9, pp. 5935–5946, Sep. 2024, doi: https://doi.org/10.1007/S00371-023-03145-W/METRICS.
[11] Z. Hai et al., “A novel approach for intelligent diagnosis and grading of diabetic retinopathy,” Comput Biol Med, vol. 172, p. 108246, Apr. 2024, doi: https://doi.org/10.1016/j.compbiomed.2024.108246.
[12] V. Guevara-Ponce, O. Roque-Paredes, C. Zerga-Morales, A. Flores-Huerta, M. Aymerich-Lau, and O. Iparraguirre-Villanueva, “Detection of Breast Cancer using Convolutional Neural Networks with Learning Transfer Mechanisms,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 6, pp. 574–580, Autumn 2023, doi: https://doi.org/10.14569/IJACSA.2023.0140661.
[13] M. V. Cicinelli et al., “Assessing Diabetic Retinopathy Staging With AI: A Comparative Analysis Between Pseudocolor and LED Imaging,” Volume 13, Issue 3, vol. 13, no. 3, Nov. 2001, doi: https://doi.org/10.1167/tvst.13.3.11.
[14] Z. Wang, S. Chen, T. Liu, and B. Yao, “Multi-Branching Temporal Convolutional Network With Tensor Data Completion for Diabetic Retinopathy Prediction,” Volume 28, Issue 3, Pages 1704 - 1715, vol. 28, no. 3, pp. 1704–1715, Mar. 2024, doi: https://doi.org/10.1109/JBHI.2024.3351949.
[15] X. N. Wang, Z. Guan, B. Qian, T. Chen, and Q. Wu, “A deep learning system for the detection of optic disc neovascularization in diabetic retinopathy using optical coherence tomography angiography images,” Visual Computer, pp. 1–10, May 2024, doi: https://doi.org/10.1007/S00371-024-03418-Y/METRICS.
[16] V. Thanikachalam, K. Kabilan, and S. K. Erramchetty, “Optimized deep CNN for detection and classification of diabetic retinopathy and diabetic macular edema,” BMC Med Imaging, vol. 24, no. 1, p. 227, Dec. 2024, doi: https://doi.org/10.1186/s12880-024-01406-1.
[17] P. K. Das and S. Pumrin, “Diabetic Retinopathy Classification: Performance Evaluation of Pre-trained Lightweight CNN using Imbalance Dataset,” Engineering Journal, vol. 28, no. 7, pp. 13–25, Jul. 2024, doi: https://doi.org/10.4186/ej.2024.28.7.13.
[18] K. Nazir, J. Kim, and Y. C. Byun, “Enhancing Early-Stage Diabetic Retinopathy Detection Using a Weighted Ensemble of Deep Neural Networks,” IEEE Access, vol. 12, pp. 113565–113579, Jan. 2024, doi: https://doi.org/10.1109/ACCESS.2024.3432867.
[19] M. Dhouibi, A. K. Ben Salem, A. Saidi, and S. Ben Saoud, “Acceleration of convolutional neural network based diabetic retinopathy diagnosis system on field programmable gate array,” International Journal of Informatics and Communication Technology, vol. 12, no. 3, pp. 214–224, Dec. 2023, doi: https://doi.org/10.11591/ijict.v12i3.pp214-224.
[20] D. Das, S. K. Biswas, and S. Bandyopadhyay, “Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification (DRFEC),” Multimed Tools Appl, vol. 82, no. 19, pp. 29943–30001, Aug. 2023, doi: https://doi.org/10.1007/s11042-022-14165-4.
[21] M. Nahiduzzaman et al., “Diabetic retinopathy identification using parallel convolutional neural network based feature extractor and ELM classifier,” Expert Syst Appl, vol. 217, p. 119557, May 2023, doi: https://doi.org/10.1016/j.eswa.2023.119557.
[22] E. Dhiravidachelvi, S. Senthil Pandi, R. Prabavathi, and C. Bala Subramanian, “Artificial Humming Bird Optimization–Based Hybrid CNN-RNN for Accurate Exudate Classification from Fundus Images,” J Digit Imaging, vol. 36, no. 1, pp. 59–72, Feb. 2023, doi: https://doi.org/10.1007/s10278-022-00707-7.
[23] A. O. Asia et al., “Detection of Diabetic Retinopathy in Retinal Fundus Images Using CNN Classification Models,” Electronics (Switzerland), vol. 11, no. 17, p. 2740, Sep. 2022, doi: https://doi.org/10.3390/electronics11172740.
[24] M. Li, Y. Jung, M. Fulham, and J. Kim, “Importance-aware 3D volume visualization for medical content-based image retrieval-a preliminary study,” Virtual Reality and Intelligent Hardware, vol. 6, no. 1, pp. 71–81, Feb. 2024, doi: https://doi.org/10.1016/j.vrih.2023.08.005.
[25] J. Li et al., “Integrated image-based deep learning and language models for primary diabetes care,” Nat Med, Oct. 2024, doi: https://doi.org/10.1038/s41591-024-03139-8.
[26] M. A. Guerroudji, K. Amara, M. Lichouri, N. Zenati, and M. Masmoudi, “A 3D visualization-based augmented reality application for brain tumor segmentation,” Comput Animat Virtual Worlds, vol. 35, no. 1, Jan. 2024, doi: https://doi.org/10.1002/cav.2223.
[27] L. Dai et al., “A deep learning system for detecting diabetic retinopathy across the disease spectrum,” Nat Commun, vol. 12, no. 1, Dec. 2021, doi: https://doi.org/10.1038/s41467-021-23458-5.
[28] R. Liu et al., “DeepDRiD: Diabetic Retinopathy—Grading and Image Quality Estimation Challenge,” Patterns, vol. 3, no. 6, Jun. 2022, doi: https://doi.org/10.1016/j.patter.2022.100512.
[29] V. Thanikachalam, K. Kabilan, and S. K. Erramchetty, “Optimized deep CNN for detection and classification of diabetic retinopathy and diabetic macular edema,” BMC Med Imaging, vol. 24, no. 1, p. 227, Dec. 2024, doi: https://doi.org/10.1186/s12880-024-01406-1.
[30] S. Liu, W. Wang, L. Deng, and H. Xu, “Cnn-trans model: A parallel dual-branch network for fundus image classification,” Biomed Signal Process Control, vol. 96, p. 106621, Oct. 2024, doi: https://doi.org/10.1016/j.bspc.2024.106621.
[31] M. Saxena, P. Narra, M. Saxena, and R. Saxena, “Deep learning ensemble framework for multiclass diabetic retinopathy classification,” Telkomnika (Telecommunication Computing Electronics and Control), vol. 22, no. 3, pp. 665–672, Jun. 2024, doi: https://doi.org/10.12928/TELKOMNIKA.v22i3.25794.
[32] J. Caicho et al., “Diabetic Retinopathy: Detection and Classification Using AlexNet, GoogleNet and ResNet50 Convolutional Neural Networks,” Communications in Computer and Information Science, vol. 1532 CCIS, pp. 259–271, 2022, doi: https://doi.org/10.1007/978-3-030-99170-8_19.
[33] F. M. J. Mehedi Shamrat et al., “An advanced deep neural network for fundus image analysis and enhancing diabetic retinopathy detection,” Healthcare Analytics, vol. 5, p. 100303, Jun. 2024, doi: https://doi.org/10.1016/j.health.2024.100303.
[34] Z. Hai et al., “A novel approach for intelligent diagnosis and grading of diabetic retinopathy,” Comput Biol Med, vol. 172, p. 108246, Apr. 2024, doi: https://doi.org/10.1016/j.compbiomed.2024.108246.
[35] C. X. Ling and C. Li, “Data Mining for Direct Marketing: Problems and”, Accessed: Oct. 11, 2024. [Online]. Available: www.aaai.org
[36] C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J Big Data, vol. 6, no. 1, pp. 1–48, Dec. 2019, doi: https://doi.org/10.1186/S40537-019-0197-0/FIGURES/33.
[37] R. Van Den Goorbergh, M. Van Smeden, D. Timmerman, and Ben Van Calster, “The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression,” Journal of the American Medical Informatics Association, vol. 29, no. 9, pp. 1525–1534, Aug. 2022, doi: https://doi.org/10.1093/JAMIA/OCAC093.
[38] Phani, “Introduction to Convolutional Neural Network - Analytics Vidhya.” Accessed: Oct. 10, 2024. [Online]. Available: https://www.analyticsvidhya.com/blog/2020/10/what-is-the-convolutional-neural-network-architecture/
[39] Y. Yang, Z. Cai, S. Qiu, and P. Xu, “Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image,” PLoS One, vol. 19, no. 3, p. e0299265, Mar. 2024, doi: https://doi.org/10.1371/journal.pone.0299265.
[40] P. Macsik, J. Pavlovicova, S. Kajan, J. Goga, and V. Kurilova, “Image preprocessing-based ensemble deep learning classification of diabetic retinopathy,” IET Image Process, vol. 18, no. 3, pp. 807–828, Feb. 2024, doi: https://doi.org/10.1049/ipr2.12987
.
[41] R. Gayathri, S. Karthikeyan, T. Kausheekraj, and S. Keerthana, “Diabetic Retinopathy Detection Using CNN With Res-LSTMDN,” Proceedings of the 2024 10th International Conference on Communication and Signal Processing, ICCSP 2024, pp. 254–259, Jan. 2024, doi: https://doi.org/10.1109/ICCSP60870.2024.10543841.
[42] Aryan, R. Chaudhuri, and S. Deb, “Precise lesion analysis to detect diabetic retinopathy using Generative Adversarial Network(GAN) and Mask-RCNN,” Procedia Comput Sci, vol. 235, pp. 520–529, Jan. 2024, doi: https://doi.org/10.1016/j.procs.2024.04.051.
[43] Sovit Ranjan Rath, “Diabetic Retinopathy 224x224 (2019 Data).” Accessed: Oct. 13, 2024. [Online]. Available: https://www.kaggle.com/datasets/sovitrath/diabetic-retinopathy-224x224-2019-data
[44] R. Gunawan, H. A. Ghani, N. Khamis, and H. F. adah Amran, “Imbalanced data handling in multiclass distributed denial of service attack detection using deep learning,” Telkomnika (Telecommunication Computing Electronics and Control), vol. 22, no. 6, pp. 1396–1404, Dec. 2024, doi: https://doi.org/10.12928/TELKOMNIKA.v22i6.26005.
[45] F. Muftic, M. Kadunic, A. Musinbegovic, A. A. Almisreb, and H. Jaafar, “Deep learning for magnetic resonance imaging brain tumor detection: evaluating ResNet, EfficientNet, and VGG-19,” International Journal of Electrical and Computer Engineering, vol. 14, no. 6, pp. 6360–6372, Dec. 2024, doi: https://doi.org/10.11591/ijece.v14i6.pp6360-6372.
[46] D. M. W. Powers and Ailab, “Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation,” Oct. 2020, Accessed: Oct. 17, 2024. [Online]. Available: https://arxiv.org/abs/2010.16061v1
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Orlando Iparraguirre-Villanueva, Michael Cabanillas-Carbonell
This work is licensed under a Creative Commons Attribution 4.0 International License.
