ADVANCEMENTS IN AI-DRIVEN DIABETIC RETINOPATHY DETECTION: A SYSTEMATIC SURVEY DIRECTIONS

(Received: 25-Mar.-2026, Revised: 31-May-2026 and 22-Jun.-2026 , Accepted: 30-Jun.-2026)

Authors Yasser A. Ali, Ahmed Z. Emam, Muhammed H. Zayyan, Samir Elmougy, Ahmed S. Tolba,

Keywords #Diabetic Retinopathy #Automated Disease Screening #Deep Learning #Artificial Intelligence #Fundus Imaging #Explainable AI #Vision Transformers #Domain Adaptation #Class Imbalance

Abstract Diabetic retinopathy (DR) is a leading cause of preventable vision impairment, requiring scalable and reliable screening solutions. Artificial intelligence (AI), particularly machine learning and deep learning, has significantly advanced the automation of DR classification from retinal fundus images. This paper presents a systematic review of AI-based DR classification approaches, focusing on binary classification, multi-class severity grading and lesion-based methods and introduces a taxonomy based on their clinical objectives. The review covers state-of- the-art models, including convolutional neural networks, vision transformers, attention mechanisms and ensemble techniques, as well as their pre-processing strategies and evaluation protocols. Common benchmark datasets are analyzed in terms of class distribution and their impact on performance. While current models achieve high accuracy on standard datasets, challenges remain in generalization, class imbalance and reliable detection of early-stage DR. Lesion-based approaches improve interpretability, but are often not fully integrated into grading frameworks. Overall, this review highlights key limitations and outlines future directions toward developing robust, interpretable and clinically deployable DR classification systems for real-world screening.

References

[1] M. C. S. Tang, S. S. Teoh, H. Ibrahim and Z. Embong, "A Deep Learning Approach for the Detection of Neovascularization in Fundus Images Using Transfer Learning," IEEE Access, vol. 10, pp. 20247–20258, DOI: 10.1109/ACCESS.2022.3151644, 2022.

[2] Md. Nur-A-Alam, Md. M. K. Nasir, M. Ahsan, Md. A. Based, J. Haider and S. Palani, "A Faster RCNN-based Diabetic Retinopathy Detection Method Using Fused Features From Retina Images," IEEE Access, vol. 11, pp. 124331–124349, DOI: 10.1109/ACCESS.2023.3330104, 2023.

[3] M. M. Farag, M. Fouad and A. T. Abdel-Hamid, "Automatic Severity Classification of Diabetic Retinopathy Based on DenseNet and Convolutional Block Attention Module," IEEE Access, vol. 10, pp. 38299–38308, DOI: 10.1109/ACCESS.2022.3165193, 2022.

[4] G. Ali, A. Dastgir, M. W. Iqbal, M. Anwar and M. Faheem, "A Hybrid Convolutional Neural Network Model for Automatic Diabetic Retinopathy Classification From Fundus Images," IEEE J. of Translational Engineering in Health and Medicine, vol. 11, pp. 341–350, DOI: 10.1109/JTEHM.2023.3282104, 2023.

[5] M. Shafiq, Q. Fan, F. H. Alghamedy and W. J. Obidallah, "DualEye-FeatureNet: A Dual-stream Feature Transfer Framework for Multi-modal Ophthalmic Image Classification," IEEE Access, vol. 12, pp. 143985–144008, DOI: 10.1109/ACCESS.2024.3469244, 2024.

[6] M. N. Hasan, M. E. R. Pial, S. Das, N. Siddique and H. Wang, "DIA-VXNET: A Framework for Automated Diabetic Eye Disease Detection Using Transfer Learning with Feature Fusion Network," Biomedical Signal Processing and Control, vol. 100, p. 106907, Feb. 2025.

[7] M. A. K. Raiaan et al., "A Lightweight Robust Deep Learning Model Gained High Accuracy in Classifying a Wide Range of Diabetic Retinopathy Images," IEEE Access, vol. 11, pp. 42361–42388, DOI: 10.1109/ACCESS.2023.3272228, 2023.

[8] W. K. Wong, F. H. Juwono and C. Apriono, "Diabetic Retinopathy Detection and Grading: A Transfer Learning Approach Using Simultaneous Parameter Optimization and Feature-weighted ECOC Ensemble," IEEE Access, vol. 11, pp. 83004–83016, DOI: 10.1109/ACCESS.2023.3301618, 2023.

[9] T. Palaniswamy and M. Vellingiri, "Internet of Things and Deep Learning Enabled Diabetic Retinopathy Diagnosis Using Retinal Fundus Images," IEEE Access, vol. 11, pp. 27590–27601, 2023.

[10] M. Nawal Sad-Houari Hicham Reguieg, Chaimaa Bachiri, "Automated Diabetes Disease Prediction System Based on Risk Factors Assessment: Taking Charge of Your Health," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 09, no. 04, pp. 377–394, DOI: 10.5455/jjcit.71-1694107771, 2023.

[11] F. C. Monteiro, "Diabetic Retinopathy Grading Using Blended Deep Learning," Procedia Computer Science, vol. 219, pp. 1097–1104, DOI: 10.1016/j.procs.2023.01.389, 2022.

[12] B. N. Jagadesh, M. G. Karthik, D. Siri, S. K. K. Shareef, S. V. Mantena and R. Vatambeti, "Segmentation Using the IC2T Model and Classification of Diabetic Retinopathy Using the Rock Hyrax Swarm-based Coordination Attention Mechanism," IEEE Access, vol. 11, pp. 124441–124458, DOI: 10.1109/ACCESS.2023.3330436, 2023.

[13] S. Samira Ait Kaci Azzou, D. Boukredera and S. Baouz, "A Hybrid CNN-Transformer Approach for Precise Three-class Diabetic Retinopathy Classification," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 11, no. 03, pp. 279–299, DOI: 10.5455/jjcit.71-1738691198, 2025.

[14] Q. Abbas, M. E. A. Ibrahim and A. R. Baig, "Transfer Learning-based Computer-aided Diagnosis System for Predicting Grades of Diabetic Retinopathy," Computers, Materials & Continua, vol. 71, no. 3, pp. 4573–4590, doi: 10.32604/cmc.2022.023670, Jan. 2022.

[15] M. S. Patil, S. Chickerur, C. Abhimalya, A. Naik, N. Kumari and S. Maurya, "Effective Deep Learning Data Augmentation Techniques for Diabetic Retinopathy Classification," Proc. of the Int. Conf. on Machine Learning and Data Engineering, vol. 218, pp. 1156–1165, Jan. 2023.

[16] W. Nazih, A. O. Aseeri, O. Y. Atallah and S. El-Sappagh, "Vision Transformer Model for Predicting the Severity of Diabetic Retinopathy in Fundus Photography-based Retina Images," IEEE Access, vol. 11, pp. 117546–117561, DOI: 10.1109/ACCESS.2023.3326528, 2023.

[17] M. H. Ashraf and H. Alghamdi, "HFF-Net: A Hybrid Convolutional Neural Network for Diabetic Retinopathy Screening and Grading," Biomedical Technology, vol. 8, pp. 50–64, Dec. 2024.

[18] D. Shi et al., "Translation of Color Fundus Photography into Fluorescein Angiography Using Deep Learning for Enhanced Diabetic Retinopathy Screening," Ophthalmology Science, vol. 3, no. 4, p. 100401, Dec. 2023.

[19] S. H. Abbood, H. N. A. Hamed, M. S. M. Rahim, A. Rehman, T. Saba and S. A. Bahaj, "Hybrid Retinal Image Enhancement Algorithm for Diabetic Retinopathy Diagnostic Using Deep Learning Model," IEEE Access, vol. 10, pp. 73079–73086, DOI: 10.1109/ACCESS.2022.3189374, 2022.

[20] S. Sundar and S. Sumathy, "Classification of Diabetic Retinopathy Disease Levels by Extracting Topological Features Using Graph Neural Networks," IEEE Access, vol. 11, pp. 51435–51444, DOI: 10.1109/ACCESS.2023.3279393, 2023.

[21] V. Deepa, C. S. Kumar and T. Cherian, "Ensemble of Multi-stage Deep Convolutional Neural Networks for Automated Grading of Diabetic Retinopathy Using Image Patches," J. of King Saud Uni. - Computer and Information Sciences, vol. 34, no. 8, Part B, pp. 6255–6265, Sep. 2022.

[22] M. Murugappan, N. B. Prakash, R. Jeya, A. Mohanarathinam, G. R. Hemalakshmi and M. Mahmud, "A Novel Few-shot Classification Framework for Diabetic Retinopathy Detection and Grading," Measurement, vol. 200, p. 111485, DOI: 10.1016/j.measurement.2022.111485, Aug. 2022.

[23] J. Amin, I. Shazadi, M. Sharif, M. Yasmin, N. A. Almujally and Y. Nam, "Localization and Grading of NPDR Lesions Using ResNet-18-YOLOv8 Model and Informative Features Selection for DR Classification Based on Transfer Learning," Heliyon, vol. 10, no. 10, p. e30954, May 2024.

[24] K. Aurangzeb, R. S. Alharthi, S. I. Haider and M. Alhussein, "Systematic Development of AI-enabled Diagnostic Systems for Glaucoma and Diabetic Retinopathy," IEEE Access, vol. 11, pp. 105069–105081, DOI: 10.1109/ACCESS.2023.3317348, 2023.

[25] 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," Computers in Biology and Medicine, vol. 174, p. 108428, May 2024.

[26] C. P. Wilkinson et al., "Proposed International Clinical Diabetic Retinopathy and Diabetic Macular Edema Disease Severity Scales," Ophthalmology, vol. 110, no. 9, pp. 1677–1682, Sep. 2003.

[27] J. Hu, H. Wang, L. Wang and Y. Lu, "Graph Adversarial Transfer Learning for Diabetic Retinopathy Classification," IEEE Access, vol. 10, pp. 119071–119083, DOI: 10.1109/ACCESS.2022.3220776, 2022.

[28] T. F. de Sousa and C. G. Camilo, "HDeep: Hierarchical Deep Learning Combination for Detection of Diabetic Retinopathy," Proc. of the Int. Neural Network Society Workshop on Deep Learning Innovations and Applications (INNS DLIA 2023), vol. 222, pp. 425–434, Jan. 2023.

[29] P. Zhang et al., "Image Quality Assessment of Diabetic Retinopathy Based on ADD-Net," IEEE Access, vol. 11, pp. 105130–105139, DOI: 10.1109/ACCESS.2023.3318876, 2023.

[30] S. Pavithra, D. Jaladi and K. Tamilarasi, "Optical Imaging for Diabetic Retinopathy Diagnosis and Detection Using Ensemble Models," Photodiagnosis and Photodynamic Therapy, vol. 48, p. 104259, Aug. 2024.

[31] Á. S. Hervella, J. Rouco, J. Novo and M. Ortega, "Multimodal Image Encoding Pre-training for Diabetic Retinopathy Grading," Computers in Biology and Medicine, vol. 143, p. 105302, Apr. 2022.

[32] G. Bogacsovics, J. Toth, A. Hajdu and B. Harangi, "Enhancing CNNs through the Use of Hand-crafted Features in Automated Fundus Image Classification," Biomedical Signal Processing and Control, vol. 76, p. 103685, DOI: 10.1016/j.bspc.2022.103685, Jul. 2022.

[33] T. R. Athira and J. J. Nair, "Diabetic Retinopathy Grading From Color Fundus Images: An Autotuned Deep Learning Approach," Proc. of the Int. Conf. on Machine Learning and Data Engineering, vol. 218, pp. 1055–1066, DOI: 10.1016/j.procs.2023.01.085, Jan. 2023.

[34] T. M. Usman, Y. K. Saheed, D. Ignace and A. Nsang, "Diabetic Retinopathy Detection Using Principal Component Analysis Multi-label Feature Extraction and Classification," Int. J. of Cognitive Computing in Eng., vol. 4, pp. 78–88, DOI: 10.1016/j.ijcce.2023.02.002, Jun. 2023.

[35] M. A. I. Mahmood, N. Aktar and Md. F. Kader, "A Hybrid Approach for Diagnosing Diabetic Retinopathy from Fundus Image Exploiting Deep Features," Heliyon, vol. 9, no. 9, p. e19625, Sep. 2023.

[36] A. Mishra, M. Pandey and L. Singh, "Segmentation and Classification of Diabetic Retinopathy Using Ensemble Deep Neural Network," Proc. of the 5th Int. Conf. on Innovative Data Communication Technologies and Application (ICIDCA 2024), vol. 233, pp. 226–234, DOI: 10.1016/j.procs.2024.03.212, Jan. 2024.

[37] S. Khalid, H. A. Rashwan, S. Abdulwahab, M. Abdel-Nasser, F. M. Quiroga and D. Puig, "FGR-Net: Interpretable Fundus Image Gradeability Classification Based on Deep Reconstruction Learning," Expert Systems with Applications, vol. 238, p. 121644, DOI: 10.1016/j.eswa.2023.121644, Mar. 2024.

[38] 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, 2024.

[39] Y. Liu, "Automatic Grading Diabetic Retinopathy in Color Fundus Image: Cascaded Hybrid Attention Network," Journal of Radiation Research and Applied Sciences, vol. 17, no. 4, p. 101160, Dec. 2024.Retinopathy Screening and Grading," Biomedical Technology, vol. 8, pp. 50–64, Dec. 2024.

[40] R. Romero-Oraá, M. Herrero-Tudela, M. I. López, R. Hornero and M. García, "Attention-based Deep Learning Framework for Automatic Fundus Image Processing to Aid in Diabetic Retinopathy Grading," Computer Methods and Programs in Biomedicine, vol. 249, p. 108160, Jun. 2024.

[41] Z. Hai et al., "A Novel Approach for Intelligent Diagnosis and Grading of Diabetic Retinopathy," Computers in Biology and Medicine, vol. 172, p. 108246, Apr. 2024.

[42] H. Naz, T. Saba, F. S. Alamri, A. S. Almasoud and A. Rehman, "An Improved Robust Fuzzy Local Information K-means Clustering Algorithm for Diabetic Retinopathy Detection," IEEE Access, vol. 12, pp. 78611–78623, DOI: 10.1109/ACCESS.2024.3392032, 2024.

[43] S. K. Henge, N. R. Viraati, M. Alhussein, A. S. Kushwaha, K. Aurangzeb and R. Singh, "Detection of Diabetic Retinopathy Using a Multi-decision Inception-ResNet-blended Hybrid Model," IEEE Access, vol. 13, pp. 8988–9005, DOI: 10.1109/ACCESS.2024.3525154, 2025.

[44] A. Zedadra, O. Zedadra, M. Yassine Salah-Salah and A. Guerrieri, "Graph-aware Multimodal Deep Learning for Classification of Diabetic Retinopathy Images," IEEE Access, vol. 13, pp. 74799–74810, 2025.

[45] A. Ikram and A. Imran, "Fundus Imaging Based Quantum Computing: Grading of Severity of Vision Threatening Diabetic Retinopathy," Informatics in Medicine Unlocked, vol. 61, p. 101744, DOI: 10.1016/j.imu.2026.101744, Mar. 2026.

[46] J. Jaskari et al., "Uncertainty-aware Deep Learning Methods for Robust Diabetic Retinopathy Classification," IEEE Access, vol. 10, pp. 76669–76681, DOI: 10.1109/ACCESS.2022.3192024, 2022.

[47] M. D. Alahmadi, "Texture Attention Network for Diabetic Retinopathy Classification," IEEE Access, vol. 10, pp. 55522–55532, DOI: 10.1109/ACCESS.2022.3177651, 2022.

[48] M. R. Islam et al., "Applying Supervised Contrastive Learning for The Detection of Diabetic Retinopathy and Its Severity Levels from Fundus Images," Computers in Biology and Medicine, vol. 146, p. 105602, DOI: 10.1016/j.compbiomed.2022.105602, Jul. 2022.

[49] M. Tian, H. Wang, Y. Sun, S. Wu, Q. Tang and M. Zhang, "Fine-grained Attention & Knowledge-based Collaborative Network for Diabetic Retinopathy Grading," Heliyon, vol. 9, no. 7, p. e17217, Jul. 2023.

[50] S. S. Mohammadi and Q. D. Nguyen, "A User-friendly Approach for the Diagnosis of Diabetic Retinopathy Using ChatGPT and Automated Machine Learning," Ophthalmology Science, vol. 4, no. 4, p. 100495, 2024.

[51] M. S. B. Phridviraj, R. Bhukya, S. Madugula, A. Manjula, S. Vodithala and M. S. Waseem, "A Bi-directional Long Short-term Memory-based Diabetic Retinopathy Detection Model Using Retinal Fundus Images," Healthcare Analysis, vol. 3, p. 100174, DOI: 10.1016/j.health.2023.100174, Nov. 2023.

[52] Y. Yang, Z. Cai, S. Qiu and P. Xu, "A Novel Transformer Model with Multiple Instance Learning for Diabetic Retinopathy Classification," IEEE Access, vol. 12, pp. 6768–6776, 2024.

[53] C. Lam, C. Yu, L. Huang and D. Rubin, "Retinal Lesion Detection with Deep Learning Using Image Patches," Investigative Ophthalmology & Visual Science, vol. 59, no. 1, p. 590, Jan. 2018.

[54] P. Khojasteh, B. Aliahmad and D. K. Kumar, "Fundus Images Analysis Using Deep Features for Detection of Exudates, Hemorrhages and Microaneurysms," BMC Ophthalmology, vol. 18, no. 1, p. 288, Dec. 2018.

[55] T. Aziz, C. Charoenlarpnopparut and S. Mahapakulchai, "Deep Learning-based Hemorrhage Detection for Diabetic Retinopathy Screening," Scientific Reports, vol. 13, no. 1, p. 1479, Jan. 2023.

[56] D. Singh and D. C. Dobhal, "A Deep Learning-based Transfer Learning Approach Fine-tuned for Detecting Diabetic Retinopathy," Proc. of the 5th Int. Conf. on Innovative Data Communication Technologies and Application (ICIDCA 2024), vol. 233, pp. 444–453, DOI: 10.1016/j.procs.2024.03.234, Jan. 2024.

[57] E. Decencière et al., "Feedback on a Publicly Distributed Image Database: The Messidor Database," Image Analysis & Stereology, vol. 33, no. 3, Art. no. 3, DOI: 10.5566/ias.1155, Aug. 2014.

[58] Emma Dugas, Jared, Jorge and Will Cukierski, "Diabetic Retinopathy Detection," Diabetic Retinopathy Detection, [Online], Available: https://kaggle.com/diabetic-retinopathy-detection, Accessed: Dec. 14, 2024.

[59] G. P. Maffre Gervais Gauthier et al., "Messidor-2," ADCIS, [Online], Available: https://www.adcis.net/en/third-party/messidor2/, Accessed: Dec. 14, 2024.

[60] E. Decencière et al., "TeleOphta: Machine Learning and Image Processing Methods for Teleophthalmology," ANR TECSAN - Technologies for Health and Autonomy, vol. 34, no. 2, pp. 196–203, DOI: 10.1016/j.irbm.2013.01.010, Apr. 2013.

[61] P. Prentašić et al., "Diabetic Retinopathy Image Database (DRiDB): A New Database for Diabetic Retinopathy Screening Programs Research," Proc. of the 2013 8th Int. Symposium on Image and Signal Processing and Analysis (ISPA), pp. 711–716, DOI: 10.1109/ISPA.2013.6703830, 2013.

[62] S. P. Prasanna Porwal, "Indian Diabetic Retinopathy Image Dataset (IDRiD)," IEEE DataPort, DOI: 10.21227/H25W98, 2018.

[63] M. Karthik and S. Dane, "APTOS 2019 Blindness Detection," [Online], Available: https://kaggle.com/aptos2019-blindness-detection, Accessed: Dec. 14, 2024.

[64] T. Li, Y. Gao, K. Wang, S. Guo, H. Liu and H. Kang, "Diagnostic Assessment of Deep Learning Algorithms for Diabetic Retinopathy Screening," Information ScienceS, vol. 501, pp. 511–522, DOI: https://doi.org/10.1016/j.ins.2019.06.011, 2019.

[65] Y. Zhou, B. Wang, L. Huang, S. Cui and L. Shao, "A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading and Transferability," IEEE Transactions on Medical Imaging, vol. 40, no. 3, pp. 818–828, DOI: 10.1109/TMI.2020.3037771, Mar. 2021.

[66] T. Kauppi et al., "DIARETDB1 Diabetic Retinopathy Database and Evaluation Protocol," [Online], Available: https://webpages.tuni.fi/vision/public_data/publications/bmvc2007_diaretdb1.pdf, 2007.