RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading

Shahram Taheri; Zahra Golrizkhatami

doi:10.35377/saucis...1760380

RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading

Abstract

This study introduces RetinaNeXt, a deep learning model based on the ConvNeXt-Base architecture for grading the severity of diabetic retinopathy (DR) into five classes. The goal is to achieve robust, interpretable, and cross-dataset generalization using a scalable convolutional backbone. RetinaNeXt integrates transfer learning from pre-trained ConvNeXt, class balancing via Focal Loss, and extensive data augmentation. It is trained on the EyePACS dataset and externally validated on APTOS and IDRiD datasets. Grad-CAM visualizations are used to interpret the model’s focus on pathological regions. RetinaNeXt achieved 95.26% accuracy on EyePACS, 94.85% on APTOS, and 90.29% on IDRiD, demonstrating strong cross-domain generalization. Class-wise analysis revealed consistent performance across all ICDR grades, with improved sensitivity in minority classes, attributed to Focal Loss. The proposed RetinaNeXt framework combines architectural efficiency, interpretability, and generalization, making it suitable for real-world DR screening applications. Future work will explore lightweight deployment and integration with federated learning for privacy-preserving detection of DR.

Keywords

Project Number

1754818862198

References

B. Kurt, V. Nabiyev, and K. Turhan, “Medical images enhancement by using anisotropic filter and CLAHE,” in Proc. Int. Symp. Innov. Intell. Syst. Appl. (INISTA), Jul. 2012, pp. 1–4, doi: 10.1109/INISTA.2012.6246971.
A. Buslaev, V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. A. Kalinin, “Albumentations: Fast and flexible image augmentations,” Information, vol. 11, no. 2, Art. no. 125, Feb. 2020, doi: 10.3390/info11020125.
N. Cheung, P. Mitchell, and T. Y. Wong, “Diabetic retinopathy,” Lancet, vol. 376, no. 9735, pp. 124–136, Jul. 2010, doi: 10.1016/S0140-6736(09)62124-3.
M. Niemeijer, B. van Ginneken, and M. D. Abràmoff, “Automatic detection of the optic disc, fovea and vascular arch in digital color photographs of the retina,” in Proc. Brit. Mach. Vis. Conf. (BMVC), Sep. 2005.
A. Sopharak, B. Uyyanonvara, and S. Barman, “Automatic microaneurysm detection from non-dilated diabetic retinopathy retinal images using mathematical morphology methods,” IAENG Int. J. Comput. Sci., vol. 38, no. 3, 2011.
V. Gulshan et al., “Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs,” JAMA, vol. 316, no. 22, pp. 2402–2410, Dec. 2016, doi: 10.1001/jama.2016.17216.
H. Pratt, F. Coenen, D. M. Broadbent, S. P. Harding, and Y. Zheng, “Convolutional neural networks for diabetic retinopathy,” Procedia Comput. Sci., vol. 90, pp. 200–205, 2016, doi: 10.1016/j.procs.2016.07.014.
Z. Wang, Y. Yin, J. Shi, W. Fang, H. Li, and X. Wang, “Zoom-in-Net: Deep mining lesions for diabetic retinopathy detection,” in Proc. Med. Image Comput. Comput.-Assist. Interv. (MICCAI), 2017, pp. 267–275, doi: 10.1007/978-3-319-66179-7_31.

A. He, T. Li, N. Li, K. Wang, and H. Fu, “CABNet: Category attention block for imbalanced diabetic retinopathy grading,” IEEE Trans. Med. Imaging, vol. 40, no. 1, pp. 143–153, Jan. 2021, doi: 10.1109/TMI.2020.3023463.
M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. Int. Conf. Mach. Learn. (ICML), May 2019, pp. 6105–6114.
Z. Liu et al., “Swin transformer: Hierarchical vision transformer using shifted windows,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2021, pp. 10012–10022, doi: 10.48550/arXiv.2103.14030.
S. Almas, F. Wahid, S. Ali, A. Alkhayyat, K. Ullah, J. Khan, and Y. Lee, “Visual impairment prevention by early detection of diabetic retinopathy based on a stacked auto-encoder,” Sci. Rep., vol. 15, Art. no. 16609, May 2025, doi: 10.1038/s41598-025-85752-2.
V. D. Vinayaki and R. Kalaiselvi, “Multithreshold image segmentation technique using remora optimization algorithm for diabetic retinopathy detection from fundus images,” Neural Process. Lett., vol. 54, no. 3, pp. 2363–2384, Sep. 2022, doi: 10.1007/s11063-021-10734-0.
A. Erciyas, N. Barışçı, H. M. Ünver, and H. Polat, “Improving detection and classification of diabetic retinopathy using CUDA and Mask RCNN,” Signal Image Video Process., vol. 17, no. 4, pp. 1265–1273, Jun. 2023.
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 618–626.
J. Cuadros and G. Bresnick, “EyePACS: An adaptable telemedicine system for diabetic retinopathy screening,” J. Diabetes Sci. Technol., vol. 3, no. 3, pp. 509–516, May 2009.
Asia Pacific Tele-Ophthalmology Society, “APTOS 2019 blindness detection,” Kaggle, 2019. [Online]. Available: https://www.kaggle.com/competitions/aptos2019-blindness-detection. Accessed: May 8, 2026.
P. Porwal et al., “Indian diabetic retinopathy image dataset (IDRiD): A database for diabetic retinopathy screening research,” Data, vol. 3, no. 3, Art. no. 25, Jul. 2018, doi: 10.3390/data3030025.
G. Quellec, K. Charrière, Y. Boudi, B. Cochener, and M. Lamard, “Deep image mining for diabetic retinopathy screening,” Med. Image Anal., vol. 39, pp. 178–193, Jul. 2017, doi: 10.1016/j.media.2017.04.012.
K. Ashwini and R. Dash, “Grading diabetic retinopathy using multiresolution based CNN,” Biomed. Signal Process. Control, vol. 86, Art. no. 105210, Sep. 2023, doi: 10.1016/j.bspc.2023.105210.
S. Yasin et al., “Severity grading and early retinopathy lesion detection through hybrid Inception-ResNet architecture,” Sensors, vol. 21, no. 20, Art. no. 6933, Oct. 2021, doi: 10.3390/s21206933.
Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2022, pp. 11976–11986, doi: 10.48550/arXiv.2201.03545.
A. Mehboob, M. U. Akram, N. S. Alghamdi, and A. Abdul Salam, “A deep learning based approach for grading of diabetic retinopathy using large fundus image dataset,” Diagnostics, vol. 12, no. 12, Art. no. 3084, Dec. 2022, doi: 10.3390/diagnostics12123084.
H. Xu, X. Shao, D. Fang, and F. Huang, “A hybrid neural network approach for classifying diabetic retinopathy subtypes,” Front. Med., vol. 10, Art. no. 1293019, Jan. 2024, doi: 10.3389/fmed.2023.1293019.
P. Uppamma and S. Bhattacharya, “A multidomain bio-inspired feature extraction and selection model for diabetic retinopathy severity classification: An ensemble learning approach,” Sci. Rep., vol. 13, Art. no. 18572, Oct. 2023, doi: 10.1038/s41598-023-45886-7.
T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 2980–2988, doi: 10.48550/arXiv.1708.02002.
Y. Cui, M. Jia, T.-Y. Lin, Y. Song, and S. Belongie, “Class-balanced loss based on effective number of samples,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2019, pp. 9268–9277.
U. Bhimavarapu, N. Chintalapudi, and G. Battineni, “Automatic detection and classification of diabetic retinopathy using the improved pooling function in the convolution neural network,” Diagnostics, vol. 13, no. 15, Art. no. 2606, Aug. 2023, doi: 10.3390/diagnostics13152606.
S. Ghosh and A. Chatterjee, “Transfer-ensemble learning based deep convolutional neural networks for diabetic retinopathy classification,” in Proc. 3rd Int. Conf. Advancement Electron. Commun. Eng. (AECE), Nov. 2023, pp. 489–493, doi: 10.1109/AECE59614.2023.10428233.
M. Akram, M. Adnan, S. F. Ali, J. Ahmad, A. Yousef, T. A. N. Alshalali, and Z. A. Shaikh, “Uncertainty-aware diabetic retinopathy detection using deep learning enhanced by Bayesian approaches,” Sci. Rep., vol. 15, Art. no. 1342, Jan. 2025, doi: 10.1038/s41598-024-84478-x.
M. S. H. Bosale and A. A. Bosale, “Detection and classification of diabetic retinopathy using deep learning algorithms for segmentation to facilitate referral recommendation for test and treatment prediction,” arXiv preprint arXiv:2401.02759, Jan. 2024.
H. Shakibania, S. Raoufi, B. Pourafkham, H. Khotanlou, and M. Mansoorizadeh, “Dual branch deep learning network for detection and stage grading of diabetic retinopathy,” Biomed. Signal Process. Control, vol. 93, Art. no. 106168, Jul. 2024, doi: 10.1016/j.bspc.2024.106168.
A. Shukla, S. Tiwari, and A. Jain, “HybridFusionNet: Deep learning for multi-stage diabetic retinopathy detection,” Technologies, vol. 12, no. 12, Art. no. 256, Dec. 2024, doi: 10.3390/technologies12120256.
S. A. Karthik, M. N. Geetha, K. Prabhavathi, D. Shashank, K. P. Suhaas, and M. Narender, “Early detection and severity classification of diabetic retinopathy using convolutional neural networks,” SN Comput. Sci., vol. 6, Art. no. 750, Jul. 2025, doi: 10.1007/s42979-025-04361-y.
T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 2980–2988, doi: 10.1109/ICCV.2017.324.
Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2022, pp. 11976–11986, doi: 10.48550/arXiv.2201.03545.
B. Menaouer, Z. Dermane, N. E. H. Kebir, and N. Matta, “Diabetic retinopathy classification using hybrid deep learning approach,” SN Comput. Sci., vol. 3, Art. no. 357, Sep. 2022, doi: 10.1007/s42979-022-01240-8.
R. Gargeya and T. Leng, “Automated identification of diabetic retinopathy using deep learning,” Ophthalmology, vol. 124, no. 7, pp. 962–969, Jul. 2017, doi: 10.1016/j.ophtha.2017.02.008.
A. B. Arrieta et al., “Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI,” Inf. Fusion, vol. 58, pp. 82–115, Jun. 2020, doi: 10.1016/j.inffus.2019.12.012.
R. Fan, Y. Liu, and R. Zhang, “Multi-scale feature fusion with adaptive weighting for diabetic retinopathy severity classification,” Electronics, vol. 10, no. 12, Art. no. 1369, Jun. 2021, doi: 10.3390/electronics10121369.
A. Sugeno, Y. Ishikawa, T. Ohshima, and R. Muramatsu, “Simple methods for the lesion detection and severity grading of diabetic retinopathy by image processing and transfer learning,” Comput. Biol. Med., vol. 137, Art. no. 104795, Oct. 2021, doi: 10.1016/j.compbiomed.2021.104795.
M. T. Al-Antary and Y. Arafa, “Multi-scale attention network for diabetic retinopathy classification,” IEEE Access, vol. 9, pp. 54190–54200, 2021, doi: 10.1109/ACCESS.2021.3070685.

Details

Primary Language

English

Subjects

Computing Applications in Health

Journal Section

Research Article

Authors

Shahram Taheri ^*
0000-0002-7279-5565
Iran

Zahra Golrizkhatami
0000-0003-2631-4561
Türkiye

Early Pub Date

June 8, 2026

Publication Date

June 17, 2026

Submission Date

August 10, 2025

Acceptance Date

November 30, 2025

Published in Issue

Year 2026 Volume: 9 Number: 2

DOI

https://doi.org/10.35377/saucis...1760380

IZ

https://izlik.org/JA88XE35SX

Cite

RIS / Bibtex

APA

Taheri, S., & Golrizkhatami, Z. (2026). RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading. Sakarya University Journal of Computer and Information Sciences, 9(2), 481-493. https://doi.org/10.35377/saucis...1760380

AMA

1.Taheri S, Golrizkhatami Z. RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading. SAUCIS. 2026;9(2):481-493. doi:10.35377/saucis.1760380

Chicago

Taheri, Shahram, and Zahra Golrizkhatami. 2026. “RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading”. Sakarya University Journal of Computer and Information Sciences 9 (2): 481-93. https://doi.org/10.35377/saucis. 1760380.

EndNote

Taheri S, Golrizkhatami Z (June 1, 2026) RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading. Sakarya University Journal of Computer and Information Sciences 9 2 481–493.

IEEE

[1]S. Taheri and Z. Golrizkhatami, “RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading”, SAUCIS, vol. 9, no. 2, pp. 481–493, June 2026, doi: 10.35377/saucis...1760380.

ISNAD

Taheri, Shahram - Golrizkhatami, Zahra. “RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading”. Sakarya University Journal of Computer and Information Sciences 9/2 (June 1, 2026): 481-493. https://doi.org/10.35377/saucis. 1760380.

JAMA

1.Taheri S, Golrizkhatami Z. RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading. SAUCIS. 2026;9:481–493.

MLA

Taheri, Shahram, and Zahra Golrizkhatami. “RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 2, June 2026, pp. 481-93, doi:10.35377/saucis. 1760380.

Vancouver

1.Shahram Taheri, Zahra Golrizkhatami. RetinaNeXt: ConvNeXt-Driven Deep Learning for Diabetic Retinopathy Severity Grading. SAUCIS. 2026 Jun. 1;9(2):481-93. doi:10.35377/saucis. 1760380