DIABETIC RETINOPATHY SEVERITY CLASSIFICATION USING GAMMA CORRECTION-BASED IMAGE ENHANCEMENT AND BN-VGG ARCHITECTURE
DOI:
https://doi.org/10.33480/jitk.v11i4.8094Keywords:
Batch Normalization, Classification, Diabetic Retinopathy, Gamma Correction, Visual Geometry GroupAbstract
Diabetic retinopathy (DR) is a diabetes-related condition that can cause vision impairment or vision loss. Accurately identifying the level of DR from retinal fundus images is crucial for early detection. However, poor image quality often degrades classification performance. This study proposes an approach that integrates gamma correction-based image enhancement with a Batch Normalization–Visual Geometry Group (BN-VGG) architecture for multiclass DR severity classification. Gamma correction is applied to improve image contrast, while BN-VGG enhances training stability and feature representation. The proposed method categorizes DR into five classifications: normal, mild, moderate, severe, and proliferative. The enhanced images achieved PSNR of 30.85 and SSIM above 0.86, indicating improved visual quality. The model achieved accuracy at 0.97, sensitivity at 0.92, specificity at 0.98, F1-score at 0.92, Cohen's Kappa at 0.90, and G-Mean at 0.97. The innovative aspect of this study is the incorporation of gamma correction with BN-VGG architecture, demonstrating that image enhancement can significantly improve multiclass DR classification performance without increasing model complexity. The study's results indicate the proposed method's effectiveness for accurate & reliable DR severity classification
Downloads
References
[1] M. Z. Atwany, A. H. Sahyoun, and M. Yaqub, “Deep Learning Techniques for Diabetic Retinopathy Classification: A Survey,” IEEE Access, vol. 10, pp. 28642–28655, 2022, doi: 10.1109/ACCESS.2022.3157632.
[2] Z. Khan et al., “Diabetic Retinopathy Detection Using VGG-NIN a Deep Learning Architecture,” IEEE Access, vol. 9, pp. 61408–61416, 2021, doi: 10.1109/ACCESS.2021.3074422.
[3] A. Bilal, G. Sun, and S. Mazhar, “Survey on recent developments in automatic detection of diabetic retinopathy,” J. Fr. Ophtalmol., vol. 44, no. 3, pp. 420–440, 2021, doi: 10.1016/j.jfo.2020.08.009.
[4] N. A. El-Hag et al., “Classification of retinal images based on convolutional neural network.,” Microsc. Res. Tech., vol. 84, no. 3, pp. 394–414, Mar. 2021, doi: 10.1002/jemt.23596.
[5] A. Desiani et al., “Multi-Stage CNN: U-Net and Xcep-Dense of Glaucoma Detection in Retinal Images,” J. Electron. Electromed. Eng. Med. Informatics, vol. 5, no. 4, pp. 211–222, 2023, doi: 10.35882/jeeemi.v5i4.314.
[6] W. L. Alyoubi, M. F. Abulkhair, and W. M. Shalash, “Diabetic retinopathy fundus image classification and lesions localization system using deep learning,” Sensors, vol. 21, no. 11, pp. 1–22, 2021, doi: 10.3390/s21113704.
[7] N. S. Rekhi, J. S. Sidhu, and A. Arora, “Gamma Correction for Brightness Preservation in Natural Images,” Comput. Syst. Sci. Eng., vol. 44, no. 3, pp. 2791–2807, 2023, doi: 10.32604/csse.2023.026976.
[8] A. Desiani, D. P. Rini, and L. I. Kesuma, “DDUSeg-Net as a Design of Convolutional Neural Network Architecture for Semantic Segmentation in Cervical Cancer.,” Int. J. Intell. Eng. Syst., vol. 18, no. 1, 2025, doi: 10.22266/ijies2025.0229.70.
[9] A. Desiani, Erwin, B. Suprihatin, F. Efriliyanti, M. Arhami, and E. Setyaningsih, “VG-DropDNet a Robust Architecture for Blood Vessels Segmentation on Retinal Image,” IEEE Access, vol. 10, pp. 92067–92083, 2022, doi: 10.1109/ACCESS.2022.3202890.
[10] S. Soni, P. Singh, and A. Waoo, “Review of Gamma Correction Techniques in Digital Imaging,” ShodhKosh J. Vis. Perform. Arts, vol. 5, May 2024, doi: 10.29121/shodhkosh.v5.i5.2024.1902.
[11] J. Xue, Y. Wang, Z. Li, and H. Zhang, “Classification of Diabetic Retinopathy Based on Efficient Computational Modeling,” Applied Sciences, vol. 14, no. 23, p. 11327, 2024, doi: 10.3390/app142311327.
[12] T. Aziz, C. Charoenlarpnopparut, and S. Mahapakulchai, “Deep learning-based hemorrhage detection for diabetic retinopathy screening,” Scientific Reports, vol. 13, no. 1, p. 1479, 2023, doi: 10.1038/s41598-023-28680-3.
[13] D. Mane, R. Ashtagi, R. Suryawanshi, A. N. Kaulage, and A. N. Hedaoo, “Diabetic Retinopathy Recognition and Classification Using Transfer Learning Deep Neural Networks,” Int. Inf. Eng. Technol. Assoc., vol. 41, no. 5, pp. 2683–2691, 2024, doi: 10.18280/ts.410541.
[14] Z. Yang, “Classification of picture art style based on VGGNET,” J. Phys. Conf. Ser., vol. 1774, no. 1, pp. 0–9, 2021, doi: 10.1088/1742-6596/1774/1/012043.
[15] D. Abhishek and P. Jatin, “Automated detection of Diabetic Retinopathy using VGG-16 architecture,” Int. Res. J. Eng. Technol., vol. 8, no. 3, pp. 2936–2940, 2021.
[16] A. T. Nair, M. L. Anitha, and M. N. Arun Kumar, “Disease Grading of Diabetic Retinopathy using Deep Learning Techniques,” Proc. - 6th Int. Conf. Comput. Methodol. Commun. ICCMC 2022, no. Iccmc, pp. 1019–1024, 2022, doi: 10.1109/ICCMC53470.2022.9754113.
[17] E. M. F. El Houby, “Using transfer learning for diabetic retinopathy stage classification,” Appl. Comput. Informatics, 2021, doi: 10.1108/ACI-07-2021-0191.
[18] J. Aftab, M. A. Khan, S. Arshad, S. ur Rehman, D. A. AlHammadi, and Y. Nam, “Artificial Intelligence Based Classification and Prediction of Medical Imaging using A Novel Framework of Inverted and Self-Attention Deep Neural Network Architecture,” Sci. Rep., vol. 15, no. 8724, pp. 1–26, 2025, doi: 10.1038/s41598-025-93718-7.
[19] A. S. Farhan, M. Khalid, and U. Manzoor, “Combined Oriented Data Augmentation Method for Brain MRI Images,” IEEE Access, vol. 13, pp. 9981–9994, 2025, doi: 10.1109/ACCESS.2025.3526684.
[20] H. Yang, J. Ni, J. Gao, Z. Han, and T. Luan, “A novel method for peanut variety identification and classification by Improved VGG16,” Sci. Rep., vol. 11, no. 1, pp. 1–17, 2021, doi: 10.1038/s41598-021-95240-y.
[21] A. Desiani, Erwin, B. Suprihatin, Y. Wahyudi, E. S. Cahyono, and M. Arhami, “BVU-Net : A U-Net Modification by VGG-Batch Normalization for Retinal Blood Vessel Segmentation,” Int. J. Intell. Eng. Syst., vol. 15, no. 6, pp. 303–314, 2022, doi: 10.22266/ijies2022.1231.29.
[22] L. Huang, J. Qin, Y. Zhou, F. Zhu, L. Liu, and L. Shao, “Normalization techniques in training dnns: Methodology, analysis and application,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 8, pp. 10173–10196, 2023, doi: 10.1109/TPAMI.2023.3250241.
[23] E. Lobacheva, M. Kodryan, N. Chirkova, A. Malinin, and D. P. Vetrov, “On the periodic behavior of neural network training with batch normalization and weight decay,” Adv. Neural Inf. Process. Syst., vol. 34, pp. 21545–21556, 2021, doi: 10.48550/arXiv.2106.15739.
[24] I. Slamet, “Retinopathy Classification using Convolutional Neural Network Method with Adaptive Momentum Optimization and Applied Batch Normalization,” J. Appl. Data Sci., vol. 5, no. 3, pp. 1123–1133, 2024, doi: 10.47738/jads.v5i3.309.
[25] T. R. Athira and J. J. Nair, “Diabetic Retinopathy Grading from Color Fundus Images: An Autotuned Deep Learning Approach,” Procedia Comput. Sci., vol. 218, no. 2022, pp. 1055–1066, 2022, doi: 10.1016/j.procs.2023.01.085.
[26] P. Porwal, S. Pachade, M. Kokare, G. Deshmukh, J. Son, W. Bae, L. Liu, J. Wang, X. Liu, L. Gao, T. Wu, J. Xiao, F. Wang, B. Yin, Y. Wang, G. Danala, L. He, Y. H. Choi, Y. C. Lee, S.-H. Jung, et al., “IDRiD: Diabetic Retinopathy—Segmentation and Grading Challenge,” Medical Image Analysis, vol. 59, p. 101561, 2020, doi: 10.1016/j.media.2019.101561.
[27] M. Triantafyllou et al., “The Effect of Ultrasound Image Pre‑Processing on Radiomics Feature Quality : A Study on Shoulder Ultrasound,” J. Imaging Informatics Med., 2025, doi: 10.1007/s10278-025-01421-w.
[28] V. Madhavi and P. L. S. Kumari, “A Qualitative Approach for Enhancing Fundus Images with Novel CLAHE Methods,” Eng. Technol. Appl. Sci. Res., vol. 15, no. 1, pp. 20102–20107, 2025, doi: 10.48084/etasr.9525.
[29] M. N. Huda, A. Musdholifah, and A. Z. K. Frisky, “Optimization of Plantar Foot Thermogram for Diabetic Foot Ulceration Early Detection : An Image Enhancement Approach,” SINTECHCOM Sci. Technol. Commun. J., vol. 5, no. 2, pp. 49–66, 2025, doi: 10.59190/stc.v5i2.273.
[30] C. P. Parmo, L. I. Kesuma, and D. Geovani, “The Combination of Black Hat Transform and U-Net in Image Enhancement and Blood Vessel Segmentation in Retinal Images,” Comput. Eng. Appl., vol. 12, no. 3, pp. 129–145, 2023, doi: 10.18495/comengapp.v12i3.452.
[31] M. Naufal, H. Al Azies, and R. M. Brilianto, “Enhanced Brain Tumor Classification Through Gamma Correction in Deep Learning,” Sist. J. Sist. Inf., vol. 13, no. 6, pp. 2348–2358, 2024, doi: 10.32520/stmsi.v13i6.4474.
[32] M. N. Noor, F. Haneef, I. Ashraf, and M. Masud, “Enhanced Skin Disease Classification via Dataset Refinement and Attention-Based Vision Approach,” Bioengineering, vol. 12, no. 275, pp. 1–17, 2025, doi: 10.3390/bioengineering12030275.
[33] P. Radočaj, D. Radočaj, and G. Martinović, “Optimal Optimizing Convolutional Neural Network Architectures with Optimal Activation Functions for Pediatric Pneumonia Diagnosis Using Chest X-rays,” Big Data Cogn. Comput., vol. 9, no. 25, pp. 1–17, 2025, doi: 10.3390/bdcc9020025.
[34] D. F. Brianna, L. I. Kesuma, D. Geovani, and P. Sari, “Combination of Image Enhancement and Double U-Net Architecture for Liver Segmentation in CT-Scan Images,” J. Electron. Electromed. Eng. Med. Informatics, vol. 7, no. 1, pp. 208–219, 2025, doi: 10.35882/jeeemi.v7i1.582.
[35] 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,” Biomed. Signal Process. Control, vol. 100, no. 106907, pp. 1–23, 2025, doi: 10.1016/j.bspc.2024.106907.
[36] S. Afrifa, V. Varadarajan, P. Appiahene, T. Zhang, D. Gyamfi, and R. M. O. M. Gyening, “Deep Neural Networks for Skin Cancer Classification: Analysis of Melanoma Cancer Data,” J. Adv. Inf. Technol., vol. 16, no. 1, pp. 1–11, 2025, doi: 10.12720/jait.16.1.1-11.
[37] M. Abidin et al., “Classification of Heart (Cardiovascular) Disease using the SVM Method,” Indones. J. Mod. Sci. Technol. Mod., vol. 1, no. 1, pp. 9–15, 2025, doi: 10.64021/ijmst.1.1.9-15.2025.
[38] R. Wijaya and G. Kosala, “Stress Detection Through Wearable Sensors : A Convolutional Neural Network-Based Approach Using Heart Rate and Step Data,” Int. J. Electr. Comput. Eng., vol. 15, no. 2, pp. 1880–1888, 2025, doi: 10.11591/ijece.v15i2.pp1880-1888.
[39] R. Chilukuri, P. Praveen, R. K. Gatla, and R. A. Almenweer, “Quantum Denoising Autoencoder Improves Retinal Fundus Image Quality for Early Diabetic Retinopathy Screening,” Sci. Rep., vol. 16, no. 5970, pp. 1–17, 2026, doi: 10.1038/s41598-026-35540-3.
[40] Z. Deng, Y. Cai, L. Chen, Z. Gong, Q. Bao, X. Yao, D. Fang, W. Yang, S. Zhang, and L. Ma, “RFormer: Transformer-Based Generative Adversarial Network for Real Fundus Image Restoration on a New Clinical Benchmark,” IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 9, pp. 4645–4655, Sep. 2022, doi: 10.1109/JBHI.2022.3187103.
[41] P. C and J. K. R, “Retinal image enhancement based on color dominance of image,” Sci. Rep., vol. 13, no. 1, pp. 1–14, 2023, doi: 10.1038/s41598-023-34212-w.
[42] C. Wan et al., “Retinal Image Enhancement Using Cycle-Constraint Adversarial Network,” Front. Med., vol. 8, no. January, pp. 1–16, 2022, doi: 10.3389/fmed.2021.793726.
[43] E. AbdelMaksoud, S. Barakat, and M. Elmogy, “A Computer-Aided Diagnosis System for Detecting Various Diabetic Retinopathy Grades Based on A Hybrid Deep Learning Technique,” Med. Biol. Eng. Comput., vol. 60, no. 7, pp. 2015–2038, 2022, doi: 10.1007/s11517-022-02564-6.
[44] V. Srinivasan and V. Rajagopal, “Multi-Scale Attention-Based Mechanism in Gradient Boosting Convolutional Neural Network for Diabetic Retinopathy Grade Classification,” Int. J. Intell. Eng. Syst., vol. 15, no. 4, pp. 489–498, 2022, doi: 10.22266/ijies2022.0831.44.
[45] E. Abdelmaksoud, S. Barakat, and M. Elmogy, “Diabetic Retinopathy Grading System Based On Transfer Learning,” Int. J. Adv. Comput. Res., vol. 11, no. 52, pp. 1–12, 2021, doi: 10.48550/arXiv.2012.12515.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Indri Ramayanti, Karnadi, Septiani Nadra Indawaty, Muhammad Umar Abdussalam, Malika Zilda, Anita Desiani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
