International Journal of Computational and Electronic Aspects in Engineering
Volume 7 · Issue 2 · May 2026 · pp. 176-188
Research Article · Peer Reviewed
Received: March 2, 2026 · Accepted: May 5, 2026 · Published: May 20, 2026
DOI: 10.26706/ijceae.7.2.20260307
Open Access · CC BY 4.0

Enhanced Diabetic Retinopathy Classification using Hybrid EfficientNetB0 with CBAM

Mohammed Khalid Yousif*
Medical Instrumentation Techniques, Polytechnic College Mosul, Northern Technical University, Mosul 41002, Iraq.

ORCID: 0000-0002-4280-3253

*Corresponding author: mohamed.khalid@ntu.edu.iq
Download PDF Cite this article Certificate Volume 7 Issue 2

Abstract

Diabetic retinopathy is considered one of the most common reasons of permanent blindness in adults. Consequently, the classification of diabetic retinopathy is of great importance to ensure the timely management of disease. The classification of diabetic retinopathy enables clinician to determine severity of disease and thereby prevent the progression of disease. The process of manual examination of retinal images involves a lot of time, human error and expertise. Hence, deep learning-based automated systems have been recognized as efficient tools to assist ophthalmologists in the analysis of retinal images. In this paper, the image classification for diabetic retinopathy is investigated using two deep learning models. In the first model, data augmentation applied to training dataset to maximize diversity of the images thus enhancing EfficientNetB0 model. Whereas, in the second model the Convolutional Block Attention Module (CBAM) is proposed integrating with EfficientNetB0 model along with dual pooling to allow model to focus on the most important regions of retina thus facilitating extraction of features from the images. The results show the model using CBAM along with dual pooling abled to classify of images more accurately which achieving accuracy rate of 96.45 % compared to 89.35% accuracy rate obtained in model using data augmentation.

Keywords

EfficientNetB0 Convolutional Block Attention Module CBAM Data Augmentation Image Classification Diabetic Retinopathy Convolutional Neural Network Deep Learning

References

  1. R. Airola and K. Hager, “Image classification, deep learning and convolutional neural networks: A comparative study of machine learning frameworks,” 2017.
  2. S. A. S. Al-Duri, “Improving Heart Disease Classification using Multimodal Fusion in Deep Learning,” International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 3, pp. 218–227, 2025.
  3. A. J. Yaseen, “Prospective Detection of Diabetic Retinopathy Using Modified CNN Models on Fundus Images: A Study at Al-Noor Institute, Al-Nasiriya,” International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 3, pp. 169–179, 2025.
  4. H. Hatem, “Improved Deep Learning Models for Plants Diseases Detection for Smart Farming,” International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 1, pp. 10–21, 2025, doi: 10.26706/ijceae.6.1.20250204.
  5. C. Bircanoğlu et al., “RecycleNet: Intelligent waste sorting using deep neural networks,” in 2018 Innovations in Intelligent Systems and Applications (INISTA), 2018, pp. 1–7, doi: 10.1109/INISTA.2018.8466276.
  6. J. D. Smith and A. B. Johnson, “Deep learning approaches for image classification,” Journal of Artificial Intelligence Research, vol. 25, no. 1, pp. 123–145, 2020, doi: 10.1145/3573428.3573691.
  7. S. Alhayali et al., “A Survey on the Moving to Green Communications Networks,” in 2023 International Conference on Information Technology and Computing (ICITCOM), 2023, pp. 78–83, doi: 10.1109/ICITCOM60176.2023.10441793.
  8. M. J. Kadhim, H. L. Majeed, and R. H. Salman, “Artificial Intelligence and Its Impact on Sustainable Development from An Industrial Perspective,” International Journal of Computational and Electronic Aspects in Engineering, vol. 7, no. 1, pp. 12–28, Feb. 2026, doi: 10.26706/ijceae.7.1.20260102.
  9. T. P. Karnowski, I. Arel, and D. Rose, “Deep spatiotemporal feature learning with application to image classification,” in 2010 Ninth International Conference on Machine Learning and Applications, 2010, pp. 883–888, doi: 10.1109/ICMLA.2010.138.
  10. B. Cheung, “Convolutional neural networks applied to human face classification,” in 2012 11th International Conference on Machine Learning and Applications, vol. 2, 2012, pp. 580–583, doi: 10.1109/ICMLA.2012.177.
  11. K. Charalampous and A. Gasteratos, “Bio-inspired deep learning model for object recognition,” in 2013 IEEE International Conference on Imaging Systems and Techniques (IST), 2013, pp. 51–55, doi: 10.1109/IST.2013.6729661.
  12. Y. Gan, T. Zhuo, and C. He, “Image classification with a deep network model based on compressive sensing,” in 2014 12th International Conference on Signal Processing (ICSP), 2014, pp. 1272–1275, doi: 10.1109/ICOSP.2014.7015204.
  13. W. Hou et al., “Blind image quality assessment via deep learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 26, no. 6, pp. 1275–1286, 2014, doi: 10.1109/TNNLS.2014.2336852.
  14. S. Khan and S.-P. Yong, “A comparison of deep learning and hand crafted features in medical image modality classification,” in 2016 3rd International Conference on Computer and Information Sciences (ICCOINS), 2016, pp. 633–638, doi: 10.1109/ICCOINS.2016.7783289.
  15. D. Li et al., “Multi-view deep metric learning for image classification,” in 2017 IEEE International Conference on Image Processing (ICIP), 2017, pp. 4142–4146, doi: 10.1109/ICIP.2017.8297062.
  16. Y.-N. Dong and G.-S. Liang, “Research and discussion on image recognition and classification algorithm based on deep learning,” in 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), 2019, pp. 274–278, doi: 10.1109/MLBDBI48998.2019.00061.
  17. M. Suganthi and J. G. R. Sathiaseelan, “An exploratory of hybrid techniques on deep learning for image classification,” in 2020 4th International Conference on Computer, Communication and Signal Processing (ICCCSP), 2020, pp. 1–4, doi: 10.1109/ICCCSP49186.2020.9315270.
  18. Z. Wang et al., “Research on application of deep learning algorithm in image classification,” in 2021 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC), 2021, pp. 1122–1125, doi: 10.1109/IPEC51340.2021.9421185.
  19. S. Bougareche, Z. Soraya, and M. Malika, “Fashion images classification using machine learning, deep learning and transfer learning models,” in 2022 7th International Conference on Image and Signal Processing and their Applications (ISPA), 2022, pp. 1–5, doi: 10.1109/ISPA54004.2022.9786364.
  20. S. E. Sunday et al., “Fruit image classification using the inception-V3 deep learning model,” in 2023 International Conference on the Cognitive Computing and Complex Data (ICCD), 2023, pp. 227–230, doi: 10.1109/ICCD59681.2023.10420760.
  21. J. Bai, “Research and application of deep learning based on transfer learning in image classification tasks,” in 2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA), 2024, pp. 1292–1297, doi: 10.1109/ICPECA60615.2024.10471046.
  22. R. Shyam, “Convolutional neural network and its architectures,” Journal of Computer Technology & Applications, vol. 12, no. 2, pp. 6–14, 2021, doi: 10.37591/JoCTA.
  23. N. B. Thota and D. U. Reddy, “Improving the Accuracy of Diabetic Retinopathy Severity Classification with Transfer Learning,” in 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS), Springfield, MA, USA, 2020, pp. 1003–1006, doi: 10.1109/MWSCAS48704.2020.9184473.
  24. N. Sikder et al., “Severity classification of diabetic retinopathy using an ensemble learning algorithm through analyzing retinal images,” Symmetry, vol. 13, no. 4, p. 670, 2021, doi: 10.3390/sym13040670.
  25. R. K. Bathla, “Machine learning for diabetic retinopathy detection using image processing,” International Journal of Recent Technology and Engineering (IJRTE), 2021, doi: 10.35940/IJRTE.E5267.019521.
  26. K. Mridha et al., “DBNet: Detect Diabetic Retinopathy to Stop Blindness Before it’s Too Late,” in 2022 10th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO), 2022, doi: 10.1109/ICRITO56286.2022.9964937.
  27. K. Duvvuri et al., “Classification of Diabetic Retinopathy Using Image Pre-processing Techniques,” in 2023 3rd International Conference on Intelligent Technologies (CONIT), 2023, doi: 10.1109/CONIT59222.2023.10205586.
  28. T. R. Athira and J. J. Nair, “Diabetic retinopathy grading from color fundus images: An autotuned deep learning approach,” Procedia Computer Science, vol. 218, pp. 1055–1066, 2023, doi: 10.1016/j.procs.2023.01.085.
  29. S. Mardianta et al., “Diabetic Retinopathy Detection Based on Convolutional Neural Networks with SMOTE and CLAHE Techniques Applied to Fundus Images,” in 2025 5th International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), 2025, doi: 10.48550/arXiv.2504.05696.
  30. A. Zhou et al., “Multi-head attention-based two-stream EfficientNet for action recognition,” Multimedia Systems, vol. 29, no. 2, pp. 487–498, 2023, doi: 10.1007/s00530-022-00961-3.
  31. W. Al-Dolat et al., “Enhancing fundus image analysis for diabetic retinopathy using CheXNet with CBAM and Grad-CAM visualization,” Frontiers in Medicine, vol. 13, p. 1732109, 2026, doi: 10.3389/fmed.2026.1732109.
  32. S. K. Ghanim, “Classification of Environmental and Human Obstacles in Automatic Driving Using EfficientNet,” Journal Européen des Systèmes Automatisés, vol. 59, no. 1, p. 53, 2026, doi: 10.18280/jesa.590106.
  33. I. P. Hariyadi, A. S. Anas, B. R. P. D. Palevi, B. A. Sasaki, and Mulyana, “Optimization of a coffee bean roasting machine using fuzzy logic and deep learning approaches,” Mathematical Modelling of Engineering Problems, vol. 12, no. 12, pp. 4325–4337, 2025, doi: 10.18280/mmep.121221.
  34. S. I. Hamad, “Utilizing Convolutional Neural Networks for the Identification of Lung Cancer,” International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 1, pp. 35–41, 2025.