IRO Journals
Journal of Innovative Image Processing

Multistage Preprocessing and Ensemble Classification for Diabetic Retinopathy Detection

Open Access
Published: 06 July, 2026
Pages: 827-843
  • Ahmed Hefdhi Hussein Hussein , Ahmed Hefdhi Hussein Hussein
    Technical Instructor Training Institute, Middle Technical University, Baghdad, Iraq
    Technical Instructor Training Institute, Middle Technical University, Baghdad, Iraq
  • Mudhar A. Al-Obaidi , Mudhar A. Al-Obaidi
    Technical Instructor Training Institute, Middle Technical University, Baghdad, Iraq
    Technical Instructor Training Institute, Middle Technical University, Baghdad, Iraq
  • Sadik Kamel Gharghan , Sadik Kamel Gharghan
    Technical Engineering College of Artificial Intelligence, Middle Technical University, Baghdad, Iraq
    Technical Engineering College of Artificial Intelligence, Middle Technical University, Baghdad, Iraq
  • Shatha A. Alsalman , Shatha A. Alsalman
    College of Dentistry, Al-Naji University, Baghdad, Iraq
    College of Dentistry, Al-Naji University, Baghdad, Iraq
  • Mohammed Ayad Saad Mohammed Ayad Saad
    Department of Cybersecurity Technical Engineering, Al-Huda University College, Ramadi, Iraq
    Department of Cybersecurity Technical Engineering, Al-Huda University College, Ramadi, Iraq
view PDF
view PDF

How to Cite

Hussein, Ahmed Hefdhi Hussein, Mudhar A. Al-Obaidi, Sadik Kamel Gharghan, Shatha A. Alsalman, and Mohammed Ayad Saad. 2026. “Multistage Preprocessing and Ensemble Classification for Diabetic Retinopathy Detection”. Journal of Innovative Image Processing 8 (3): 827-43. https://doi.org/10.36548/jiip.2026.3.005.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Diabetic Retinopathy
Image Preprocessing
Ensemble Classification
Convolutional Neural Networks
Support Vector Machines
ResNet50V2
CLAHE
Ben Graham Preprocessing

Abstract

Diabetic retinopathy (DR) is a leading cause of preventable blindness among people with diabetes and demands improved automated screening. The principal challenge addressed here is the variability of fundus-image quality, which limits the reliability of automated DR detection. A multistage image enhancement and classification framework is proposed. First, the input image is preprocessed by dark-border cropping, circular retinal region extraction, Ben Graham's weighted-Gaussian contrast enhancement, and Contrast Limited Adaptive Histogram Equalization (CLAHE) on the CIELAB L-channel, followed by resizing to 640×640 pixels. Second, a fine-tuned ResNet50V2 network with appended Global-Average-Pooling, dropout, and dense layers produces a 2048-dimensional feature vector. Third, a two-stage ensemble of RBF-kernel SVMs is used: (i) five one-vs-rest classifiers covering all DR classes and (ii) three additional SVMs targeting the intermediate grades (Mild, Moderate, Severe), combined by a four-rule confidence-scored decision system. All SVM hyperparameters are tuned by 5-fold stratified cross-validation on a training subset, and features are standardised (z-score) before classification. On the Kaggle DR Detection dataset, using an approximate 81% for training 9% for validation and 10% for testing. The model achieves an overall test accuracy of 83% and an F_1-score of 0.91 for the No DR class. The proposed hybrid deep learning and SVM approach performs competitively for grading diabetic retinopathy, and also offers transparency in terms of evaluation.

References

  1. AbdelMaksoud, Eman, Sherif Barakat, and Mohammed Elmogy. "A Computer-Aided Diagnosis System for Detecting Various Diabetic Retinopathy Grades Based on a Hybrid Deep Learning Technique." Medical & Biological Engineering & Computing 60, no. 7 (2022): 2015-2038.
  2. Mukherjee, Nilarun, and Souvik Sengupta. "In Search for the Optimal Preprocessing Technique for Deep Learning-Based Diabetic Retinopathy Stage Classification from Retinal Fundus Images." In Artificial Intelligence Technologies for Computational Biology, pp. 161-176. CRC Press, 2022.
  3. Hussein, Naseer Alwan. "Simulation of RC5 Algorithm to Provide Security for WLAN, Peer-to-Peer." Al-Kitab Journal for Pure Sciences 8, no. 02 (2024): 31-47.
  4. Moya-Albor, Ernesto, Sandra L. Gomez-Coronel, Jorge Brieva, and Alberto Lopez-Figueroa. "Bio-inspired Watermarking Method for Authentication of Fundus Images in Computer-Aided Diagnosis of Retinopathy." Mathematics 12, no. 5 (2024): 734.
  5. Farag, Mohamed M., Mariam Fouad, and Amr T. Abdel-Hamid. "Automatic Severity Classification of Diabetic Retinopathy Based on Densenet and Convolutional Block Attention Module." IEEE Access 10 (2022): 38299-38308.
  6. Mehboob, Ayesha, Muhammad Usman Akram, Norah Saleh Alghamdi, and Anum Abdul Salam. "A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image Dataset." Diagnostics 12, no. 12 (2022): 3084.
  7. Hayder, Hajir Hayder, Nada Yassen Kasm, and Noor Hussain Abdullah. "Application of Coding Theory in Field 5." Al-Kitab Journal for Pure Sciences 8, no. 01 (2024): 136-144.
  8. Ali, Ghulam, Aqsa Dastgir, Muhammad Waseem Iqbal, Muhammad Anwar, and Muhammad Faheem. "A Hybrid Convolutional Neural Network Model for Automatic Diabetic Retinopathy Classification from Fundus Images." IEEE Journal of Translational Engineering in Health and Medicine 11 (2023): 341-350.
  9. Abbood, Saif Hameed, Haza Nuzly Abdull Hamed, Mohd Shafry Mohd Rahim, Amjad Rehman, Tanzila Saba, and Saeed Ali Bahaj. "Hybrid Retinal Image Enhancement Algorithm for Diabetic Retinopathy Diagnostic Using Deep Learning Model." IEEE Access 10 (2022): 73079-73086.
  10. Venkaiahppalaswamy, B., PVGD Prasad Reddy, and Suresh Batha. "An Effective Diagnosis of Diabetic Retinopathy Based on 3-D Hybrid SqueezeNet Architecture." International Journal of Engineering Trends and Technology (IJETT) 70, no. 12 (2022): 147-159.
  11. Raiaan, Mohaimenul Azam Khan, Kaniz Fatema, Inam Ullah Khan, Sami Azam, Md Rafi Ur Rashid, Md Saddam Hossain Mukta, Mirjam Jonkman, and Friso De Boer. "A Lightweight Robust Deep Learning Model Gained High Accuracy in Classifying a Wide Range of Diabetic Retinopathy Images." IEEE Access 11 (2023): 42361-42388.
  12. Sundaram, Swaminathan, Meganathan Selvamani, Sekar Kidambi Raju, Seethalakshmi Ramaswamy, Saiful Islam, Jae-Hyuk Cha, Nouf Abdullah Almujally, and Ahmed Elaraby. "Diabetic Retinopathy and Diabetic Macular Edema Detection Using Ensemble Based Convolutional Neural Networks." Diagnostics 13, no. 5 (2023): 1001.
  13. Almeshrky, Hamida, and Abdulkadir Karacı. "Optic Disc Segmentation in Human Retina Images Using a Meta Heuristic Optimization Method and Disease Diagnosis with Deep Learning." Applied Sciences 14, no. 12 (2024): 5103.
  14. Nur-A-Alam, Md, Md Mostofa Kamal Nasir, Mominul Ahsan, Md Abdul Based, Julfikar Haider, and Sivaprakasam Palani. "A Faster RCNN-based Diabetic Retinopathy Detection Method Using Fused Features from Retina Images." IEEE Access 11 (2023): 124331-124349.
  15. Huang, Yijin, Li Lin, Pujin Cheng, Junyan Lyu, Roger Tam, and Xiaoying Tang. "Identifying the key Components in Resnet-50 For Diabetic Retinopathy Grading from Fundus Images: A Systematic Investigation." Diagnostics 13, no. 10 (2023): 1664.
  16. Nadeem, Muhammad Waqas, Hock Guan Goh, Muzammil Hussain, Soung-Yue Liew, Ivan Andonovic, and Muhammad Adnan Khan. "Deep Learning for Diabetic Retinopathy Analysis: A Review, Research Challenges, and Future Directions." Sensors 22, no. 18 (2022): 6780.
  17. Abbood, Saif Hameed, Haza Nuzly Abdull Hamed, Mohd Shafry Mohd Rahim, Amjad Rehman, Tanzila Saba, and Saeed Ali Bahaj. "Hybrid Retinal Image Enhancement Algorithm for Diabetic Retinopathy Diagnostic Using Deep Learning Model." IEEE Access 10 (2022): 73079-73086