A Parallel Comparative Multi-Scenario Framework For Diabetic Retinopathy Detection Using Three-Tiered Feature Selection

Loneli Costaner; Nor Hazlyna Harun

doi:10.37385/xtfckd08

Authors

Loneli Costaner Universitas Lancang Kuning
Nor Hazlyna Harun University Utara Malaysia

DOI:

https://doi.org/10.37385/xtfckd08

Keywords:

Biomedical Engineering, Diabetic Retinopathy, Feature Extraction, Feature Selection, LBP, SVM, 1D-CNN, RFE

Abstract

Early detection of Microaneurysms (MAs) is vital for diagnosing Diabetic Retinopathy, yet standard deep learning models often struggle with high false-negative rates and overfitting on limited medical datasets. Objective: This study proposes a Parallel Comparative Multi-Scenario Framework to identify the most robust configuration for MA detection. The framework evaluates independent 1D vectorized feature descriptors, each initialized as a high-dimensional 16,384-feature baseline, to avoid the redundancy inherent in feature fusion. Methodology: The system systematically processes six independent descriptors LBP, GLCM, Gabor, Wavelet, Fractal, and LMR across three selection tiers (Filter, Wrapper/RFE, and Embedded). These optimized vectors, reduced from the initial 16,384 dimensions to the most discriminative "Best Subsets," serve as uniform inputs for six classifiers: five traditional Machine Learning (ML) models and a proposed representation-consistent 1D-CNN architecture, resulting in 128 experimental scenarios. Results: Experimental evaluation was conducted on a balanced dataset of 740 fundus images derived from two distinct sources: the publicly available MESSIDOR dataset and a clinically acquired dataset from Hospital Universiti Sains Malaysia (HUSM). The model was trained on MESSIDOR data and subsequently evaluated on an independent HUSM test set to assess generalization performance. The results reveal a significant performance gap. The independent LBP-RFE-SVM scenario achieved the highest performance with an accuracy, recall, and precision of 91.00%. In contrast, the best Deep Learning (DL) configuration, Gabor-ANOVA-1DCNN, reached 87.00% accuracy. Notably, while the 1D-CNN maintained a "performance floor" of 60%, ML demonstrated extreme volatility, dropping to 51.00% with global statistical features. The optimal framework significantly minimized the False Negative Rate (FNR) to 6.76%, missing only 5 out of 74 cases.

Downloads

Download data is not yet available.

References

Adriman, R., Muchtar, K., & Maulina, N. (2021). Performance Evaluation of Binary Classification of Diabetic Retinopathy through Deep Learning Techniques using Texture Feature. Procedia Computer Science, 179(2020), 88–94. https://doi.org/10.1016/j.procs.2020.12.012

Ali, S. G., Wang, X., Bi, L., Jung, Y., Chen, T., & Zhang, H. (2025). Deep learning-based binocular system for automated diabetic retinopathy grading with prior clinical knowledge integration. The Visual Computer, 41(8), 5675–5688. https://doi.org/10.1007/s00371-024-03745-0

Alshahrani, M., Al-jabbar, M., Senan, Ebrahim mohammed Ahmed, I. abdulrab, & Saif, J. A. M. (2023). Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features. Diagnostics MDPI, 13, 1–20. https://doi.org/10.3390/diagnostics13172783

Alshayeji, M. H., & Chandrabhasi, S. (2023). Early detection of diabetic foot ulcers from thermal images using the bag of features technique. Biomedical Signal Processing and Control, 79(P2), 104143. https://doi.org/10.1016/j.bspc.2022.104143

Alyoubi, W. L., & Abulkhair, M. F. (2021). Diabetic Retinopathy Fundus Image Classification and Lesions Localization System Using Deep Learning. Sensor, 1–22.

Bai, Y., Zhang, X., Wang, C., Gu, H., Zhao, M., & Shi, F. (2023). Microaneurysms detection in retinal fundus images based on shape constraint with region-context features. In Biomedical Signal Processing and Control (Vol. 85, Issue March). https://doi.org/10.1016/j.bspc.2023.104903

Bala, R., Sharma, A., & Goel, N. (2024). Comparative Analysis of Diabetic Retinopathy Classification Approaches Using Machine Learning and Deep Learning Techniques. In Archives of Computational Methods in Engineering (Vol. 31, Issue 2). Springer Netherlands. https://doi.org/10.1007/s11831-023-10002-5

Barges, E., & Thabet, E. (2023). GLDM and Tamura features based KNN and particle swarm optimization for automatic diabetic retinopathy recognition system. Multimedia Tools and Applications, 82(1), 271–295. https://doi.org/10.1007/s11042-022-13282-4

Costaner, L., Lisnawita, L., & Guntoro, G. (2025). Optimization Of LBP Texture Feature Extraction Using Correlation And MI For SVM Based Diabetic Retinopathy Classification. INOVTEK Polbeng-Seri Informatika, 10(2), 1281–1291. https://doi.org/10.35314/4vrj4930

Ding, Y., Zhang, Z., Zhao, X., Hong, D., Cai, W., Yu, C., & Yang, N. (2022). Multi-feature fusion : Graph neural network and CNN combining for hyperspectral image classification. Neurocomputing, 501, 246–257. https://doi.org/10.1016/j.neucom.2022.06.031

Du, J., Zou, B., Chen, C., Xu, Z., & Liu, Q. (2020). Automatic microaneurysm detection in fundus image based on local cross-section transformation and multi-feature fusion. Computer Methods and Programs in Biomedicine, 196, 1–15. https://doi.org/10.1016/j.cmpb.2020.105687

Fathimah, F. S. N., Widjaja, S. A., & Wimbo. (2025). Retinal vessel tortuosity and fractal dimension in diabetic retinopathy. International Journal of Retina and Vitreous, 11, 1–10. https://doi.org/10.1186/s40942-025-00688-z

Gupta, A., & Kumar, V. (2023). A Deep Learning Fusion Approach for Automatic Diagnosis and Grading of Diabetic Retinopathy. 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), 1–6. https://doi.org/10.1109/ICCCNT56998.2023.10306810

Hwang, C., & Lee, T. (2025). Screening Retinal Diseases With Local Binary Patterns. Data Science And Iot Management System, 4(2), 5. https://doi.org/10.64751

Ige, A. O., & Sibiya, M. (2024). State-of-the-Art in 1D Convolutional Neural Networks : A Survey. IEEE Access, 12(June), 144082–144105. https://doi.org/10.1109/ACCESS.2024.3433513

Kandhasamy, J. P., Balamurali, S., Kadry, S., & Ramasamy, L. K. (2020). Diagnosis of diabetic retinopathy using multi level set segmentation algorithm with feature extraction using SVM with selective features. Multimedia Tools and Applications, 79(15–16), 10581–10596. https://doi.org/10.1007/s11042-019-7485-8

Kurniawan, A. R., & Irmawati. (2024). Detection of Diabetic Retinopathy in Retinal Fundus Images Using Gabor Filters and ConvNeXt. International Conference on Digital Medicine and Image Processing, 47–52. https://doi.org/10.1145/3705927.3705936

Latha, D., Bell, T. B., & Sheela, C. J. J. (2022). Red lesion in fundus image with hexagonal pattern feature and two-level segmentation. Multimedia Tools and Applications, 26143–26161. https://doi.org/10.1007/s11042-022-12667-9

Lavanya, D., Derwin, D. J., Remya, R., Shan, B. P., Singh, O. J., & Umamaheswari, K. (2022). Diagnosis of Early-Stage Diabetic Retinopathy in Digital Fundus Images. 2022 2nd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2022, 1–5. https://doi.org/10.1109/ICAECT54875.2022.9807977

Mahmood, M. A. I., Aktar, N., & Kader, M. F. (2023). A hybrid approach for diagnosing diabetic retinopathy from fundus image exploiting deep features. Heliyon, 9(9), 1–14. https://doi.org/10.1016/j.heliyon.2023.e19625

Makmur, N. M., Kwan, F., Dewi, A., & Indra, F. (2023). Comparing Local Binary Pattern and Level Co-occurrence Matrix for Feature Extraction in Diabetic Retinopathy Classification. Procedia Computer Science, 227, 355–363. https://doi.org/10.1016/j.procs.2023.10.534

Maltsev, D. S., Kulikov, A. N., & Burnasheva, M. A. (2022). Association of Resolved Paracentral Acute Middle Maculopathy Lesions with Diabetic Retinopathy. Journal of Current Ophthalmology, 318–322. https://doi.org/10.4103/joco.joco

Minarno, A. E., Bagaskara, D. A., Bimantoro, F., & Suharso, W. (2025). Classification of Diabetic Retinopathy Based on Fundus Image Using. JOIV, 9(January), 23–28.

Miron, M., Culea-florescu, A., & Moldovanu, S. (2023). Diabetic Retinopathy Image Classification Using Machine Learning and Local Binary Patterns Features. 2023 8th International Symposium on Electrical and Electronics Engineering (ISEEE), 136–139. https://doi.org/10.1109/ISEEE58596.2023.10310398

Modi, P., & Kumar, Y. (2023). Smart detection and diagnosis of diabetic retinopathy using bat based feature selection algorithm and deep forest technique. Jurnal Computers & Industrial Engineering, 182(June).

Mohan, N. J., Tripti, R. M., Tanveer, G. M., & Roy, P. (2023). An efficient microaneurysms detection approach in retinal fundus images. International Journal of Machine Learning and Cybernetics (2023), 1235–1252. https://doi.org/10.1007/s13042-022-01696-3

Mohd Sharif, N. A., Harun, N. H., & Yusof, Y. (2024). Colour Image Enhancement Model of Retinal Fundus Image for Diabetic Retinopathy Recognition. Journal Of Information And Communication Technology, 2(2), 293–334.

Mukherjee, N., & Sengupta, S. (2023). Comparing Deep Feature Extraction Strategies for Diabetic Retinopathy Stage Classification from Fundus Images. Arabian Journal for Science and Engineering, 48(8), 10335–10354. https://doi.org/10.1007/s13369-022-07547-1

Mulyani, A., Muljono, Purwanto, & Soeleman, M. A. (2024). Filter Gabor and SMOTE Method-Based Convolutional Neural Network for Diabetic Retinopathy Classification. International Seminar on Application for Technology of Information and Communication (ISemantic), 465–470. https://doi.org/10.1109/iSemantic63362.2024.10762114

Mutawa, A. M., Al-sabti, K., Raizada, S., & Sruthi, S. (2024). A Deep Learning Model for Detecting Diabetic Retinopathy Stages with Discrete Wavelet Transform. Applied Sciences MDPI, 1–19. https://doi.org/10.3390/app14114428

Mutawa, A. M., Hemalakshmi, G. R., & Prakash, N. B. (2025). Randomization-Driven Hybrid Deep Learning for Diabetic Retinopathy Detection. IEEE Access, 13(February), 38901–38913. https://doi.org/10.1109/ACCESS.2025.3546359

Pak, A., Ziyaden, A., Tukeshev, K., Jaxylykova, A., & Abdullina, D. (2020). Comparative analysis of deep learning methods of detection of diabetic retinopathy. Cogent Engineering, 7(1). https://doi.org/10.1080/23311916.2020.1805144

Pendekal, M. J., & Gupta, S. (2022). An Ensemble Classifier Based on Individual Features for Detecting Microaneurysms in Diabetic Retinopathy. Indonesian Journal of Electrical Engineering and Informatics, 10(1), 60–71. https://doi.org/10.52549/ijeei.v10i1.3522

Rahman, F., Hossain, S., & Tiang, J. (2025). Diabetes Prediction Using Feature Selection Algorithms and Boosting-Based Machine Learning Classifiers. Diagnostics, 1–24. https://doi.org/10.3390/diagnostics15202622

Rodriguez, D., Church, K. A., Smith, C. T., Vanegas, D., Cardona, S. M., Muzzio, I. A., Nash, K. R., & Cardona, A. E. (2024). Therapeutic Delivery of Soluble Fractalkine Ameliorates Vascular Dysfunction in the Diabetic Retina. International Journal of Molecular Sciences, 25, 1–20. https://doi.org/10.3390/ijms25031727

Shamsan, A., Senan, E. M., Salameh, H., & Shatnawi, H. S. A. (2023). Predicting of diabetic retinopathy development stages of fundus images using deep learning based on combined features. Plos One, 1–26. https://doi.org/10.1371/journal.pone.0289555

Suhaimi, N. M., Samad, R., Rul, N., Abdullah, H., Mustafa, M., Ibrahim, M. Z., & Pebrianti, D. (2024). Comparative Analysis of Superpixel and Gabor Methods for Exudate Feature Extraction in Diabetic Retinopathy Fundus Images. Proceedings of the 7th International Conference on Electrical, Control and Computer Engineering, 2, 123–136. https://doi.org/10.1007/978-981-97-3851-9

Sundar, S., & Subramanian, S. (2024). Classification of Diabetic Retinopathy Disease Levels by Extracting Spectral Features Using Wavelet CNN. Diagnostics MDPI, 14(5), 1–18. https://doi.org/10.3390/ diagnostics14111093

Sundar, S., & Sumathy, S. (2023). Classification of Diabetic Retinopathy Disease Levels by Extracting Topological Features Using Graph Neural Networks. IEEE Access, 11(June), 51435–51444. https://doi.org/10.1109/ACCESS.2023.3279393

Usman, T. M., Saheed, Y. K., Ignace, D., & Nsang, A. (2023). Diabetic retinopathy detection using principal component analysis multi-label feature extraction and classification. International Journal of Cognitive Computing in Engineering, 4(February 2022), 78–88. https://doi.org/10.1016/j.ijcce.2023.02.002

Wee, B. F., Sivakumar, S., Lim, K. H., Wong, W. K., & Juwono, F. H. (2023). Diabetes detection based on machine learning and deep learning approaches. Multimedia Tools and Applications, 83(8), 24153–24185. https://doi.org/10.1007/s11042-023-16407-5

Yadav, D., Karn, A. K., Giddalur, A., Dhiman, A., Sharma, S., Muskan, & Yadav, A. K. (2021). Microaneurysm detection using color locus detection method. Journal of the International Measurement Confederation, 176(July 2020), 109084. https://doi.org/10.1016/j.measurement.2021.109084

Yadav, S., & Awasthi, P. (2022). Diabetic Retinopathy Detection Using Deep Learning And Inception-V3 Model. International Research Journal of Modernization in Engineering Technology and Science, 06, 1731–1735.

Zhang, N., Jiang, Z., Li, J., & Zhang, D. (2023). Multiple color representation and fusion for diabetes mellitus diagnosis based on back tongue images. Computers in Biology and Medicine, 155(February), 106652. https://doi.org/10.1016/j.compbiomed.2023.106652

Zhang, X., Ma, Y., Gong, Q., & Yao, J. (2023). Automatic detection of microaneurysms in fundus images based on multiple preprocessing fusion to extract features. Biomedical Signal Processing and Control, 85(November 2022). https://doi.org/10.1016/j.bspc.2023.104879

Zhou, H., Wang, X., & Zhu, R. (2022). Feature selection based on mutual information with correlation coefficient. Applied Intelligence, 5457–5474.