Eye Disease Classification Using K-means Clustering Algorithm and Ensemble Classification Approach

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 03 | Issue : 02 | Page :
    By

    E.Dhiravidachelvi,

  • S.Vengatesh Kumar,

  • K.Sabitha Banu,

  • H.Peer oli,

Abstract

In this study, we present a comprehensive approach for the classification of eye diseases, specifically targeting normal, cataract, glaucoma, and diabetic retinopathy conditions. This research uses a dataset from Kaggle, which provides a wide and varied collection of retinal images to ensure good representation. The methodology encompasses advanced image processing and machine learning techniques to ensure accurate diagnosis and prediction. The preprocessing phase involves a series of image enhancement techniques to improve the quality and features of retinal images. These techniques include histogram equalization, conversion to grayscale (rgb2gray), discrete wavelet transform (DWT), Haar wavelet transform, and Gaussian filtering. These steps are essential to highlight the relevant features and reduce noise, thereby facilitating better segmentation and classification. For the segmentation phase, we employ the k-means clustering algorithm combined with Gaussian blur. This method successfully groups the retinal images into useful clusters, making it easier to extract important features and accurately pinpoint the areas of interest. During the classification stage, we use several machine learning models such as Decision Tree, Random Forest, Support Vector Machine (SVM), Naïve Bayes, Boosted Trees, and an Ensemble Classifier. Each classifier is thoroughly trained and tested using k-fold cross-validation, which helps ensure reliable performance results like accuracy, sensitivity, and specificity. To further enhance the performance and reliability of the classification system, we incorporate the Synthetic Minority Over-sampling Technique (SMOTE) to balance the dataset and address class imbalances. This step helps train the classifiers on a more balanced and representative dataset, which enhances their ability to make accurate predictions. The final prediction is obtained through an ensemble voting mechanism, where the individual predictions of all classifiers are combined to determine the most probable class for each test image. This majority voting approach leverages the strengths of each classifier, resulting in a more accurate and reliable diagnosis. Experimental results after hyperparameter tuning demonstrate that the proposed system achieves exceptionally high accuracy, sensitivity, and specificity in classifying normal, cataract, glaucoma, and diabetic retinopathy conditions, making it a valuable tool for automated eye disease diagnosis.

Keywords: Eye disease classification, k-means clustering, image segmentation, machine learning, ensemble voting, Decision Tree

[This article belongs to International Journal of Bioinformatics and Computational Biology ]

How to cite this article:
E.Dhiravidachelvi, S.Vengatesh Kumar, K.Sabitha Banu, H.Peer oli. Eye Disease Classification Using K-means Clustering Algorithm and Ensemble Classification Approach. International Journal of Bioinformatics and Computational Biology. 2025; 03(02):-.
How to cite this URL:
E.Dhiravidachelvi, S.Vengatesh Kumar, K.Sabitha Banu, H.Peer oli. Eye Disease Classification Using K-means Clustering Algorithm and Ensemble Classification Approach. International Journal of Bioinformatics and Computational Biology. 2025; 03(02):-. Available from: https://journals.stmjournals.com/ijbcb/article=2025/view=216477


References

1. Zhang X, Homma N, Goto S, Yosuke Kawasumi, Ishibashi T, Abe M, et al. A Hybrid Image Filtering Method for Computer-Aided Detection of Microcalcification Clusters in Mammograms. Journal of Medical Engineering 2013;1–8.

2. Ramakrishna N, Kohir VV. Diabetic Retinopathy Detection at Early Stage Using a Set of Morphological Operations. Lecture Notes in Electrical Engineering 2021;467–78.

3. Amin J, Sharif M, Yasmin M. A Review on Recent Developments for Detection of Diabetic Retinopathy. Scientifica (Cairo). 2016;2016:6838976. doi: 10.1155/2016/6838976.

4. Meltem Esengönül, Cunha A. Glaucoma Detection using Convolutional Neural Networks for Mobile Use. Procedia Computer Science 2023 ;219:1153–60.

5. Alawad M, Aljouie A, Alamri S, Alghamdi M, Alabdulkader B, Alkanhal N, Almazroa A. Machine Learning and Deep Learning Techniques for Optic Disc and Cup Segmentation – A Review. Clin Ophthalmol. 2022 Mar 11;16:747-764.

6. Abdel-Hamid L. Glaucoma Detection from Retinal Images Using Statistical and Textural Wavelet Features. J Digit Imaging. 2020 Feb;33(1):151-158. doi: 10.1007/s10278-019-00189-0.

7. Son KY, Ko J, Kim E, Lee SY, Kim MJ, Han J, Shin E, Chung TY, Lim DH. Deep Learning-Based Cataract Detection and Grading from Slit-Lamp and Retro-Illumination Photographs: Model Development and Validation Study. Ophthalmol Sci. 2022 Mar 18;2(2):100147. doi: 10.1016/j.xops.2022.

8. Imran A, Li J, Pei Y, Akhtar F, Mahmood T, Zhang L. Fundus image-based cataract classification using a hybrid convolutional and recurrent neural network. The Visual Computer 2020 Nov 8 37(8):2407–17.

9. Salim Lahmiri, Stelios Bekiros. Intelligent forecasting with machine learning trading systems in chaotic intraday Bitcoin market. Chaos Solitons & Fractals 2020;133:109641–1.

10. Nadeem MW, Goh HG, Hussain M, Liew SY, Andonovic I, Khan MA. Deep Learning for Diabetic Retinopathy Analysis: A Review, Research Challenges, and Future Directions. Sensors (Basel). 2022 Sep 8;22(18):6780. doi: 10.3390/s22186780.

11. Wiharto W, Suryani E. The Comparison of Clustering Algorithms K-Means and Fuzzy C-Means for Segmentation Retinal Blood Vessels. Acta Inform Med. 2020 Mar;28(1):42-47. doi: 10.5455/aim.2020.28.42-47.

12. Md. Jahiruzzaman, Hossain ABMA. Detection and classification of diabetic retinopathy using K-means clustering and fuzzy logic. 2015 Dec 1;534–8. Available from: https://www.researchgate.net/publication/306294154_Detection_and_Classification_of_Diabetic_Retinopathy_Using_K-Means_Clustering_and_Fuzzy_Logic

13. Lam C, Yi D, Guo M, Lindsey T. Automated Detection of Diabetic Retinopathy using Deep Learning. AMIA Jt Summits Transl Sci Proc. 2018 May 18;2017:147-155.

14. Wu CW, Chen HY, Chen JY, Lee CH. Glaucoma Detection Using Support Vector Machine Method Based on Spectralis OCT. Diagnostics (Basel). 2022 Feb 3;12(2):391. doi: 10.3390/diagnostics12020391.

15. Du, F., Zhao, L., Luo, H. et al. Recognition of eye diseases based on deep neural networks for transfer learning and improved D-S evidence theory. BMC Med Imaging 24, 19 (2024). https://doi.org/10.1186/s12880-023-01176-2

16. Gogula SV, Divakar Ch, Satyanarayana Ch, Rao AA. A diabetic retinopathy detection method using an improved pillar K-means algorithm. Bioinformation. 2014 Jan 29;10(1):28-32. doi: 10.6026/97320630010028.

17. Abbaraju Sai Sathwik, Agarwal R, Ajith Jubilson E, Basa SS. Diabetic Retinopathy Classification Using Deep Learning. EAI Endorsed Transactions on Pervasive Health and Technology 2023 Nov 8;9. Available from: https://www.researchgate.net/publication/375499909_Diabetic_Retinopathy_Classification_Using_Deep_Learning

18. Gurcan OF, Beyca OF, Dogan O. A Comprehensive Study of Machine Learning Methods on Diabetic Retinopathy Classification. International Journal of Computational Intelligence Systems 2021;14(1):1132.

19. P. A. Aquino, M. E. G. Bernardino, and C. G. Bautista, “K-means clustering for segmentation of fundus images for diabetic retinopathy classification,” in IEEE Access, 2020.

20. J. Surendiran, Meena M. Classification of Glaucoma Using K-Mean Clustering with Optic Disk and Cup Segmentation. 2022 Dec 28;97–102.

21. Marouf AA, Mottalib MM, Alhajj R, Rokne J, Jafarullah O. An Efficient Approach to Predict Eye Diseases from Symptoms Using Machine Learning and Ranker-Based Feature Selection Methods. Bioengineering (Basel). 2022 Dec 24;10(1):25. doi: 10.3390/bioengineering10010025.

22. Sathwik AS, Agarwal R, Jubilson E A, Basa SS. Diabetic Retinopathy Classification Using Deep Learning. EAI Endorsed Transactions on Pervasive Health and Technology. 2023 Nov 8;9. Available from: https://www.researchgate.net/publication/375499909_Diabetic_Retinopathy_Classification_Using_Deep_Learning

23. Usman TM, Saheed YK, Ignace D, Nsang A. Diabetic retinopathy detection using principal component analysis multi-label feature extraction and classification. International Journal of Cognitive Computing in Engineering 2023 Jun;4:78–88.

24. Verma PK, Kaur J. Systematic Review of Retinal Blood Vessels Segmentation Based on AI-driven Technique. J Imaging Inform Med. 2024 Aug;37(4):1783-1799. doi: 10.1007/s10278-024-01010-3.

25. B K, Jaya KR, A. P., Bhuvaneswari, H. L., Gururaj, Ravi V, Almeshari M, et al. A Novel Application of K-means Cluster Prediction Model for Diabetes Early Identification using Dimensionality Reduction Techniques. The Open Bioinformatics Journal 2023;16(1).

26. Nikos Tsiknakis, Theodoropoulos D, Georgios Manikis, Emmanouil Ktistakis, Ourania Boutsora, Berto A, et al. Deep learning for diabetic retinopathy detection and classification based on fundus images: A review. Computers in Biology and Medicine 2021 Jun 25 135:104599–9. Available from:https://www.sciencedirect.com/science/article/pii/S0010482521003930

27. Kamble R, Kokare M, Deshmukh G, Hussin FA, Mériaudeau F. Localization of optic disc and fovea in retinal images using intensity based line scanning analysis. Computers in Biology and Medicine 2017 Aug;87:382–96.

28. Velpula VK, Vadlamudi J, Kasaraneni PP, Kumar YVP. Automated Glaucoma Detection in Fundus Images Using Comprehensive Feature Extraction and Advanced Classification Techniques. ECSA-11 2024 Nov;33.

29. Agarwal DK. Diabetic Retinopathy Detection Using Convolution Neural Networks. International Journal of Intelligent Systems and Applications in Engineering 2023 Mar 6 12(22s):1873–7.

30. Badah N, Algefes A, AlArjani A, Mokni R. Automatic Eye Disease Detection Using Machine Learning and Deep Learning Models. Lecture Notes in Networks and Systems 2022 Sep 2 773–87.

Regular Issue Subscription Original Research
Volume 03
Issue 02
Received 29/01/2025
Accepted 25/04/2025
Published 09/07/2025
Publication Time 161 Days
Total Visits: 90


My IP

PlumX Metrics