{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T14:58:38Z","timestamp":1779289118597,"version":"3.51.4"},"reference-count":46,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T00:00:00Z","timestamp":1726444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Eye diseases are defined as disorders or diseases that damage the tissue and related parts of the eyes. They appear in various types and can be either minor, meaning that they do not last long, or permanent blindness. Cataracts, glaucoma, and diabetic retinopathy are all eye illnesses that can cause vision loss if not discovered and treated early on. Automated classification of these diseases from fundus images can empower quicker diagnoses and interventions. Our research aims to create a robust model, BayeSVM500, for eye disease classification to enhance medical technology and improve patient outcomes. In this study, we develop models to classify images accurately. We start by preprocessing fundus images using contrast enhancement, normalization, and resizing. We then leverage several state-of-the-art deep convolutional neural network pre-trained models, including VGG16, VGG19, ResNet50, EfficientNet, and DenseNet, to extract deep features. To reduce feature dimensionality, we employ techniques such as principal component analysis, feature agglomeration, correlation analysis, variance thresholding, and feature importance rankings. Using these refined features, we train various traditional machine learning models as well as ensemble methods. Our best model, named BayeSVM500, is a Support Vector Machine classifier trained on EfficientNet features reduced to 500 dimensions via PCA, achieving 93.65 \u00b1 1.05% accuracy. Bayesian hyperparameter optimization further improved performance to 95.33 \u00b1 0.60%. Through comprehensive feature engineering and model optimization, we demonstrate highly accurate eye disease classification from fundus images, comparable to or superior to previous benchmarks.<\/jats:p>","DOI":"10.3390\/computation12090190","type":"journal-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T07:36:00Z","timestamp":1726472160000},"page":"190","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Bayesian Optimized Machine Learning Model for Automated Eye Disease Classification from Fundus Images"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1323-9700","authenticated-orcid":false,"given":"Tasnim Bill","family":"Zannah","sequence":"first","affiliation":[{"name":"Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka 1341, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8924-1523","authenticated-orcid":false,"given":"Md.","family":"Abdulla-Hil-Kafi","sequence":"additional","affiliation":[{"name":"Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka 1341, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5845-5210","authenticated-orcid":false,"given":"Md. Alif","family":"Sheakh","sequence":"additional","affiliation":[{"name":"Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka 1341, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0132-1717","authenticated-orcid":false,"given":"Md. Zahid","family":"Hasan","sequence":"additional","affiliation":[{"name":"Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka 1341, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4672-4528","authenticated-orcid":false,"given":"Taslima Ferdaus","family":"Shuva","sequence":"additional","affiliation":[{"name":"Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka 1341, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6747-0846","authenticated-orcid":false,"given":"Touhid","family":"Bhuiyan","sequence":"additional","affiliation":[{"name":"Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka 1341, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6173-0483","authenticated-orcid":false,"given":"Md. Tanvir","family":"Rahman","sequence":"additional","affiliation":[{"name":"School of Health and Rehabilitation Sciences, The University of Queensland, Brisbane, QLD 4072, Australia"},{"name":"Department of Information and Communication Technology, Mawlana Bhashani Science and Technology University, Tangail 1902, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8236-5959","authenticated-orcid":false,"given":"Risala Tasin","family":"Khan","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, Jahangirnagar University, Savar, Dhaka 1342, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4721-8798","authenticated-orcid":false,"given":"M. Shamim","family":"Kaiser","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, Jahangirnagar University, Savar, Dhaka 1342, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2822-0657","authenticated-orcid":false,"given":"Md","family":"Whaiduzzaman","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence Research and Optimisation (AIRO), Torrens University, Adelaide, SA 5000, Australia"},{"name":"School of Information Systems, Queensland University of Technology, Brisbane, QLD 4000, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Raza, A., Khan, M.U., Saeed, Z., Samer, S., Mobeen, A., and Samer, A. (2021, January 13\u201314). Classification of Eye Diseases and Detection of Cataract using Digital Fundus Imaging (DFI) and Inception-V4 Deep Learning Model. Proceedings of the 2021 International Conference on Frontiers of Information Technology (FIT), Islamabad, Pakistan.","DOI":"10.1109\/FIT53504.2021.00034"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1278","DOI":"10.1098\/rstb.2010.0300","article-title":"The ageing lens and cataract: A model of normal and pathological ageing","volume":"366","author":"Michael","year":"2011","journal-title":"Philos. Trans. R. Soc. B Biol. Sci."},{"key":"ref_3","first-page":"e30110","article-title":"Endophthalmitis After Cataract Surgery: A Postoperative Complication","volume":"14","author":"Wadbudhe","year":"2022","journal-title":"Cureus"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"489","DOI":"10.4239\/wjd.v6.i3.489","article-title":"Diabetic retinopathy\u2014Ocular complications of diabetes mellitus","volume":"6","author":"Nentwich","year":"2015","journal-title":"World J. Diabetes"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.exer.2010.08.005","article-title":"Pathophysiology of human glaucomatous optic nerve damage: Insights from rodent models of glaucoma","volume":"93","author":"Morrison","year":"2011","journal-title":"Exp. Eye Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1038\/s41433-021-01684-x","article-title":"Eye disease and mortality, cognition, disease, and modifiable risk factors: An umbrella review of meta-analyses of observational studies","volume":"36","author":"Trott","year":"2022","journal-title":"Eye"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1016\/j.mayocpiqo.2022.09.007","article-title":"Updates on the Diagnosis and Management of Glaucoma","volume":"6","author":"Wagner","year":"2022","journal-title":"Mayo Clin. Proc. Innov. Qual. Outcomes"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1038\/s41597-022-01388-1","article-title":"PAPILA: Dataset with fundus images and clinical data of both eyes of the same patient for glaucoma assessment","volume":"9","author":"Kovalyk","year":"2022","journal-title":"Sci. Data"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4828","DOI":"10.1038\/s41467-021-25138-w","article-title":"Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks","volume":"12","author":"Cen","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101414","DOI":"10.1016\/j.imu.2023.101414","article-title":"Optimizing brain tumor classification through feature selection and hyperparameter tuning in machine learning models","volume":"43","author":"Tahosin","year":"2023","journal-title":"Inform. Med. Unlocked"},{"key":"ref_11","first-page":"264","article-title":"Promising artificial intelligence-machine learning-deep learning algorithms in ophthalmology","volume":"8","author":"Balyen","year":"2019","journal-title":"Asia-Pac. J. Ophthalmol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5278196","DOI":"10.1155\/2018\/5278196","article-title":"Applications of artificial intelligence in ophthalmology: General overview","volume":"2018","author":"Lu","year":"2018","journal-title":"J. Ophthalmol."},{"key":"ref_13","unstructured":"Babaqi, T., Jaradat, M., Yildirim, A., Al-Nimer, S., and Won, D. (2023). Eye Disease Classification Using Deep Learning Techniques. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Triwijoyo, B.K., Sabarguna, B.S., Budiharto, W., and Abdurachman, E. (2020). Deep learning approach for classification of eye diseases based on color fundus images. Diabetes Fundus OCT, Elsevier.","DOI":"10.1016\/B978-0-12-817440-1.00002-4"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"101267","DOI":"10.1109\/ACCESS.2021.3094649","article-title":"Classification of Eye Diseases in Fundus Images","volume":"9","author":"Bernabe","year":"2021","journal-title":"IEEE Access"},{"key":"ref_16","first-page":"974","article-title":"Eye Disease Identification Using Deep Learning","volume":"9","author":"Sattigeri","year":"2022","journal-title":"Int. Res. J. Eng. Technol."},{"key":"ref_17","first-page":"442","article-title":"GMD Model Based on Multi-Label Classification for Detection and Diagnosis of Eye Diseases","volume":"5","author":"Yaroshchak","year":"2022","journal-title":"Eur. Mod. Stud. J."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Paradisa, R.H., Bustamam, A., Mangunwardoyo, W., Victor, A.A., Yudantha, A.R., and Anki, P. (2021). Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus Image. Electronics, 11.","DOI":"10.3390\/electronics11010023"},{"key":"ref_19","first-page":"47","article-title":"An Expert System to Predict Eye Disorder Using Deep Convolutional Neural Network","volume":"9","author":"Ahmed","year":"2021","journal-title":"Acad. Platf. J. Eng. Sci."},{"key":"ref_20","unstructured":"(2022). Eye Disease Retinal Images Dataset. Kaggle, Available online: https:\/\/www.kaggle.com\/datasets\/gunavenkatdoddi\/eye-diseases-classification."},{"key":"ref_21","unstructured":"(2019). Cataract and Normal Eye Image Dataset for Cataract Detection. Kaggle, Available online: https:\/\/www.kaggle.com\/datasets\/jr2ngb\/cataractdataset."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Porwal, P., Pachade, S., Kamble, R., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., and Meriaudeau, F. (2018). Indian Diabetic Retinopathy Image Dataset (IDRiD). Data, 3.","DOI":"10.3390\/data3030025"},{"key":"ref_23","unstructured":"(2024, September 01). Glaucoma Detection. Available online: https:\/\/www.kaggle.com\/datasets\/sshikamaru\/glaucoma-detection?select=ACRIMA."},{"key":"ref_24","unstructured":"Erlangen-N\u00fcrnberg, L.F.M.F. (2024, September 01). High-Resolution FundUS (HRF) Image Database. Available online: https:\/\/www5.cs.fau.de\/research\/data\/fundus-images\/."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1109\/TSMCB.2007.909440","article-title":"Human Visual System-Based Image Enhancement and Logarithmic Contrast Measure","volume":"38","author":"Panetta","year":"2008","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"012049","DOI":"10.1088\/1742-6596\/1764\/1\/012049","article-title":"Analysis of contrast limited adaptive histogram equalization (CLAHE) parameters on finger knuckle print identification","volume":"1764","author":"Hana","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_27","first-page":"2630","article-title":"Statistical approach to normalization of feature vectors and clustering of mixed datasets","volume":"468","author":"Pham","year":"2012","journal-title":"Proc. R. Soc. Math. Phys. Eng. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Talebi, H., and Milanfar, P. (2021). Learning to Resize Images for Computer Vision Tasks. arXiv.","DOI":"10.1109\/ICCV48922.2021.00055"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Kumar, G., and Bhatia, P.K. (2014, January 8\u20139). A Detailed Review of Feature Extraction in Image Processing Systems. Proceedings of the 2014 Fourth International Conference on Advanced Computing & Communication Technologies, Rohtak, India.","DOI":"10.1109\/ACCT.2014.74"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ta\u015fci, B. (2023). Deep Learning-Based Approaches Using Feature Selection Methods for Automatic Diagnosis of COVID-19 Disease from X-ray Images, Springer.","DOI":"10.1007\/978-981-99-3784-4_2"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"28936","DOI":"10.1109\/ACCESS.2018.2837654","article-title":"Integrating Feature Selection and Feature Extraction Methods with Deep Learning to Predict Clinical Outcome of Breast Cancer","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/s40008-022-00261-z","article-title":"A new method of identifying key industries: A principal component analysis","volume":"11","author":"Tsoulfidis","year":"2022","journal-title":"J. Econ. Struct."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ciarelli, P.M., and Oliveira, E. (December, January 30). Agglomeration and Elimination of Terms for Dimensionality Reduction. Proceedings of the 2009 Ninth International Conference on Intelligent Systems Design and Applications, Washington, DC, USA.","DOI":"10.1109\/ISDA.2009.9"},{"key":"ref_34","unstructured":"Hall, M. (1999). Correlation-Based Feature Selection for Machine Learning. [Ph.D. Thesis, Department of Computer Science, The University of Waikato]."},{"key":"ref_35","unstructured":"Ambarwati, Y.S., and Uyun, S. (2020, January 10). Feature Selection on Magelang Duck Egg Candling Image Using Variance Threshold Method. Proceedings of the 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Yogyakarta, Indonesia."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Geng, X., Liu, T.Y., Qin, T., and Li, H. (2007, January 23\u201327). Feature Selection for Ranking. Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR `07, Amsterdam, The Netherlands.","DOI":"10.1145\/1277741.1277811"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sheakh, M.A., Tahosin, M.S., Hasan, M.M., Islam, T., Islam, O., and Rana, M.M. (2023, January 11\u201312). Child and Maternal Mortality Risk Factor Analysis Using Machine Learning Approaches. Proceedings of the 2023 11th International Symposium on Digital Forensics and Security (ISDFS), Chattanooga, TN, USA.","DOI":"10.1109\/ISDFS58141.2023.10131826"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"11","DOI":"10.4236\/jcc.2024.121002","article-title":"Lexicon and Deep Learning-Based Approaches in Sentiment Analysis on Short Texts","volume":"12","author":"Islam","year":"2024","journal-title":"J. Comput. Commun."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.ject.2024.01.002","article-title":"A review of cyber attacks on sensors and perception systems in autonomous vehicle","volume":"1","author":"Islam","year":"2023","journal-title":"J. Econ. Technol."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Islam, T., Sheakh, M.A., Tahosin, M.S., Hena, M.H., Akash, S., Jardan, Y.A.B., FentahunWondmie, G., Nafidi, H.A., and Bourhia, M. (2024). Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-57740-5"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Roy, U., Tahosin, M.S., Hasan, M.M., Islam, T., Imtiaz, F., Sadik, M.R., Maleh, Y., Sulaiman, R.B., and Talukder, M.S.H. (2024, January 18\u201319). Enhancing Bangla Fake News Detection Using Bidirectional Gated Recurrent Units and Deep Learning Techniques. Proceedings of the 7th International Conference on Networking, Intelligent Systems and Security, Meknes, Morocco.","DOI":"10.1145\/3659677.3659703"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"220","DOI":"10.4097\/kjae.2015.68.3.220","article-title":"Standard deviation and standard error of the mean","volume":"68","author":"Dong","year":"2015","journal-title":"Korean J. Anesthesiol."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Abudelrahman, A., and Viriri, S. (2023). EfficientNet family U-Net models for deep learning semantic segmentation of kidney tumors on CT images. Front. Comput. Sci., 5.","DOI":"10.3389\/fcomp.2023.1235622"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1109\/TKDE.2005.50","article-title":"Using AUC and accuracy in evaluating learning algorithms","volume":"17","author":"Huang","year":"2005","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Rana, S., Hosen, M.J., Tonni, T.J., Rony, M.A.H., Fatema, K., Hasan, M.Z., Rahman, M.T., Khan, R.T., Jan, T., and Whaiduzzaman, M. (2024). DeepChestGNN: A Comprehensive Framework for Enhanced Lung Disease Identification through Advanced Graphical Deep Features. Sensors, 24.","DOI":"10.3390\/s24092830"},{"key":"ref_46","unstructured":"Lu, Y., Zhang, W., Jin, C., and Xue, X. (2012, January 16\u201321). Learning attention map from images. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA."}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-3197\/12\/9\/190\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:57:27Z","timestamp":1760111847000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-3197\/12\/9\/190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,16]]},"references-count":46,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,9]]}},"alternative-id":["computation12090190"],"URL":"https:\/\/doi.org\/10.3390\/computation12090190","relation":{},"ISSN":["2079-3197"],"issn-type":[{"value":"2079-3197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,16]]}}}