Journals / Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji / 2026 / Cilt: 14 Sayı: 3

A Hybrid Classification Approach for Glaucoma Diagnosis with MultiSURF Feature Selection

MultiSURF Özellik Seçimi ile Glokom Tanısı için Hibrit Bir Sınıflandırma Yaklaşımı

Halil İbrahim Sarı(KÜTAHYA DUMLUPINAR ÜNİVERSİTESİ)0009-0006-3964-3101
Kübra Keser(KÜTAHYA DUMLUPINAR ÜNİVERSİTESİ)0000-0001-7215-7232
Pages
1586–1607
Publication Date
2026-09-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Experimental results demonstrate that the proposed hybrid framework can accurately distinguish between individuals with glaucoma and those without, with high accuracy.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:asymptomatic in its early stages.
📊
Key Findings & Data:This situation increases the need for automated and reliable screening systems, especially those based on retinal fundus images.
💡
Conclusion & Impact:Experimental results demonstrate that the proposed hybrid framework can accurately distinguish between individuals with glaucoma and those without, with high accuracy.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Glokom · Retinal fundus görüntüleri · Hibrit sınıflandırma

Abstract

asymptomatic in its early stages. This situation increases the need for automated and reliable screening systems, especially those based on retinal fundus images. This study presents a hybrid classification framework for glaucoma detection that combines classical image processing methods with deep learning-based representations, possessing the potential to support clinical processes and exhibiting generalizability. In the proposed approach, deep features obtained from the fc7 layer of a pre-trained AlexNet architecture, along with HSV colour histograms, Haralick textural features, LBP and HOG descriptors, are combined using the ORIGA retinal fundus dataset. The class imbalance problem was addressed by applying the SMOTE method exclusively to the training data, while the high-dimensional feature space was optimised using the MultiSURF algorithm. The selected features obtained were evaluated using Support Vector Machines (SVM), Random Forest (RF), and XGBoost classifiers. Experimental results demonstrate that the proposed hybrid framework can accurately distinguish between individuals with glaucoma and those without, with high accuracy. Specifically, the Random Forest model demonstrated the highest performance with 96.92% accuracy, an F1 score of 0.939, and an AUC value of 0.994. The findings reveal that the combined use of deep and hand-crafted features, supported by MultiSURF-based feature selection and balanced learning strategies, offers a robust and stable solution for glaucoma detection. The proposed approach is considered an automated glaucoma screening method with the potential to be integrated into clinical decision support systems for early diagnosis.

Özet

Glokom, geri dönüşü olmayan görme kaybına yol açabilen ve erken evrelerinde genellikle asemptomatik olan ciddi bir optik nöropatidir. Bu durum, özellikle retina fundus görüntülerine dayalı otomatik ve güvenilir tarama sistemlerine olan ihtiyacı artırmaktadır. Bu çalışmada, glokom tespiti için klasik görüntü işleme yöntemlerini derin öğrenme tabanlı temsillerle birleştiren, klinik süreçleri destekleme potansiyeline sahip ve genelleştirilebilir nitelikte hibrit bir sınıflandırma çerçevesi sunulmaktadır. Önerilen yaklaşımda, önceden eğitilmiş bir AlexNet mimarisinin fc7 katmanından elde edilen derin özellikler, HSV renk histogramları, Haralick dokusal özellikleri, LBP ve HOG tanımlayıcıları ile birlikte ORIGA retina fundus veri seti kullanılarak birleştirilmiştir. Sınıf dengesizliği sorunu, SMOTE yönteminin yalnızca eğitim verilerine uygulanmasıyla ele alınırken, yüksek boyutlu özellik alanı MultiSURF algoritması kullanılarak optimize edilmiştir. Elde edilen seçilen özellikler, Destek Vektör Makineleri (SVM), Rastgele Orman (RF) ve XGBoost sınıflandırıcıları kullanılarak değerlendirilmiştir. Deneysel sonuçlar, önerilen hibrit çerçevenin, glokomlu bireyleri glokomsuz bireylerden yüksek doğrulukla ayırt edebildiğini göstermektedir. Özellikle, Rastgele Orman modeli %96,92 doğruluk, 0,939 F1 puanı ve 0,994 AUC değeri ile en yüksek performansı göstermiştir. Bulgular, MultiSURF tabanlı özellik seçimi ve dengeli öğrenme stratejileriyle desteklenen derin ve el yapımı özelliklerin birleşik kullanımının, glokom tespiti için sağlam ve istikrarlı bir çözüm sunduğunu ortaya koymaktadır. Önerilen yaklaşım, erken teşhis için klinik karar destek sistemlerine entegre edilebilecek potansiyele sahip otomatik bir glokom tarama yöntemi olarak değerlendirilmektedir.

🔖

Cite This Article

Sarı, H. İ., Keser, K. (2026). A Hybrid Classification Approach for Glaucoma Diagnosis with MultiSURF Feature Selection. Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, Cilt: 14 Sayı: 3, 1586–1607. https://doi.org/10.29109/gujsc.1910949

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (73)

  1. KUMRULAR RK. and POLAT A. Klinik Uygulamalarda İleri Biyomedikal Görüntüleme Teknolojileri. European Journal of Science and Technology, 23(1-5), (2021). https://doi.org/10.31590/ejosat.840321
  2. Zubair M., Hussain M., Al-Bashrawi A., Bendechache M. and Owais M. A Comprehensive Review of Techniques, Algorithms, Advancements, Challenges, and Clinical Applications of Multi-Modal Medical Image Fusion for Improved Diagnosis. IEEE Access, 12(1420-1445), (2024). https://doi.org/10.1109/ACCESS.2024.3351234
  3. Chin CW., Yazid H. and Lee HL. Challenges, Advances, and Evaluation Metrics in Medical Image Enhancement: A Systematic Literature Review. Archives of Computational Methods in Engineering, 30(2411–2435), (2023). https://doi.org/10.1007/s11831-023-09890-w
  4. Kierszenbaum, A. L., & Tres, L. (2015). Histology and Cell Biology: an introduction to pathology E-Book. Elsevier Health Sciences, (600-612), (2019).
  5. Moore KL., Agur AMR. and Dalley AF. (2018). Clinically Oriented Anatomy (Eighth Edition). Wolters Kluwer, 12(230-245).
  6. Purves D. and Williams SM. (2001). Neuroscience (Second Edition). Sinauer Associates, 8(150-162).
  7. T.C. Sağlık Bakanlığı. Sağlık İstatistikleri Yıllığı. https://www.saglik.gov.tr/TR%2C2591/2591.Html, (2021). (Erişim Tarihi: 12.02.2026).
  8. National Eye Institute (NEI). Glaucoma. https://www.nei.nih.gov/eye-health-information/eye-conditions-and-diseases/glaucoma, (2024). (Erişim Tarihi: 15.01.2026).
  9. National Eye Institute (NEI). Diabetic Retinopathy Guide. https://www.nei.nih.gov/learn-about-eye-health/eye-conditions-and-diseases/diabetic-retinopathy, (2023). (Erişim Tarihi: 15.01.2026).
  10. National Eye Institute (NEI). Age-Related Macular Degeneration. https://www.nei.nih.gov/learn-about-eye-health/eye-conditions-and-diseases/age-related-macular-degeneration, (2023). (Erişim Tarihi: 15.01.2026).
  11. John, F. (2020). Salmon. Kanski’s Clinical Ophthalmology: A Systematic Approach. Elsevier, 20(1), 9.
  12. Glaucoma Research Foundation. Glaucoma Facts and Stats. https://glaucoma.org/articles/glaucoma-facts-and-stats, (2023). (Erişim Tarihi: 10.03.2026).
  13. Chen TC., Mansberger SL., Chang RT., Do AT., Girkin CA., Herndon LW., Noecker RJ., Qiu M. and Shah MM. Glaucoma Care at the Golden Gate and Beyond. Ophthalmology, 130(45-52), (2023).
  14. Broadway DC. Visual Field Testing for Glaucoma - a Practical Guide. Community Eye Health, 25(66–70), (2012).
  15. Oğuz H. and Esen F. Glokomun Teşhis ve Takibinde Görme Alanı. Turkiye Klinikleri J Ophthalmol-Special Topics 11(1):38-47, 2018.
  16. American Academy of Ophthalmology (AAO). What Is Glaucoma: Diagnosis and Screening. https://www.aao.org/eye-health/diseases/what-is-glaucoma#diagnosis, (2024). (Erişim Tarihi: 19.03.2026).
  17. Bussel II., Wollstein G. and Schuman JS. OCT for Glaucoma Diagnosis, Screening and Detection of Glaucoma Progression. British Journal of Ophthalmology, 98(15–19), (2014). https://doi.org/10.1136/bjophthalmol-2013-304326
  18. Khodeiry MM., Colvin E., Ayoubi M., Mendoza X. and Kostic M. Applications of Optical Coherence Tomography in Optic Nerve Head Diseases: A Narrative Review. Diagnostics, 15(3001), (2025). https://doi.org/10.3390/diagnostics15233001
  19. Kaya M. and Bilgen Y. ViT Tabanlı Hibrit Öğrenme Yöntemleri Ile Göz Tansiyonu Hastalığının Tespiti. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 13(248–265), (2025). https://doi.org/10.29130/dubited.1494138
  20. Juneja M., Thakur S., Uniyal A., Wani A., Thakur N. and Jindal P. Deep Learning-Based Classification Network for Glaucoma in Retinal Images. Computers and Electrical Engineering, 101(108009), (2022). https://doi.org/10.1016/j.compeleceng.2022.108009
  21. Urmamen E. and Koçer S. Retinal Hastalıkların Teşhisi Için Optik Koherans Tomografi Görüntülerinin Derin Öğrenme Metotları Ile Sınıflandırılması. Eskişehir Türk Dünyası Uygulama ve Araştırma Merkezi Bilişim Dergisi, 4(22–28), (2023). https://doi.org/10.53608/estudambilisim.1310906
  22. Ayan F. and Serttaş S. Derin Öğrenme Modelleri Kullanarak Retina Hastalığı Sınıflandırması. Beykent Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 18(53–64), (2025). https://doi.org/10.20854/bujse.1612453
  23. Sudhan MB., Sinthuja M., Pravinth Raja S., Amutharaj J., Charlyn Pushpa Latha G., Sheeba Rachel S., Anitha T., Rajendran T. and Waji YA. Segmentation and Classification of Glaucoma Using U-Net with Deep Learning Model. Journal of Healthcare Engineering, 2022(1–10), (2022). https://doi.org/10.1155/2022/1601354
  24. Uçar M. Glokom Hastalığının Evrişimli Sinir Ağı Mimarileri Ile Tespiti. DEU Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 23(521–529), (2021). https://doi.org/10.21205/deufmd.2021236815
  25. Gök, A. E., & Tasdemır, S. (2024). Detection of Retinal Diseases from Fundus Images Using Deep Learning and Adaptive Histogram Equality. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi, 40(1), (123-135), (2024).
  26. Şahin Sadık E. Determination of Glaucoma Disease with Gray Level Co-Occurrence Matrix Features. European Journal of Science and Technology, 38(124-131), (2022). https://doi.org/10.31590/ejosat.1202569
  27. Thakur N. and Juneja M. Classification of Glaucoma Using Hybrid Features with Machine Learning Approaches. Biomedical Signal Processing and Control, 62(102137), (2020). https://doi.org/10.1016/j.bspc.2020.102137
  28. Joshi S., Partibane B., Hatamleh WA., Tarazi H., Yadav CS. and Krah D. Glaucoma Detection Using Image Processing and Supervised Learning for Classification. Journal of Healthcare Engineering, 2022(1–12), (2022). https://doi.org/10.1155/2022/2988262
  29. Latif J., Tu S., Xiao C., Ur Rehman S., Imran A. and Latif Y. ODGNet: A Deep Learning Model for Automated Optic Disc Localization and Glaucoma Classification Using Fundus Images. SN Applied Sciences, 4(98), (2022). https://doi.org/10.1007/s42452-022-04984-3
  30. Sonti K. and Dhuli R. A New Convolution Neural Network Model “KR-NET” for Retinal Fundus Glaucoma Classification. Optik, 283(170861), (2023). https://doi.org/10.1016/j.ijleo.2023.170861
  31. Jun TJ., Eom Y., Kim D., Kim C., Park JH., Nguyen HM., Kim YH. and Kim D. TRk-CNN: Transferable Ranking-CNN for Image Classification of Glaucoma, Glaucoma Suspect, and Normal Eyes. Expert Systems with Applications, 182(115211), (2021). https://doi.org/10.1016/j.eswa.2021.115211
  32. Yıldırım Ö. and Altunbey Özbay F. Fundus Görüntülerinden Derin Öğrenme Teknikleri Ile Glokom Hastalığının Tespiti. European Journal of Science and Technology, 41(98-105), (2022). (makale) https://doi.org/10.31590/ejosat.1216404
  33. Camara J., Neto A., Pires IM., Villasana MV., Zdravevski E. and Cunha A. Literature Review on Artificial Intelligence Methods for Glaucoma Screening, Segmentation, and Classification. Journal of Imaging, 8(19), (2022). https://doi.org/10.3390/jimaging8020019
  34. Thanki R. A Deep Neural Network and Machine Learning Approach for Retinal Fundus Image Classification. Healthcare Analytics, 3(100140), (2023). https://doi.org/10.1016/j.health.2023.100140
  35. Juhsz F. ORIGA Retinal Fundus Image Dataset. Kaggle Repository. https://www.kaggle.com/datasets/ferencjuhsz/origa-retinal-fundus-image-dataset, (2020). (Erişim Tarihi: 12.03.2026).
  36. MIT License Repository. Academic Software Terms and Conditions. https://www.mit.edu/~amini/LICENSE.md, (2018). (Erişim Tarihi: 19.03.2026).
  37. Saipureddi L. Drishti-GS Retina Dataset for ONH Segmentation. Kaggle Repository. https://www.kaggle.com/datasets/lokeshsaipureddi/drishtigs-retina-dataset-for-onh-segmentation, (2020). (Erişim Tarihi: 14.03.2026).
  38. Https://Medimrg.Webs.Ull.Es/. (Erişim Tarihi: 09.06.2026).
  39. Pena-Betancor C., Gonzalez-Hernandez M., Fumero-Batista F., Sigut J., Medina-Mesa E., Alayon S. and De La Rosa MG. Estimation of the relative amount of hemoglobin in the cup and neuroretinal rim using stereoscopic color fundus images. Investigative Ophthalmology & Visual Science, 56(1562–1568), (2015). https://doi.org/10.1167/iovs.14-15592
  40. Camargo A. and Smith JS. An Image-Processing Based Algorithm to Automatically Identify Plant Disease Visual Symptoms. Biosystems Engineering, 102(9–21), (2009). https://doi.org/10.1016/j.biosystemseng.2008.09.030
  41. Burambekova A. and Shamoi P. Comparative Analysis Of Color Models For Human Perception And Visual Color Difference. Journal of Computer Science and Technology, 5(12-19), (2024).
  42. Jäckl B., Metz Y., Schlegel U., Keim DA. and Fischer MT. Leveraging Color Channel Independence for Improved Unsupervised Object Detection. Pattern Recognition Letters, 178(44-51), (2024).
  43. Khattab D., Ebied HM., Hussein AS. and Tolba MF. Color Image Segmentation Based on Different Color Space Models Using Automatic GrabCut. The Scientific World Journal, 2014(1–10), (2014). https://doi.org/10.1155/2014/126025
  44. Mohd Ali N., Md Rashid NKA. and Mustafah YM. Performance Comparison between RGB and HSV Color Segmentations for Road Signs Detection. Applied Mechanics and Materials, 393(550–555), (2013). https://doi.org/10.4028/www.scientific.net/AMM.393.550
  45. Krizhevsky A., Sutskever I. and Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60(84-90), (2017). https://doi.org/10.1145/3065386
  46. Nielsen MA. (2015). Neural Networks and Deep Learning. Determination Press, 15,24.
  47. Simonyan K. and Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv Preprint arXiv:1409.1556, 1(1-14), (2015).
  48. Yosinski J., Clune J., Bengio Y. and Lipson H. How Transferable Are Features in Deep Neural Networks? Advances in Neural Information Processing Systems, 27(3320-3328), (2014).
  49. Rawat W. and Wang Z. Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review. Neural Computation, 29(2352–2449), (2017). https://doi.org/10.1162/neco_a_00990
  50. He H. and Garcia EA. Learning from Imbalanced Data. IEEE Transactions on Knowledge and Data Engineering, 21(1263–1284), (2009). https://doi.org/10.1109/TKDE.2008.239
  51. Chawla NV., Bowyer KW., Hall LO. and Kegelmeyer WP. SMOTE: Synthetic Minority Over-Sampling Technique. Journal of Artificial Intelligence Research, 16(321–357), (2002). https://doi.org/10.1613/jair.953
  52. Hamid MA. and Subhiyakto ER. Performance Comparison of Random Forest, SVM, and XGBoost Algorithms with SMOTE for Stunting Prediction. Journal of Applied Informatics and Computing, 9(1163–1169), (2025). https://doi.org/10.30871/jaic.v9i4.9701
  53. Hidayat R., Mahdiana D. and Fergina A. Comparative Analysis of Logistic Regression, SVM, Xgboost, and Random Forest Algorithms for Diabetes Classification. Jurnal Teknologi Sistem Informasi dan Aplikasi, 7(281–291), (2024). https://doi.org/10.32493/jtsi.v7i1.38258
  54. Alpaydin, E. (2020). Introduction to machine learning. MIT press, 120-135.
  55. Noble WS. What Is a Support Vector Machine? Nature Biotechnology, 24(1565–1567), (2006). https://doi.org/10.1038/nbt1206-1565
  56. Breiman L. Random Forests. Machine Learning, 45(5–32), (2001). https://doi.org/10.1023/A:1010933404324
  57. Hastie T., Tibshirani R. and Friedman J. (2009). The Elements of Statistical Learning (Second Edition). Springer New York, 200-225.
  58. Chen T. and Guestrin C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 22(785–794), (2016). https://doi.org/10.1145/2939672.2939785
  59. Friedman JH. Greedy Function Approximation: A Gradient Boosting Machine. The Annals of Statistics, 29(1189-1232), (2001). https://doi.org/10.1214/aos/1013203451
  60. Kostas, K. Basitçe Accuracy, Precision, Recall ve F1 Score. (2021).
  61. Bragança CP., Torres JM., Soares CP. and Macedo LO. Detection of Glaucoma on Fundus Images Using Deep Learning on a New Image Set Obtained with a Smartphone and Handheld Ophthalmoscope. Healthcare, 10(2345), (2022). https://doi.org/10.3390/healthcare10122345
  62. Ajitha S., Akkara JD. and Judy MV. Identification of Glaucoma from Fundus Images Using Deep Learning Techniques. Indian Journal of Ophthalmology, 69(2702–2709), (2021). https://doi.org/10.4103/ijo.IJO_92_21
  63. Hemelings R., Elen B., Barbosa-Breda J., Blaschko MB., De Boever P. and Stalmans I. Deep Learning on Fundus Images Detects Glaucoma beyond the Optic Disc. Scientific Reports, 11(20313), (2021). https://doi.org/10.1038/s41598-021-99605-1
  64. Velpula VK. and Sharma LD. Multi-Stage Glaucoma Classification Using Pre-Trained Convolutional Neural Networks and Voting-Based Classifier Fusion. Frontiers in Physiology, 14(1175881), (2023). https://doi.org/10.3389/fphys.2023.1175881
  65. Chiang YY., Chen CL. and Chen YH. Deep Learning Evaluation of Glaucoma Detection Using Fundus Photographs in Highly Myopic Populations. Biomedicines, 12(1394), (2024). https://doi.org/10.3390/biomedicines12071394
  66. Rajendran, R., Pugalenthi, A. S., Mahendran, D., Akash, N., Thanikachalam, S., and Balasubramaniyam, S. (2025, April). Glaucoma detection with functional CNN using fundus imaging. In AIP Conference Proceedings (Vol. 3279, No. 1, p. 020109). AIP Publishing LLC.
  67. Sharma P., Takahashi N., Ninomiya T., Sato M., Miya T., Tsuda S. and Nakazawa T. A Hybrid Multi Model Artificial Intelligence Approach for Glaucoma Screening Using Fundus Images. NPJ Digital Medicine, 8(130), (2025). https://doi.org/10.1038/s41746-025-01473-w
  68. Şatır E., Azboy F., Aydın A., Arslan H. and Hacıefendioğlu Ş. Veri İndirgeme ve Sınıflandırma Teknikleri Ile Glokom Hastalığı Teşhisi. El-Cezeri Fen ve Mühendislik Dergisi, 3(258-266), (2016). https://doi.org/10.31202/ecjse.258576
  69. Dey A. and Bandyopadhyay S. Automated Glaucoma Detection Using Support Vector Machine Classification Method. British Journal of Medicine and Medical Research, 11(1–12), (2016). https://doi.org/10.9734/BJMMR/2016/19617
  70. Wu CW., Chen HY., Chen JY. and Lee CH. Glaucoma Detection Using Support Vector Machine Method Based on Spectralis OCT. Diagnostics, 12(391), (2022). https://doi.org/10.3390/diagnostics12020391
  71. Phasuk, S., Poopresert, P., Yaemsuk, A., Suvannachart, P., Itthipanichpong, R., Chansangpetch, S.,. and Tantibundhit, C. Automated glaucoma screening from retinal fundus image using deep learning. IEEE Engineering in Medicine and Biology Society (EMBC), 41, 904-907, (2019). https://doi.org/10.1109/EMBC.2019.8857136
  72. Li Z., He Y., Keel S., Meng W., Chang RT. and He M. Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs. Ophthalmology, 125(1199–1206), (2018). https://doi.org/10.1016/j.ophtha.2018.01.023
  73. Phasuk, S., Poopresert, P., Yaemsuk, A., Suvannachart, P., Itthipanichpong, R., Chansangpetch, S.,. and Tantibundhit, C. Automated glaucoma screening from retinal fundus image using deep learning. IEEE Engineering in Medicine and Biology Society (EMBC), 41, 904-907, (2019). https://doi.org/10.1109/EMBC.2019.8857136