Retinal Vessel Segmentation Based On Meta-Heuristic Algorithms

Abstract

The functional losses due to the diabetes disease occurring in the vessels that carry blood to the retina layer causes the Diabetic Retinopathy (DR) disease. The DR which causes vision loss at certain rate in its initial stages, can lead to complete destruction of visual function if it is not correctly diagnosed and treated. In order to diagnose and treat DR with high accuracy, retinal vessel structure should be separated from the retinal image by segmentation and then to be analyzed in detail. In this work, Wild Horse Optimization (WHO) and Bald Eagle Search (Bald Eagle Search, BES) algorithms which are among the most recently proposed meta-heuristic algorithms have been improved as clustering based for retinal vessel segmentation and then their performances have been compared to that of well-known Gray Wolf Optimization (Grey Wolf Optimization, GWO) algorithm.

Keywords

• Retinal vessel segmentation
• Wild horse optimization algorithm
• Bald eagle search optimization algorithm
• Grey wolf optimization algorithm

Meta-Sezgisel Algoritmalara Dayalı Retinal Damar Bölütleme

Öz

Diyabet hastalığına bağlı olarak retina tabakasına kan taşıyan kılcal damarlarda fonksiyon kayıpları oluşmakta ve Diyabetik Retinopati (Diabetic Retinopathy, DR) hastalığı ortaya çıkmaktadır. İlk aşamalarında gözde belirli oranlarda görme kayıplarına yol açan DR hastalığı doğru bir şekilde teşhis ve tedavi edilmez ise görme fonksiyonunun tamamen yok olmasına sebep olabilmektedir. DR hastalığının yüksek doğrulukta teşhis ve tedavi edilebilmesi için retinal damar yapısının bölütleme işlemi ile retina görüntüsünden ayrıştırılması ve analiz edilmesi gerekmektedir. Bu çalışmada, en güncel meta-sezgisel algoritmalardan olan Vahşi At Optimizasyon (Wild Horse Optimization, WHO) ve Kel Kartal Araştırma (Bald Eagle Search, BES) algoritmaları retinal damar bölütlemeye yönelik olarak kümeleme tabanlı geliştirilmiş ve performansları yaygın olarak kullanılan Gri Kurt Optimizasyon (Grey Wolf Optimization, GWO) algoritması ile mukayese edilmiştir.

Anahtar Kelimeler

• Retinal damar bölütleme
• Vahşi at optimizasyon algoritması
• Kel kartal optimizasyon algoritması
• Gri kurt optimizasyon algoritması.

Kaynakça

1. Ali M. H., Kamel S., Hassan M. H., Veliz M. T., An Improved Wild Horse Optimization Algorithm for Reliability Based Optimal DG Planning of Radial Distribution Networks. Energy Reports 8, 582-604, 2022.
2. Alsattar H. A., Zaidan A. A., Zaidan B. B., Novel Meta-Heuristic Bald Eagle Search Optimization Algorithm. Artificial Intelligence Review 53, 2237-2264, 2020.
3. Alonso-Montes C., Vilari˜no D. L., Dudek P., Penedo M. G., Fast Retinal Vessel Tree Extraction: A Pixel Parallel Approach. International Journal of Circuit Theory and Applications 36 (5-6), 641-651, 2008.
4. Budak Ü., Cömert Z., Şengür A., DCCMED-Net: Densely connected and concatenated multi Encoder-Decoder CNNs for retinal vessel extraction from fundus images. Medical Hypotheses 134(109426), 2020.
5. Budak Ü., Alçin Ö. F., Aslan M., Şengür A., Optic Disc Detection in Retinal Images via Faster Regional Convolutional Neural Networks. 1st International Engineering and Technology Symposium, Batman/Turkey, May 03-05, 2018, pp: 731-734.
6. Çetinkaya M. B., Duran H., A Detailed and Comparative Work for Retinal Vessel Segmentation Based on The Most Effective Heuristic Approaches. Biomedical Engineering / Biomedizinische Technik 66(2), 181-200, 2021.
7. Çetinkaya M. B., Duran H., Performance Comparison of Most Recently Proposed Evolutionary, Swarm Intelligence, and Physics-Based Metaheuristic Algorithms for Retinal Vessel Segmentation. Mathematical Problems in Engineering 2022(4639208), 1-25, 2022.
8. Frame A. J., Undrill P. E., Cree M. J., Olson J. A., McHardy K. C., Sharp P. F., Forrester J. V., A Comparison of Computer Based Classification Methods Applied to The Detection of Microaneurysms in Ophthalmic Fluorescein Angiograms. Computers in Biology and Medicine 28(3), 225-238, 1998.

9. Gao J., Chen G., Lin W., An Effective Retinal Blood Vessel Segmentation by Using Automatic Random Walks Based on Centerline Extraction. BioMed Research International 2020(7352129), 1-11, 2020.
10. Guo Y., Budak Ü., Şengür A., Smarandache F., A Retinal Vessel Detection Approach based on Shearlet Transform and Indeterminacy Filtering on Fundus Images. Symmetry 9(10), 1-10, 2017.
11. Jayakumari C., Santhanam T., An Intelligent Approach to Detect Hard and Soft Exudates Using Echo State Neural Network. Information Technology Journal 7(2), 386-395, 2008.
12. Karegowda A. G., Bhattacharyya S., Jayaram M. A., Manjunath A. S., Exudates Detection in Retinal Images Using KNNFP And WKNNFP Classifiers. Artificial Intelligent Systems and Machine Learning 3(7), 419-425, 2011.
13. Kaur A., Kaur P., A Comparative Study of Various Exudate Segmentation Techniques for Diagnosis of Diabetic Retinopathy. International Journal of Current Engineering and Technology 46(1), 142-146, 2016.
14. Kennedy J., Eberhart R., Particle Swarm Optimization. IEEE International Conference on Neural Networks 4, 1942-1948, 1995.
15. Keerthana K., Jayasuriya T. J., Raja N. S. M., Rajinikanth V., Retinal Vessel Extraction Based on Firefly Algorithm Guided Multi-Scale Matched Filter. International Journal of Modern Science and Technology 2(2), 74-80, 2017.
16. Khanal A., Estrada R., Dynamic Deep Networks for Retinal Vessel Segmentation. Frontiers in Computer Science 2(35), 1-13, 2020.
17. Khomri B., Christodoulidis A., Djerou L., Babahenini M. C., Cheriet F., Particle Swarm Optimization Method for Small Retinal Vessels Detection on Multiresolution Fundus Images. Journal of Biomedical Optics 23(5) 056004, 2018.
18. Larsen M., Godt J., Larsen N., Lund-Andersen H., Sjølie A. K., Agardh E., Kalm H., Grunkin M., Owens D. R., Automated Detection of Fundus Photographic Red Lesions in Diabetic Retinopathy. Investigative Ophthalmology and Visual Science 44(2), 761-766, 2003.
19. Melinscak M., Prentasic, P., Loncarik S., Retinal Vessel Segmentation using Deep Neural Networks. 10th International Conference on Computer Vision Theory and Applications 1, 577-582, 2015.
20. Mirjalili S., Mirjalili S. M., Lewis A., Grey Wolf Optimizer. Advances in Engineering Software 69,46-61, 2014.
21. Naruei I., Keynia F., Wild Horse Optimizer: A New Meta-Heuristic Algorithm for Solving Engineering Optimization Problems. Engineering With Computers, https://doi.org/10.1007/s00366-021-01438-z, 2021.
22. Shuangling W., Yilong Y., Guibao C., Benzheng W., Yuanjie Z., Gongping Y., Hierarchical Retinal Blood Vessel Segmentation Based on Feature and Ensemble Learning. Neurocomputing 149(Part B), 708-717, 2015.
23. Soares J. V. B., Leandro J. J. G., Cesar J. R. M., Jelinek H. F., Cree M. J., Retinal Vessel Segmentation Using The 2-D Gabor Wavelet and Supervised Classification. IEEE Medical Imaging 25(9), 1214-1222, 2006.
24. Somasundaram A., Prabhu J., Detection of Exudates for The Diagnosis of Diabetic Retinopathy. International Journal of Innovation and Applied Studies 3(1), 116-120, 2013.
25. Tchinda B. S., Tchiotsop D., Noubom M., Dorr V. L., Wolf D., Retinal Blood Vessels Segmentation Using Classical Edge Detection Filters and The Neural Network. Informatics in Medicine Unlocked 23(100521), 1-8, 2021.
26. Uyen T. V., Nguyen A. B., Laurence A. F. P., Kotagiri R., An Effective Retinal Blood Vessel Segmentation Method Using Multi-Scale Line Detection. Pattern Recognition 46(3), 703-715, 2013.
27. Yağmur F. D., Yapay sinir ağları ile retinada hastalık teşhisi. Haliç Üniversitesi, Fen Bilimleri Enstitüsü, Yüksek Lisans Tezi, 2008.
28. Xu S., Chen Z., Cao W., Zhang F., Tao B., Retinal Vessel Segmentation Algorithm Based on Residual Convolution Neural Network. Frontiers in Bioengineering and Biotechnology 9 (786425), 1-15, 2021.