Blood Vessel Segmentation and Classification of Diabetic Retinopathy with Machine Learning-Based Ensemble Model

Yıl 2024, Cilt: 10 Sayı: 3, 560 - 570, 30.09.2024

Cihan Akyel , Bünyamin Ciylan

https://doi.org/10.28979/jarnas.1482123

Öz

The incidence of diabetes has increased in recent times due to factors such as obesity and genetic predisposition. Diabetes wears out the eye vessels over time. Diabetic retinopathy (DR) is a serious disease that leads to vision problems. DR can be diagnosed by specialists who examine the fundus images of the eye at regular intervals. With 537 million diabetics in 2021, this method can be time-consuming, costly and inadequate. Artificial intelligence algorithms can provide fast and cost-effective solutions for DR diagnosis. In this study, the noise of blood vessels in fundus images was eliminated using the LinkNet-RCB7 model, and diabetic retinopathy was categorized into five classes using a machine learning-based ensemble model. Artificial intelligence-based classification training using images as input takes a long time and requires high resource requirements such as Random Access Memory (RAM) and Graphics Processing Unit (GPU). By using Gray Level Cooccurrence Matrix (GLCM) attributes in the classification phase, a lower resource requirement was aimed for. A Dice coefficient of 85.95% was achieved for the segmentation of blood vessels in the Stare dataset, in addition to 97.46% accuracy for binary classification and 96.10% accuracy for classifying DR into five classes in the dataset APTOS 2019.

Anahtar Kelimeler

Diabetic retinopathy, ensemble learning, classification, segmentation, information systems

Kaynakça

• M. J. Hossain, M. Al-Mamun, M. R. Islam, Diabetes mellitus, the fastest growing global public health concern: Early detection should be focused, Health Science Reports 7 (3) (2024) 1–5.
• S. İnan, Diabetic retinopathy and etiopathogenesis, Kocatepe Medical Journal 15 (2) (2014) 207–217.
• L. Dai, L. Wu, H. Li, C. Cai, Q. Wu, H. Kong, R. Liu, X. Wang, X. Hou, Y. Liu, X. Long, Y. Wen, L. Lu, Y. Shen, Y. Chen, D. Shen, X. Yang, H. Zou, B. Sheng, W. Jia, A deep learning system for detecting diabetic retinopathy across the disease spectrum, Nature Communications 12 (2021) 3242 11 pages.
• Y. B. Özçelik, A. Altan, Ö. Canbolat, Ş. Ekenler, Ü. Polat, Deep learning-based classification of fundus images for the diagnosis of diabetic retinopathy, Europan Journal of Science and Technology (29) (2021) 156–167.
• X. Tan, S. Lai, M. Zhang, Green channel guiding denoising on Bayer image, The Scientific World Journal 2014 (2014) 1–9.
• S. Long, J. Chen, A. Hu, H. Liu, Z. Chen, D. Zheng, Microaneurysms detection in color fundus images using machine learning based on directional local contrast, BioMedical Engineering Online 19 (21) (2020) 1–23.
• Z. Tang, J. Zhang, W. Gui, Selective search and intensity context-based retina vessel image segmentation, Journal of Medical Systems 41 (3) (2017) 1–12.
• S. Guo, K. Wang, H. Kang, Y. Zhang, Y. Gao, T. Li, BTS-DSN: Deeply supervised neural network with short connections for retinal vessel segmentation, International Journal of Medical Informatics 126 (2019) 105–113.
• H. Boudegga, Y. Elloumi, M. Akil, M. H. Bedoui, R. Kachouri, A. B. Abdallah, Fast and efficient retinal blood vessel segmentation method based on deep learning network, Computerized Medical Imaging and Graphics 90 (2021) 101902 12 pages.
• T. Laibacher, T. Weyde, S. Jalali, M2U-Net: Effective and efficient retinal vessel segmentation for real-world applications, in: L. O'Conner (Ed.), IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, 2019, pp. 1–10.
• K. Aurangzeb, S. I. Haider, M. Alhussein, Retinal vessel segmentation based on the anam-net model, Elektronika ir Elektrotechnika 28 (3) (2022) 54–63.
• G. Zhang, B. Sun, Z. Chen, Y. Gao, Z. Zhang, W. Yang, L. Li, Diabetic retinopia grading by deep graph correlation network on retinal images without manual annotations, Frontiers in Medicine 9 (2022) 1–9.
• N. Sikder, M. S. Chowdhury, A. S. Mohammad, A. A. Nahid, Early blindness detection based on retinal images using ensemble learning, 22nd International Conference on Computer and Information Technology (ICCIT), Dhaka, 2019, pp. 1–6.
• H. Liu, K. Yue, S. Cheng, C. Pan, J. Sun, W. Li, Hybrid model structure for diabetic retinopathy classification, Internet of Medical Things for Healthcare Engineering 2020 (2020) Article ID 840174 9 pages.
• S. Majumder, N. Kehtarnavaz, Multitasking deep learning model for detection of five stages of diabetic retinopathy, IEEE Access 9 (2021) 123220–123230.
• P. Modi, Y. Kumar, Smart detection and diagnosis of diabetic retinopathy using bat-based feature selection algorithm and deep forest technique, Computers & Industrial Engineering 182 (2023) 109364 21 pages.
• X. Wang, Y. Wang, W. Chen, Diabetic retinopathy stage classification using convolutional neural networks, in: R. Bilof (Ed.), 2018 IEEE International Conference on Information Reuse and Integration (IRI), UT, 2018, pp. 465–471.
• G. Nagaraj, S. C. Simha, H. G. R. Chandra, M. Indiramma, Deep learning framework for diabetic retinopathy diagnosis, 3rd International Conference on Computing Methodologies and Communication (ICCMC), Erode, 2019, pp. 648–653.
• Z. Wu, G. Shi, Y. Chen, F. Shi, X. Chen, G. Coatrieux, J. Yang, L. Luo, S. Li, Coarse-to-fine classification for diabetic retinopathy grading using convolutional neural network, Artificial Intelligence in Medicine 108 (2020) 1–19.
• K. Rahman, M. Nasor, A. Imran, Automatic screening of diabetic retinopathy using fundus images and machine learning algorithms, Diagnostics 12 (9) (2022) 2262–2274.
• N. Sikder, M. Masud, A. Bairagi, A. Arif, A. Nahid, H. A. Alhumyani, Severity classification of diabetic retinopathy using an ensemble learning algorithm through analyzing retinal images, Symmetry 13 (4) (2021) 670–696.
• U. Ishtiaq, E. Abdullah, Z. Ishtiaque, A hybrid technique for diabetic retinopathy detection based on ensemble-optimized CNN and texture features, Diagnostics 13 (10) (2023) 1–21.
• A. Z. Foeady, D. C. R. Novitasari, A. H. Asyhar, M. Firmansjah, Automated diagnosis system of diabetic retinopathy using GLCM method and SVM classifier, in: A. Yudhana, Zulfatman, D. Stiawan, M. A. Riyadi, I. M. I. Subroto, A. E. Minarno, C. S. K. Aditya (Eds.), 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), Malang, 2018, pp. 153–160.
• V. Deepa, S. Kumar, T. Cherian, Ensemble of multi-stage deep convolutional neural networks for automated grading of diabetic retinopathy using image patches, Journal of King Saud University - Computer and Information Sciences 34 (8) (2022) 6255–6265.
• A. Hoover, V. Kouznetsova, M. Goldbaum, Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response, IEEE Transactions on Medical Imaging 19 (3) (2000) 203–210.
• S. Kılıçarslan, A novel nonlinear hybrid HardSReLUE activation function in transfer learning architectures for hemorrhage classification, Multimedia Tools Applications 82 (2023) 6345–6365.
• C. Közkurt, A. Diker, A. Elen, S. Kılıçarslan, E. Dönmez, F. B. Demir, Trish: An efficient activation function for CNN models and analysis of its effectiveness with optimizers in diagnosing glaucoma, The Journal of Supercomputing 2024 (2024) 1–32.
• J. Staal, M. D. Abràmoff, M. Niemeijer, M. A. Viergever, B. Van Ginneken, Ridge-based vessel segmentation in color images of the retina, IEEE Transactions on Medical Imaging 23 (4) (2004) 501–509.
• K. Dane, M. Dane, S. Dane, APTOS 2019 Blindness Detection (2019), https://kaggle.com/competitions/aptos2019-blindness-detection, Accessed 1 May 2024.
• C. Akyel, N. Arıcı, Decision support system for blood vessel and optic disc segmentation, Gazi Journal of Engineering Sciences, 9 (1) (2023) 12–26.
• C. Akyel, N. Arıcı, LinkNet-B7: Noise removal and lesion segmentation in images of skin cancer, Mathematics 10 (5) (2022) 736–751.
• C. Akyel, N. Arıcı, Hair removal and lesion segmentation with FCN8-ResNetC and Image processing in images of skin cancer, Journal of Information Technologies 15 (2) (2022) 231–238.