Advanced Edge Detection Techniques for Enhanced Diabetic Retinopathy Diagnosis Using Machine Learning
DOI:
https://doi.org/10.20535/RADAP.2024.97.67-75Keywords:
Diabetic retinopathy, edge detection, machine learning, Sobel operator, Canny edge detector, APTOS 2019, neural networks, medical imaging, early diagnosis, vision impairmentAbstract
Diabetic retinopathy (DR) represents one of the most serious complications associated with diabetes mellitus, posing a significant threat to vision and leading to severe impairment and potential blindness if not diagnosed and treated promptly. The study investigates the integration of advanced edge detection techniques with machine learning algorithms to enhance the precision and effectiveness of DR diagnosis. By leveraging the APTOS 2019 Blindness Detection dataset, the research employs a combination of edge detection methods such as the Sobel operator and the Canny edge detector, alongside advanced preprocessing techniques and sophisticated feature extraction methods. The study reveals that the synergy between these edge detection techniques and machine learning significantly boosts the diagnostic accuracy of neural networks. Specifically, the accuracy for multiclass classification (spanning five categories: No diabetic retinopathy, Mild, Moderate, Severe, and Proliferative diabetic retinopathy) improved from 78.5% to an impressive 88.2%. This marked enhancement underscores the potential of these techniques in refining the diagnostic processes for early DR detection. By improving the accuracy of classification, this approach not only facilitates early intervention but also plays a crucial role in reducing the risk of severe vision loss among patients with diabetes. The findings of this study emphasize the importance of integrating advanced image processing techniques with machine learning frameworks in medical diagnostics. The improved outcomes demonstrated in this research highlight the potential for such technological advancements to contribute meaningfully to the field of ophthalmology, leading to better patient care and potentially transforming the standard of practice in DR diagnosis.
References
References
Yuan Y., Zhang Y., Zhu L., Cai L., Qian Y. (2024). Exploiting Cross-Scale Attention Transformer and Progressive Edge Refinement for Retinal Vessel Segmentation. Mathematics, Vol. 12(2), 264. DOI: 10.3390/math12020264.
Jiang Y., Zhang H., Tan N., Chen L. (2019). Automatic Retinal Blood Vessel Segmentation Based on Fully Convolutional Neural Networks. Symmetry, Vol. 11(9), 1112. DOI: 10.3390/sym11091112.
Gojić G., Kundačina O., Mišković D., Dragan D. (2023). Overview of Deep Learning Methods for Retinal Vessel Segmentation. arXiv. DOI: 10.48550/arXiv.2306.06116.
Shukla U. V., Tripathy K. (2024). Diabetic Retinopathy. StatPearls, Treasure Island (FL): StatPearls Publishing.
NHS. (2021). Diabetic retinopathy. NHS.
Chen W., Xiao L., Bai J., Zeng W., Yang M., Shi B., Zhu C. (2018). The promotion of tissue engineering blood vessel patency by CGS21680 through regulating pro-inflammatory activities of endothelial progenitor cell. J Biomed Mater Res A, Vol. 106(10), pp. 2634-2642. DOI: 10.1002/jbm.a.36457.
Canny J. (1986). A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, Iss. 6, pp. 679-698. DOI: 10.1109/TPAMI.1986.4767851.
Subbiah A., Mahajan S., Yadav R. K., Agarwal S. K. (2018). Intravenous immunoglobulin therapy for dengue capillary leak syndrome in a renal allograft recipient. BMJ Case Rep, 2018:bcr2018225225. DOI: 10.1136/bcr-2018-225225.
Tajbakhsh N., Shin J. Y., Gurudu S. R. et al. (2016). Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? IEEE Trans Med Imaging, Vol. 35(5), pp. 1299-1312. DOI: 10.1109/TMI.2016.2535302.
Gulshan V., Peng L., Coram M. et al. (2016). Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA, Vol. 316(22), pp. 2402-2410. DOI: 10.1001/jama.2016.17216.
Skouta A., Elmoufidi A., Jai-Andaloussi S. et al. (2023). Deep learning for diabetic retinopathy assessments: a literature review. Multimed Tools Appl, Vol. 82, pp. 41701–41766. DOI: 10.1007/s11042-023-15110-9.
Kaggle. APTOS 2019 blindness detection competition. Kaggle.
Armi, L., Fekri-Ershad, S. (2019). Texture image analysis and texture classification methods - A review. International Online Journal of Image Processing and Pattern Recognition, Vol. 2, No. 1, pp. 1-29. DOI: 10.48550/arXiv.1904.06554.
Clausi D. A. (2002). An analysis of co-occurrence texture statistics as a function of gray level quantization. Can J Remote Sens, Vol. 28(1), pp. 45-62. DOI: 10.5589/m02-004.
Venkataramani D., Veeranan J., Pitchai L. (2022). Fractal analysis of retinal vasculature in relation with retinal diseases – a machine learning approach. Nonlinear Engineering, Vol. 11(1), pp. 411-419. DOI: 10.1515/nleng-2022-0233.
Lyu X., Jajal P., Tahir M. Z. et al. (2022). Fractal dimension of retinal vasculature as an image quality metric for automated fundus image analysis systems. Sci Rep, Vol. 12, 11868. DOI: 10.1038/s41598-022-16089-3.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Марко Басараб, Kateryna Ivanko
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
