Pengembangan Sistem Klasifikasi Retinopati Diabetik Berbasis Tekstur Tapis Gabor pada Pembuluh Darah dan Eksudat Menggunakan SVM
(1) Universitas Sultan Ageng Tirtayasa
(2) Politeknik Bina Trada Semarang
(3) Universitas Sultan Ageng Tirtayasa
(4) Universitas Sultan Ageng Tirtayasa
(5) Universitas Muhammadiyah Semarang, Indonesia
(*) Corresponding Author
Abstract
Retinopati Diabetik (RD) merupakan komplikasi mikrovaskular akibat diabetes melitus yang dapat menyebabkan kebutaan. Deteksi otomatis berbasis citra fundus retina menjadi solusi untuk meningkatkan efisiensi dan akurasi diagnosis. Penelitian ini mengembangkan sistem klasifikasi otomatis tingkat keparahan RD menggunakan metode ekstraksi fitur Tapis Gabor dan algoritma Support Vector Machine (SVM). Citra fundus diklasifikasikan ke dalam empat kelas: normal, mild, moderate, dan severe. Ekstraksi fitur dilakukan pada dua objek utama, yaitu pembuluh darah dan eksudat, menggunakan parameter statistik orde pertama berupa mean, variance, dan entropy dari hasil konvolusi Tapis Gabor. Klasifikasi menggunakan SVM dengan kernel Radial Basis Function dan dievaluasi melalui 10-fold stratified cross-validation. Hasil menunjukkan bahwa sistem berbasis fitur pembuluh darah memberikan akurasi, sensitivitas, dan spesifisitas rerata masing-masing sebesar 92,9%, 92,9%, dan 96,7%. Sementara itu, sistem berbasis eksudat menghasilkan akurasi 82,1%, sensitivitas 82,1%, dan spesifisitas 94%. Fitur pembuluh darah lebih stabil dalam mengidentifikasi seluruh kelas RD, sedangkan eksudat berkontribusi signifikan pada deteksi tingkat keparahan tinggi. Kombinasi kedua fitur direkomendasikan untuk meningkatkan performa sistem klasifikasi.
Keywords
Full Text:
PDFReferences
S. Matoori, “Diabetes and its Complications,” ACS Pharmacol. Transl. Sci., vol. 5, no. 8, pp. 513–515, 2022, doi: 10.1021/acsptsci.2c00122.
S. A. Antar et al., “Diabetes mellitus: Classification, mediators, and complications; A gate to identify potential targets for the development of new effective treatments,” Biomed. Pharmacother., vol. 168, pp. 1–25, 2023, doi: 10.1016/j.biopha.2023.115734.
T. E. da Silva, I. Christine, and E. M. Djaputra, “Blood Sugar Levels With Neutrophil-Lymphocyte Ratio As a Marker of Diabetes Mellitus In Elderly,” J. Widya Med. Jr., vol. 2, no. 3, pp. 203–208, 2020, doi: 10.33508/jwmj.v2i3.2667.
D. Tomic, J. E. Shaw, and D. J. Magliano, “The burden and risks of emerging complications of diabetes mellitus,” Nat. Rev. Endocrinol., vol. 18, no. 9, pp. 525–539, 2022, doi: 10.1038/s41574-022-00690-7.
D. Zhu, X. Zhang, F. Wang, Q. Ye, C. Yang, and D. Liu, “Irisin rescues diabetic cardiac microvascular injury via ERK1/2/Nrf2/HO-1 mediated inhibition of oxidative stress,” Diabetes Res. Clin. Pract., vol. 183, p. 109170, 2022, doi: 10.1016/j.diabres.2021.109170.
T. Chivese et al., “IDF Diabetes Atlas: The prevalence of pre-existing diabetes in pregnancy – A systematic review and meta-analysis of studies published during 2010–2020,” Diabetes Res. Clin. Pract., vol. 183, p. 109049, 2022, doi: 10.1016/j.diabres.2021.109049.
T. Q. Binh et al., “Corrigendum to ‘A simple nomogram for identifying individuals at high risk of undiagnosed diabetes in rural population’ [Diabet. Res. Clin. Pract. 180 (2021) 109061] (Diabetes Research and Clinical Practice (2021) 180, (S0168822721004204), (10.1016/j.diabres.2021.109061)),” Diabetes Res. Clin. Pract., vol. 183, p. 109184, 2022, doi: 10.1016/j.diabres.2021.109184.
A. Zmysłowska et al., “Next- generation sequencing is an effective method for diagnosing patients with different forms of monogenic diabetes,” Diabetes Res. Clin. Pract., vol. 183, 2022, doi: 10.1016/j.diabres.2021.109154.
F. Becker et al., “Lifetime cost-effectiveness simulation of once-weekly exenatide in type 2 diabetes: A cost-utility analysis based on the EXSCEL trial,” Diabetes Res. Clin. Pract., vol. 183, pp. 1–8, 2022, doi: 10.1016/j.diabres.2021.109152.
H. Wang et al., “IDF Diabetes Atlas: Estimation of Global and Regional Gestational Diabetes Mellitus Prevalence for 2021 by International Association of Diabetes in Pregnancy Study Group’s Criteria,” Diabetes Res. Clin. Pract., vol. 183, p. 109050, 2022, doi: 10.1016/j.diabres.2021.109050.
G. D. Ogle et al., “Global estimates of incidence of type 1 diabetes in children and adolescents: Results from the International Diabetes Federation Atlas, 10th edition,” Diabetes Res. Clin. Pract., vol. 183, p. 109083, 2022, doi: 10.1016/j.diabres.2021.109083.
Z. G. Abbas and A. J. M. Boulton, “Diabetic foot ulcer disease in African continent: ‘From clinical care to implementation’ – Review of diabetic foot in last 60 years – 1960 to 2020,” Diabetes Res. Clin. Pract., vol. 183, p. 109155, 2022, doi: 10.1016/j.diabres.2021.109155.
V. Zanardo, D. Tortora, A. Sandri, L. Severino, P. Mesirca, and G. Straface, “COVID-19 pandemic: Impact on gestational diabetes mellitus prevalence,” Diabetes Res. Clin. Pract., vol. 183, p. 109149, 2022, doi: 10.1016/j.diabres.2021.109149.
E. Bosi, G. Gregori, C. Cruciani, C. Irace, P. Pozzilli, and R. Buzzetti, “The use of flash glucose monitoring significantly improves glycemic control in type 2 diabetes managed with basal bolus insulin therapy compared to self-monitoring of blood glucose: A prospective observational cohort study,” Diabetes Res. Clin. Pract., vol. 183, p. 109172, 2022, doi: 10.1016/j.diabres.2021.109172.
M. Kupis, K. Samelska, A. Zaleska-Żmijewska, and J. Szaflik, “Introduction to pathophysiology of diabetic retinopathy,” Klin. Oczna, vol. 123, no. 2, pp. 69–73, 2021, doi: https://doi.org/10.5114/ko.2021.106907.
A. O. Dan, A. T. Bălășoiu, I. Puiu, A. C. Tănasie, A. E. Târtea, and V. Sfredel, “Retinal Microvascular Alterations in a Patient with Type 1 Diabetes Mellitus, Hemoglobin D Hemoglobinopathy, and High Myopia—Case Report and Review of the Literature,” Diagnostics, vol. 13, no. 18, pp. 1–8, 2023, doi: 10.3390/diagnostics13182934.
D. Iskandar, A. F. S. Pangerang, and A. Nurtania, “Kolerasi Kejadian Retinopati Diabetik Pada Pasien Diabetes Melitus Tipe 2,” Prepotif J. Kesehat. Masy., vol. 8, no. 3, pp. 7685–7690, 2024, doi: 10.31004/prepotif.v8i3.36079.
N. K. Nafia, T. Nugroho, A. Wildan, H. P. Julianti, and H. D. Purnomo, “Berbagai Faktor Risiko Retinopati Diabetik pada Penderita Diabetes Melitus Tipe 2,” Medica Hosp. J. Clin. Med., vol. 8, no. 3, pp. 265–272, 2021, doi: 10.36408/mhjcm.v8i3.596.
O. Mosenzon, A. Y. Y. Cheng, A. A. Rabinstein, and S. Sacco, “Diabetes and Stroke: What Are the Connections?,” J. Stroke, vol. 25, no. 1, pp. 26–38, 2023, doi: 10.5853/jos.2022.02306.
F. Z. Berrichi and A. Belmadani, “Identification of ocular disease from fundus images using CNN with transfer learning,” Indones. J. Electr. Eng. Comput. Sci., vol. 38, no. 1, p. 613, 2025, doi: 10.11591/ijeecs.v38.i1.pp613-621.
S. Vidivelli, P. Padmakumari, C. Parthiban, A. DharunBalaji, R. Manikandan, and A. H. Gandomi, “Optimising deep learning models for ophthalmological disorder classification,” Sci. Rep., vol. 15, no. 1, pp. 1–13, 2025, doi: 10.1038/s41598-024-75867-3.
M. M. I. Abdalla and J. Mohanraj, “Revolutionizing diabetic retinopathy screening and management: The role of artificial intelligence and machine learning,” World J. Clin. Cases, vol. 13, no. 5, pp. 1–13, 2025, doi: 10.12998/wjcc.v13.i5.101306.
K. Kaushik et al., “Residual Network-Based Deep Learning Framework for Diabetic Retinopathy Detection,” J. Database Manag., vol. 36, no. 1, pp. 1–21, 2025, doi: 10.4018/JDM.368006.
D. Das, S. K. Biswas, and S. Bandyopadhyay, “Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification (DRFEC),” Multimed. Tools Appl., vol. 82, no. 19, pp. 29943–30001, 2023, doi: 10.1007/s11042-022-14165-4.
Article Metrics
Abstract view : 9 timesPDF - 8 times
DOI: https://doi.org/10.26714/me.v18i1.18207
Refbacks
- There are currently no refbacks.
Copyright (c) 2025 MEDIA ELEKTRIKA
Editorial Office of Media Elektrika
Universitas Muhammadiyah Semarang FT-FMIPA Building, 7nd Floor. Phone: 085327178613 |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.