Research Article
BibTex RIS Cite

YOLOv8 TABANLI DERİN ÖĞRENME MODELİ İLE DİYABETİK RETİNOPATİ TEŞHİSİ VE SINIFLANDIRMASI

Year 2024, Volume: 27 Issue: 4, 1297 - 1305, 03.12.2024

Ömer Şanver , Ahmet Saygılı

https://doi.org/10.17780/ksujes.1453034

Abstract

Diyabetik retinopati, diyabetin gözlere etki eden bir komplikasyonudur. Yüksek kan şekeri düzeyleri, retinanın damarlarına zarar vererek gözdeki ışığı algılayan hücrelere zarar vermekte ve görme kaybına, ciddi durumlarda ise körlüğe neden olabilmektedir. Derin öğrenme modelleri, büyük veri setlerini işleme ve öğrenme kapasitesine sahip güçlü araçlardır ve diyabet ile diyabetik retinopati teşhisinde de kullanılması durumunda hastalığın erken teşhisine fayda sağlayabilecektir. Derin öğrenme, yüksek hassasiyet ve spesifiklik ile diyabetik retinopati belirtilerinin erken ve yüksek doğrulukla tespit edilmesini ve bunun yanı sıra uzmanlar tarafından yapılan hataların minimize edilmesine olanak sağlar. Gerçekleştirdiğimiz bu çalışmada da CNN mimarilerinden biri olan YOLOv8 modeli kullanılarak diyabetik retinopati hastalığının tespiti ve sınıflandırılması amaçlanmıştır. Çalışmamızda 2 farklı CPU ve 2 farklı GPU ile deneysel çalışmalar yapılmıştır. Yapılan deneysel çalışmalar sonucunda en yüksek doğruluk değeri GPU1 ile %84.91 olarak elde edilmiş ve dört farklı yöntemin (CPU1, CPU2, GPU1, GPU2) ortalama doğruluk değeri de %83.82 olarak elde edilmiştir.

Keywords

Diyabetik Retinopati Derin Öğrenme Yolov8 CNN

References

  • Ansari, P., Tabasumma, N., Snigdha, N. N., Siam, N. H., Panduru, R. V., Azam, S., Hannan, J., & Abdel-Wahab, Y. H. (2022). Diabetic retinopathy: an overview on mechanisms, pathophysiology, and pharmacotherapy. Diabetology, 3(1), 159-175.
  • Arslan Tuncer, Seda & Çinar, Ahmet & Fırat, Murat. (2021). Hybrid CNN Based Computer-Aided Diagnosis System for Choroidal Neovascularization, Diabetic Macular Edema, Drusen Disease Detection from OCT Images. Traitement du Signal. 38. 673-679. 10.18280/ts.380314.
  • Association, A. D. (2022). Standards of medical care in diabetes—2022 abridged for primary care providers. Clinical Diabetes, 40(1), 10-38.
  • Çavli, A., & Toğaçar, M. (2023). Yapay Zekâ Yaklaşımlarını Kullanarak Retinopati Hastalığının Tespiti. Mühendislik Bilimleri ve Araştırmaları Dergisi, 5(1), 88-97.
  • Dai, L., Wu, L., Li, H., Cai, C., Wu, Q., Kong, H., Liu, R., Wang, X., Hou, X., & Liu, Y. (2021). A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nature communications, 12(1), 3242.
  • Deperlıoğlu, Ö., & Köse, U. (2018). Diagnosis of diabetic retinopathy by using image processing and convolutional neural network. 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT),
  • Dugas, E., Jared, J., & Cukierski, W(2015). Diabetic retinopathy detection. URL https://kaggle. com/competitions/diabetic-retinopathy-detection, 7.
  • Dulkadir, S., & Gültekin, G. K. (2023). Tarımsal Otomasyon Sistemleri için Muz Olgunluk Seviyelerinin Derin Öğrenme Yöntemleri İle Sınıflandırılması. EMO Bilimsel Dergi, 13(3), 27-34.
  • Lingling Fang, Huan Qiao(2022),Diabetic retinopathy classification using a novel DAG network based on multi-feature of fundus images,Biomedical Signal Processing and Control,Volume 77, 2022, 103810, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2022.103810.
  • Fong, D. S., Aiello, L., Gardner, T. W., King, G. L., Blankenship, G., Cavallerano, J. D., Ferris III, F. L., Klein, R., & Association, A. D. (2003). Diabetic retinopathy. Diabetes care, 26(suppl_1), s99-s102.
  • Kemal, A., & Takci, H. (2022). Hibrit Bir Model Oluşturarak Diyabetik Retinopati Sınıflandırılması. Avrupa Bilim ve Teknoloji Dergisi(36), 227-236.
  • King, R. Retrieved 01.01.2024 from https://github.com/open-mmlab/mmyolo
  • Özçelik, Y. B., & Altan, A. (2021). Diyabetik retinopati teşhisi için fundus görüntülerinin derin öğrenme tabanlı sınıflandırılması. Avrupa Bilim ve Teknoloji Dergisi(29), 156-167.
  • Özçelik YB, Altan A(2023). Overcoming Nonlinear Dynamics in Diabetic Retinopathy Classification: A Robust AI-Based Model with Chaotic Swarm Intelligence Optimization and Recurrent Long Short-Term Memory. Fractal and Fractional.; 7(8):598. https://doi.org/10.3390/fractalfract7080598
  • Ultralytics. Ultralytics Documentation. . Retrieved 01.02.2024 from https://docs.ultralytics.com/
  • Vujosevic, S., Aldington, S. J., Silva, P., Hernández, C., Scanlon, P., Peto, T., & Simó, R. (2020). Screening for diabetic retinopathy: new perspectives and challenges. The Lancet Diabetes & Endocrinology, 8(4), 337-347. V. Vipparthi, D. R. Rao, S. Mullu and V. Patlolla(2022). "Diabetic Retinopathy Classification using Deep Learning Techniques," 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 2022, pp. 840-846, doi: 10.1109/ICESC54411.2022.9885687.
  • Wong, T. Y., Sun, J., Kawasaki, R., Ruamviboonsuk, P., Gupta, N., Lansingh, V. C., Maia, M., Mathenge, W., Moreker, S., & Muqit, M. M. (2018). Guidelines on diabetic eye care: the international council of ophthalmology recommendations for screening, follow-up, referral, and treatment based on resource settings. Ophthalmology, 125(10), 1608-1622.
  • Yau, J. W., Rogers, S. L., Kawasaki, R., Lamoureux, E. L., Kowalski, J. W., Bek, T., Chen, S.-J., Dekker, J. M., Fletcher, A., & Grauslund, J. (2012). Global prevalence and major risk factors of diabetic retinopathy. Diabetes care, 35(3), 556-564.

DIAGNOSIS AND CLASSIFICATION OF DIABETIC RETINOPATHY WITH YOLOv8-BASED DEEP LEARNING MODEL

Year 2024, Volume: 27 Issue: 4, 1297 - 1305, 03.12.2024

Ömer Şanver , Ahmet Saygılı

https://doi.org/10.17780/ksujes.1453034

Abstract

Diabetic retinopathy is a complication of diabetes that affects the eyes. High blood sugar levels damage the vessels of the retina, damaging the light-sensing cells in the eye, and can cause vision loss and, in severe cases, blindness. Deep learning models are powerful tools that can process and learn large data sets, and if used in the diagnosis of diabetes and diabetic retinopathy, they can benefit the early diagnosis of the disease. Deep learning enables early and high-accuracy detection of diabetic retinopathy symptoms with high sensitivity and specificity, as well as minimizing errors made by experts. In this study, we aimed to detect and classify diabetic retinopathy using the YOLOv8 (You Only Look Once) model, one of the CNN (convolutional neural network) architectures. The experimental studies were conducted with two different CPUs and two different GPUs. As a result of the experimental studies, the highest accuracy value was obtained as 84.91% with GPU1, and the average accuracy across the four different methods (CPU1, CPU2, GPU1, GPU2) was 83.82%.

Keywords

Diabetic Retinopathy Deep Learning Yolov8 CNN

References

  • Ansari, P., Tabasumma, N., Snigdha, N. N., Siam, N. H., Panduru, R. V., Azam, S., Hannan, J., & Abdel-Wahab, Y. H. (2022). Diabetic retinopathy: an overview on mechanisms, pathophysiology, and pharmacotherapy. Diabetology, 3(1), 159-175.
  • Arslan Tuncer, Seda & Çinar, Ahmet & Fırat, Murat. (2021). Hybrid CNN Based Computer-Aided Diagnosis System for Choroidal Neovascularization, Diabetic Macular Edema, Drusen Disease Detection from OCT Images. Traitement du Signal. 38. 673-679. 10.18280/ts.380314.
  • Association, A. D. (2022). Standards of medical care in diabetes—2022 abridged for primary care providers. Clinical Diabetes, 40(1), 10-38.
  • Çavli, A., & Toğaçar, M. (2023). Yapay Zekâ Yaklaşımlarını Kullanarak Retinopati Hastalığının Tespiti. Mühendislik Bilimleri ve Araştırmaları Dergisi, 5(1), 88-97.
  • Dai, L., Wu, L., Li, H., Cai, C., Wu, Q., Kong, H., Liu, R., Wang, X., Hou, X., & Liu, Y. (2021). A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nature communications, 12(1), 3242.
  • Deperlıoğlu, Ö., & Köse, U. (2018). Diagnosis of diabetic retinopathy by using image processing and convolutional neural network. 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT),
  • Dugas, E., Jared, J., & Cukierski, W(2015). Diabetic retinopathy detection. URL https://kaggle. com/competitions/diabetic-retinopathy-detection, 7.
  • Dulkadir, S., & Gültekin, G. K. (2023). Tarımsal Otomasyon Sistemleri için Muz Olgunluk Seviyelerinin Derin Öğrenme Yöntemleri İle Sınıflandırılması. EMO Bilimsel Dergi, 13(3), 27-34.
  • Lingling Fang, Huan Qiao(2022),Diabetic retinopathy classification using a novel DAG network based on multi-feature of fundus images,Biomedical Signal Processing and Control,Volume 77, 2022, 103810, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2022.103810.
  • Fong, D. S., Aiello, L., Gardner, T. W., King, G. L., Blankenship, G., Cavallerano, J. D., Ferris III, F. L., Klein, R., & Association, A. D. (2003). Diabetic retinopathy. Diabetes care, 26(suppl_1), s99-s102.
  • Kemal, A., & Takci, H. (2022). Hibrit Bir Model Oluşturarak Diyabetik Retinopati Sınıflandırılması. Avrupa Bilim ve Teknoloji Dergisi(36), 227-236.
  • King, R. Retrieved 01.01.2024 from https://github.com/open-mmlab/mmyolo
  • Özçelik, Y. B., & Altan, A. (2021). Diyabetik retinopati teşhisi için fundus görüntülerinin derin öğrenme tabanlı sınıflandırılması. Avrupa Bilim ve Teknoloji Dergisi(29), 156-167.
  • Özçelik YB, Altan A(2023). Overcoming Nonlinear Dynamics in Diabetic Retinopathy Classification: A Robust AI-Based Model with Chaotic Swarm Intelligence Optimization and Recurrent Long Short-Term Memory. Fractal and Fractional.; 7(8):598. https://doi.org/10.3390/fractalfract7080598
  • Ultralytics. Ultralytics Documentation. . Retrieved 01.02.2024 from https://docs.ultralytics.com/
  • Vujosevic, S., Aldington, S. J., Silva, P., Hernández, C., Scanlon, P., Peto, T., & Simó, R. (2020). Screening for diabetic retinopathy: new perspectives and challenges. The Lancet Diabetes & Endocrinology, 8(4), 337-347. V. Vipparthi, D. R. Rao, S. Mullu and V. Patlolla(2022). "Diabetic Retinopathy Classification using Deep Learning Techniques," 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 2022, pp. 840-846, doi: 10.1109/ICESC54411.2022.9885687.
  • Wong, T. Y., Sun, J., Kawasaki, R., Ruamviboonsuk, P., Gupta, N., Lansingh, V. C., Maia, M., Mathenge, W., Moreker, S., & Muqit, M. M. (2018). Guidelines on diabetic eye care: the international council of ophthalmology recommendations for screening, follow-up, referral, and treatment based on resource settings. Ophthalmology, 125(10), 1608-1622.
  • Yau, J. W., Rogers, S. L., Kawasaki, R., Lamoureux, E. L., Kowalski, J. W., Bek, T., Chen, S.-J., Dekker, J. M., Fletcher, A., & Grauslund, J. (2012). Global prevalence and major risk factors of diabetic retinopathy. Diabetes care, 35(3), 556-564.
There are 18 citations in total.

Details

Primary Language English
Subjects Image Processing, Deep Learning
Journal Section Computer Engineering
Authors

Ömer Şanver 0009-0004-4313-8007

Ahmet Saygılı 0000-0001-8625-4842

Publication Date December 3, 2024
Submission Date March 15, 2024
Acceptance Date May 14, 2024
Published in Issue Year 2024Volume: 27 Issue: 4

Cite

APA Şanver, Ö., & Saygılı, A. (2024). DIAGNOSIS AND CLASSIFICATION OF DIABETIC RETINOPATHY WITH YOLOv8-BASED DEEP LEARNING MODEL. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(4), 1297-1305. https://doi.org/10.17780/ksujes.1453034
 Download Cover Image