International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning Techniques for Diabetic Retinopathy Detection: A Review

  • Rachna Kumari (Department of Computer Science & Engineering Guru Jambheshwar University of Science & Technology) ;
  • Sanjeev Kumar (Department of Computer Science & Engineering Guru Jambheshwar University of Science & Technology) ;
  • Sunila Godara (Department of Computer Science & Engineering Guru Jambheshwar University of Science & Technology)
  • Received : 2024.04.05
  • Published : 2024.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Diabetic retinopathy is a threatening complication of diabetes, caused by damaged blood vessels of light sensitive areas of retina. DR leads to total or partial blindness if left untreated. DR does not give any symptoms at early stages so earlier detection of DR is a big challenge for proper treatment of diseases. With advancement of technology various computer-aided diagnostic programs using image processing and machine learning approaches are designed for early detection of DR so that proper treatment can be provided to the patients for preventing its harmful effects. Now a day machine learning techniques are widely applied for image processing. These techniques also provide amazing result in this field also. In this paper we discuss various machine learning and deep learning based techniques developed for automatic detection of Diabetic Retinopathy.

Keywords

References

  1. I. Qureshi Sha Pires ndong and Q. Abbas Imam(2019). "Recent Development on Detection Methods for the Diagnosis of Diabetic Retinopathy", MDPI Article in Symmetry 11(6): 1-35.
  2. J. Elia Duh, K. Jennifer Sun, W. Alan Stitt(2017). "Diabetic retinopathy: current understanding, mechanisms, and treatment strategies", The Journal of Clinical Insight, 2(14): 1-13.
  3. M. J. Paranjpe and M. N. Kakatkar(2014). "Review of Methods for Diabetic Retinopathy Detection and Severity Classification", International Journal of Research in Engineering and Technology, 3(3): 619-624.
  4. Pezzullo, L. J, Streatfeild, P. Simkiss, and D, Shickle(2018). "The economic impact of sight loss and blindness in the UK adult population", BMC health services research. 18(1): 1-13.
  5. U. Ishtiaq, S. A. Kareem., E.R.M.F. Abdullah,G. Mujtaba, and R. Jahangir(2019). "Diabetic retinopathy detection through artificial intelligent techniques: a review and open issues", Springer: Multimedia Tools and Applications 79(21): 15209-15252.
  6. S. A. G. Naqvi,M. F. Zafar and I ul Haq(2015). "Referral system for hard exudates in eye fundus", Computers in biology and medicine 64: 217-235. https://doi.org/10.1016/j.compbiomed.2015.07.003
  7. R. Chand CP and J Dheeba(2015). "Automatic detection of exudates in color fundus retinopathy images", Indian Journal of Science and Technology 8(26): 1-6.
  8. E. V. Carrera , A. Gonzalez and R. Carrera(2017). "Automated detection of Diabetic Retinopathy using SVM", IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON) 1-4.
  9. D. Xiao, Yu, S., Vignarajan, J., An, D., Tay-Kearney, M.L. and Kanagasingam(2017). "Retinal hemorrhage detection by rule-based and machine learning approach", 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 660-663.
  10. SS. Rahim S. Suhaila, C. Jayne, V. Palade, and J. Shuttleworth(2016). " Automatic detection of microaneurysms in colour fundus images for diabetic retinopathy screening", Neural Computing Application 27(5): 1149-1164. https://doi.org/10.1007/s00521-015-1929-5
  11. P. Nijalingappa and B. Sandeep(2016). "Machine learning approach for the identification of diabetes retinopathy and its stages", International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT) 653-658.
  12. S. Wang Tang, H.L. Hu, and Y., Sanei(2017). "Localizing microaneurysms in fundus images through singular spectrum analysis", IEEE Transactions on Biomedical Engineering 64(5): 990-1002.
  13. Wu JY, J. Xin and L. Hong(2017). "New hierarchical approach for microaneurysms detection with matched filter and machine learning", 37th Annual International Conference of the Ieee Engineering in Medicine and Biology Society. IEEE 4322-4325.
  14. V. Hanuskova, J. Pavlovicova and R. Blasko(2013). "Diabetic retinopathy screening by bright lesions extraction from fundus image", Journal of Electrical Engineering 64(5): 311-316. https://doi.org/10.2478/jee-2013-0045
  15. K. Ganesan, R. J. Martis, U. R. Acharya and C. K. Chua(2014). "Computer-aided diabetic retinopathy detection using trace transforms on digital fundus images", Medical & biological engineering & computing 52(8): 663-672. https://doi.org/10.1007/s11517-014-1167-5
  16. Al-Jarrah and H. Shatnawi(2017). "Non-proliferative diabetic retinopathy symptoms detection and classification using neural network", Journal of Medical Engineering and Technology 41(6): 498-505.
  17. T. Bui, N. Maneerat and U. Watchareeruetai(2017). "Detection of cotton wool for diabetic retinopathy analysis using neural network", IEEE 10th International Workshop on Computational Intelligence and Applications 203-206.
  18. Vargas, Rocio, A. Mosavi, and R. Ruiz(2017). "Deep learning: A Review", Advances in Intelligent Systems and Computing 127354.
  19. G. Yanming, Yu Oerlemans, S. Lao, Song and S. Michael(2016). "Deep learning for visual understanding: A review", Neurocomputing 187: 27-48. https://doi.org/10.1016/j.neucom.2015.09.116
  20. M. Andonova and J. Pavlovicova(2017). "Diabetic retinopathy screening based on CNN", International Symposium ELMAR IEEE 51-54.
  21. Prabhu, Raghav(2018). "Understanding of Convolutional Neural Network (CNN)-Deep Learning", A Medium Corporation, US.
  22. H. F. Jelinek, A. Rocha and T. Carvalho(2011). "Machine Learning and Pattern Classification in Identification of Indigenous Retinal Pathology", Annual International Conference of the IEEE Engineering in Medicine and Biology Society 5951-5954.
  23. G. Wilkins, O. Houghton, and A. Oldenburg(2012). "Automated segmentation of intraretinal cystoid fluid in optical coherence tomography," IEEE Transactions on Biomedical Engineering 59(4): 1109-1114. https://doi.org/10.1109/TBME.2012.2184759
  24. Y. Zheng, J. Sahni and C. Campa iet(2013). "Computerized Assessment of Intraretinal and Subretinal Fluid Regions in Spectral-Domain Optical Coherence Tomography Images of The Retina", am j ophthalmol 2(155): 277-286.
  25. P. Liskowski and K. Krawiec(2016). "Segementing Retinal Blood Vessels With Deep Neural Networks", IEEE Transactions on Medical Imaging 35(11): 2369-2380. https://doi.org/10.1109/TMI.2016.2546227
  26. Pedro Costa and Aur elio Campilho(2017). "Convolutional Bag of Words for Diabetic Retinopathy Detection from Eye Fundus Images", IAPR International Conference on Machine Vision Applications IEEE 165-168.
  27. Di Nui, P. Xu, C. Wan and J. Chang(2017). "Automatic localization of Optic Disc Based on Deep Learning in Fundus Images", IEEE International Conference on Signal and Image Processing 208-212.
  28. J. Hamwood, D. Alonso-Caneiro and A. Scott (2018). "Effect Of Patch Size And Network Architecture On A Convolutional Neural Network Approach For Automatic Segmentation Of Oct Retinal Layers", Biomedical Optics Express, 9(7).
  29. A. Vahadane, A. Joshi, K. Madan and T. Dastidar(2018). "Detection of Diabetic Macular Edema in Optical Coherence Tomography Scans using Patch Based Deep Learning", IEEE International Symposium on Biomedical Imaging 18: 1427-1430.
  30. J. Kim and E. Y. Chew(2018). "Region of Interest Detection Fundus Images Using Deep Learning and Blood Vessel Information", IEEE International Symposium on Computer Based Medical Systems 18: 357-362.
  31. P. Seebock, J. I. Orlando, T. Schlegl, S. M. Waldstein, H. Bogunovic, S. Klimscha and U. Schmidt-Erfurth(2019). "Exploiting Epistemic Uncertainity of Anatomy Segmentation for Anomaly detection in Retinal OCT", IEEE Transactions on Medical imaging 20(20): 1- 12.
  32. J. Orlando and P. Seebok(2019). "U2-NET Model With Epistemic Uncertainty Feedback for Photoreceptor Layer Segmentation in Pathological OCT Scan", International Symposium on Biomedical Imaging 1441-1445.
  33. N. Motozawa, A. Guangzhou and S. Takagi(2019). "Optical Coherence Tomography-Based Deep-Learning Models for Classifying Normal and Age-Related Macular Degeneration and Exudative and NonExudative Age-Related Macular Degeneration Changes", Ophthalmol Ther 19: 1-10.
  34. Z. Wang and N. Dong(2019). "Ellipse Detection of Optic Disc and Optic Cup Boundary in Fundus Images", IEEE International Symposium on Biomedical Imaging 19: 601-604.
  35. Z. Wang and J. Yang(2019). "Diabetic Retinopathy Detection via Deep Convolutional Networks for Discriminative Localization and Visual Explanation", 1-19.
  36. B. Tymchenko, and P. Marchenko(2020). "Deep Learning Approach to Diabetic Retinopathy Detection".
  37. Di Nui, P. Xu, C. Wan and J. Chang(2017). "Automatic localization of Optic Disc Based on Deep Learning in Fundus Images", IEEE International Conference on Signal and Image Processing 208-212.
  38. J. Li and Q. Hui(2018). "Vessel Recognition of Retinal Fundus Images Based on Fully Convolutional Network", IEEE International Conference on Computer Software and Application 18: 413-418.
  39. T. Hassan, A. Usman, M. Akram, M. Masood, U. Yasin(2018). "Deep Learning Based Automated Extraction of IntraRetinal Layers for Analyzing Retianl Abnormalities", IEEE International Conference on E-Health Networking, Applications and Services.
  40. Y. Yang, T. Li, W. Li, H. Wu and Wensheng Zhang(2017). "Lesion detection and grading of diabetic retinopathy via two-stages deep convolutional neural networks", Cornell University Computer Vision and Pattern Recognition 533-540.
  41. Yu, Shuang, Di Xiao, and Yogesan Kanagasingam(2017). "Exudate detection for diabetic retinopathy with convolutional neural networks", 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE 1744-1747.
  42. Gargeya, Rishab, and Theodore Leng(2017). "Automated identification of diabetic retinopathy using deep learning", Ophthalmology 124 (7): 962-969. https://doi.org/10.1016/j.ophtha.2017.02.008
  43. J. de Moura, J. Novo and M. Ortega(2019). "Deep Feature Analysis in a Transfer Learning-based Approach for the Automatic Identification of Diabetic Macular Edema", IEEE International Joint Conference on Neural Networks 1-8.
  44. J. Kim, et al.(2019). "Optic Disc And Cup Segmentation For Glaucoma Characterization Using Deep Learning", IEEE International Symposium on Computer Based Medical System 489-494.
  45. Orlando, Jose Ignacio, Elena Prokofyeva, Mariana Del Fresno, and Matthew B. Blaschko(2018). "An ensemble deep learning based approach for red lesion detection in fundus images", Computer methods and programs in biomedicine 153: 115-127. https://doi.org/10.1016/j.cmpb.2017.10.017
  46. R. Arunkumarand Palanivel Karthigaikumar(2017). "Multi-retinal disease classification by reduced deep learning features". Neural Computing and Applications 28(2): 329-334. https://doi.org/10.1007/s00521-015-2059-9