International Journal of Nonlinear Analysis and Applications
Diabetic retinopathy detection and classification based on deep learning: A review
Document Type : Review articles
Authors
Computer Science Department, Collage of Science, University of Baghdad, Baghdad, Iraq
Abstract
Diabetic retinopathy can be defined as an eye disease that occurs specifically in diabetic patients and results in damaging the small blood vessels of the retina because of high and low blood sugar. Delayed detection and treatment often lead to blindness, so one of the most significant issues is early detection of this disease, which is necessary for successful treatment. Many deep learning methods have been suggested for diabetic retinopathy detection and classification. Manual inspection of the fundus images to check diabetic retinopathy is highly tedious and time-consuming work. Thus, an automatic method for early diabetic retinopathy diagnosis utilizing the fundus images is very useful tool that helps experts. In this review paper, several deep learning models that are widely used in literature investigated diabetic retinopathy classification will be presented and discussed. In addition, a comparative analysis for classification performance accuracy of diabetic retinopathy using these deep learning models will be reviewed comprehensively. Thus, an automatic approach for early diabetic retinopathy diagnosis utilizing the fundus images is a very useful tool that helps the experts.
Keywords
[1] M.D. Abràmoff, Y. Lou, E. Ali, C. Warren, A. Ryan, J.C. Folk and M. Niemeijer, Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning, Invest. Opthalmol. Vis. Sci. 57 (2016), no. 13, 5200–5206.
[2] K. Adem, Exudate detection for diabetic retinopathy with circular Hough transformation and convolutional neural networks, Expert Syst. Appl. 114 (2018), 289–295.
[3] W.L. Alyoubi, W.M. Shalash and M.F. Abulkhair, Diabetic retinopathy detection through deep learning techniques: A review, Inf. Med. Unlocked 20 (2020), 100377.
[4] N. Asiri, M. Hussain, F. Al Adel and N. Alzaidi, Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey, Artif. Intel. Med. 99 (2019), 101701.
[5] M.A. Bennet, D. Dharini and S.M. Priyadharshini, Detection of blood vessel segmentation in retinal images using adaptive filters, J. Chem. Pharmac. Res. 8 (2016), no. 4, 290–298.
[6] P. Chudzik, S. Majumdar, F. Calivá, B. Al-Diri and A. Hunter, Microaneurysm detection using fully convolutional neural networks, Comput. Meth. Prog. Biomed. 158 (2018), 185–192.
[7] E. Decenciere, G. Cazuguel, X. Zhang, G. Thibault, J.C. Klein, F. Meyer, B. Marcotegui, G. Quellec, M. Lamard, R. Danno and D. Elie, TeleOphta: Machine learning and image processing methods for teleophthalmology, Irbm 34 (2013), no. 2, 196–203.
[8] E. Decencière, X. Zhang, G. Cazuguel, B. Lay, B. Cochener, C. Trone, P. Gain, R. Ordonez, P. Massin, A. Erginay and B. Charton, Feedback on a publicly distributed image database: the Messidor database, Image Anal. Ster. 33 (2014), no. 3, 231–234.
[9] D. Doshi, A. Shenoy, D. Sidhpura and P. Gharpure, Diabetic retinopathy detection using deep convolutional neural networks, Int. Conf. Comput. Anal. Secur. Trends (CAST), IEEE, 2016, pp. 261–266.
[10] S. Dutta, B.C. Manideep, S.M. Basha, R.D. Caytiles and N.C.S.N. Iyenger, Classification of diabetic retinopathy images by using deep learning models, Int. J. Grid Distrib. Comput. 11 (2018), no. 1, 89–106.
[11] M. Esmaeili, H. Rabbani, A.M. Dehnavi and A. Dehghani, Automatic detection of exudates and optic disk in retinal images using curvelet transform, IET Image Process. 6 (2012), no. 7, 1005–1013.
[12] R. Gargeya and T. Leng, Automated identification of diabetic retinopathy using deep learning, Ophthalmology 124 (2017) no. 7, 962–969.
[13] K.A. Goatman, A.D. Whitwam, A. Manivannan, J.A. Olson and P.F. Sharp, Colour normalisation of retinal images, Proc. Med. Imag. Understanding Anal. 2003, pp. 49–52.
[14] M.T. Hagos and S. Kant, Transfer learning based detection of diabetic retinopathy from small dataset, arXivpreprint arXiv:1905.07203, (2019).
[15] S. Hajeb Mohammad Alipour, H. Rabbani and M.R. Akhlaghi, Diabetic retinopathy grading by digital curvelet transform, Comput. Math. Meth. Med. 2012 (2012).
[16] Y. Hatanaka, K. Ogohara, W. Sunayama, M. Miyashita, C. Muramatsu and H. Fujita, Automatic microaneurysms detection on retinal images using deep convolution neural network, Int. Workshop Adv.Image Technol. (IWAIT), IEEE, 2018, pp. 1–2.
[17] K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition, Proc. IEEE Conf. Comput. Vision Pattern Recogn., 2016, pp. 770–778.
[18] L. Hill and L.E. Makaroff, Early detection and timely treatment can prevent or delay diabetic retinopathy, Diabetes Res. Clin. Pract. 120 (2016), 241–243.
[19] A. Hoover, V. Kouznetsova and M. Goldbaum, Locating blood vessels in retinal images by piece-wise threshold probing of a matched filter response, IEEE Trans. Med. Imag. 19 (2000), no. 3, 203–210.
[20] K. Hu, Z. Zhang, X. Niu, Y. Zhang, C. Cao, F. Xiao and X. Gao, Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with an improved cross-entropy loss function, Neurocomput. 309 (2018), 179–191.
[21] A.J. Jenkins, M.V. Joglekar, A.A. Hardikar, A.C. Keech, D.N. O’Neal and A.S. Januszewski, Biomarkers in diabetic retinopathy, Rev. Diabet. Stud. 12 (2015), no. 1-2, 159–195.
[22] Y. Kanagasingam, D. Xiao, J. Vignarajan, A. Preetham, M.-L. Tay-Kearney and A. Mehrotra, Evaluation of artificial intelligence-based grading of diabetic retinopathy in primary care, JAMA Network Open. 1 (2018), no. 5, e182665–e182665.
[23] N. Kaur, S. Chatterjee, M. Acharyya, J. Kaur, N. Kapoor and S. Gupta, A supervised approach for automated detection of haemorrhages in retinal fundus images, 5th Int. Conf. Wireless Networks Embed. Syst. (WECON), IEEE, 2016, pp. 1–5.
[24] A. Krizhevsky, I. Sutskever and G.E. Hinton, Imagenet classification with deep convolutional neural networks, Adv. Neural Info. Process. Syst. 25 (2012), 1097–1105.
[25] C. Lam, D. Yi, M. Guo and T. Lindsey, Automated detection of diabetic retinopathy using deep learning, AMIA Joint Summits Transl. Sci. Proc. 2018 (2018), 147–155.
[26] T. Li, Y. Gao, K. Wang, S. Guo, H. Liu and H. Kang, Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening, Info. Sci. 501 (2019), 511–522.
[27] X. Li, X. Hu, L. Yu, L. Zhu, C.-W. Fu and P.-A. Heng, CANet: Cross-disease attention network for joint diabetic retinopathy and diabetic macular edema grading, IEEE Trans. Med. Imag. 39 (2020), no. 5, 1483–1493.
[28] F. Li, Z. Liu, H. Chen, M. Jiang, X. Zhang and Z. Wu, Automatic detection of diabetic retinopathy in retinal fundus photographs based on deep learning algorithm, Trans. Vis. Sci. Tech. 8 (2019), no. 6.
[29] Y.-P. Liu, Z. Li, C. Xu, J. Li and R. Liang, Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network, Artif. Intell. Med. 99 (2019), 101694.
[30] S. Patel, Diabetic retinopathy detection and classification using pre-trained convolutional neural networks, Int. J. Emerging Technol. 11 (2020), no. 3, 1082–1087.
[31] P. Prentašić and S. Lončarić, Detection of exudates in fundus photographs using deep neural networks and anatomical landmark detection fusion, Comput. Meth. Prog. Biomed. 137 (2016), 281–292.
[32] P. Prentašić, S. Lončarić, Z. Vatavuk, G. Bencic, M. Subasic, T. Petkovic, L. Dujmović, M. Malenica-Ravlić, N. Budimlija and R. Tadić, Diabetic retinopathy image database (DRIDB): A new database for diabetic retinopathy screening programs research, 8th Int. Symp. Image Signal Process. Anal. (ISPA), 2013, pp. 711–716.
[33] R. Priya and P. Aruna, SVM and neural network based diagnosis of diabetic retinopathy, Int. J. Comput. Appl. 41 (2012), 6–12.
[34] M. Raju, P. Venkatesh, B. Ryan, A. Kadam, V. Kasivajjala and A. Aswath, Development of a deep learning algorithm for automatic diagnosis of diabetic retinopathy, Stud. Health Technol. Inf. 245 (2017), 559–563.
[35] O. Ronneberger, P. Fischer and T. Brox, U-net: convolutional networks for biomedical image segmentation, Int. Conf. Med. Image Comput. Computer-Assisted Interven., Springer, 2015, pp. 234–241.
[36] K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:14091556, (2014).
[37] The Foundation of the American Society of Retina Specialists, Diabetic Retinopathy: Diabetic retinopathy, https://www.asrs.org/content/documents/fact_sheet_22_diabetic_retinopathy_new.pdf.
[38] N. Tsiknakis, D. Theodoropoulos, G. Manikis, E. Ktistakis, O. Boutsora, A. Berto, F. Scarpa, A. Scarpa, D.I. Fotiadis and K. Marias, Deep learning for diabetic retinopathy detection and classification based on fundus images: A review, Comput. Bio. Med. 135 (2021), 104599.
[39] M.J. Van Grinsven, B. van Ginneken, C.B. Hoyng, T. Theelen and C.I. Sánchez, Fast convolutional neural network training using selective data sampling: Application to hemorrhage detection in color fundus images, IEEE Trans. Med. Imag. 35 (2016), no. 5, 1273–1284.
[40] S. Wan, Y. Liang and Y. Zhang, Deep convolutional neural networks for diabetic retinopathy detection by image classification, Comput. Electr. Eng. 72 (2018), 274–282.
[41] C.P. Wilkinson, F.L. Ferris III, R.E. Klein, P.P. Lee, C.D. Agardh, M. Davis, D. Dills, A. Kampik, R. Parara-jasegaram, J.T. Verdaguer and G.D.R.P. Group, Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales, Ophthalmology 110 (2003), no. 9, 1677–1682.
[42] W. Zhang, J. Zhong, S. Yang, Z. Gao, J. Hu, Y. Chen and Z. Yi, Automated identification and grading system of diabetic retinopathy using deep neural networks, Knowledge-Based Syst. 175 (2019), 12–25.
)
Volume 13, Issue 2
July 2022Pages 3203-3212
- Receive Date: 23 June 2022
- Revise Date: 18 July 2022
- Accept Date: 13 August 2022