Abstract
Due to growing trend of urban living, there is a considerable increase in the consumption of processed carbohydrates and sugar by the people, it is found to be one of the very common reasons for diabetes being on the rise worldwide. Diabetic Retinopathy is a disease prone to diabetic people which causes severe damage to the retina of the eye, it is observed that most of the patients with diabetes also suffer from partial or complete loss of their vision if not detected in their early stages. The aim of this paper is to achieve autonomy in the diagnosis of Diabetic Retinopathy (DR), that is achieved by categorizing different DR affected fundus images into 5 sections (0-Normal, 1-Mild, 2-Moderate, 3-Severe, 4-Proliferative) and then training Dense Convolutional Network (DenseNet) algorithm which is one of the efficient Convolution Neural Network (CNN) using these 5 sections, by which accurate identification and diagnosis of the input image is achieved. This autonomous process will help the physician in treating DR easily, saving physicians time and reducing diagnostic errors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Author F (1998) World Diabetes, A newsletter from the World Health Organization, 4
Solanki MS (1998) CS365: artificial intelligence: diabetic retinopathy detection using eye. World Diabetes, A newsletter from the World Health Organization, 4
Umarfarooq AS. Blood vessel identification and segmentation from retinal images for diabetic retinopathy
Feng X, Yao H, Zhang S (2019) An efficient way to refine DenseNet. Springer-Verlag London Ltd., part of Springer Nature
Huang G, Liu Z, van der Maaten L, Weinberger KQ (2018) Densely connected convolutional networks. Facebook AI Research, 28 Jan 2018
Mishra S, Hanchate S, Saquib Z (2020) Diabetic retinopathy detection using deep learning. In: International conference on smart technologies in computing, electrical and electronics (ICSTCEE 2020)
Albahli S, Nazir T, Irtaza A, Javed A. Recognition and detection of diabetic retinopathy using DenseNet-65 based faster-RCNN. Comput Mater Contin. https://doi.org/10.32604/cmc.2021.014691
Xia M, Song W, Sun X, Liu J, Ye T, Xu Y (2019) Weighted densely connected convolutional networks for reinforcement learning. Int J Pattern Recognit Artif Intell. https://doi.org/10.1142/S0218001420520011
Luke JJ, Joseph R, Balaji M (2019) Impact of image size on accuracy and generalization of convolutional neural networks. Int J Res Anal Rev (IJRAR)
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Kale S, Sekhar A, Sridharan K (2021) SGD: the role of implicit regularization, batch-size and multiple epochs. In: 35th conference on neural information processing systems (NeurIPS 2021)
Ben-Davi A (2008) Comparison of classification accuracy using Cohen’s weighted kappa. Expert Syst Appl 34(2):825–832. https://doi.org/10.1016/j.eswa.2006.10.022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Viraktamath, S.V., Hiremath, D., Tallur, K. (2023). Detection of Diabetic Retinopathy Using Fundus Images. In: Shetty, N.R., Patnaik, L.M., Prasad, N.H. (eds) Emerging Research in Computing, Information, Communication and Applications. Lecture Notes in Electrical Engineering, vol 928. Springer, Singapore. https://doi.org/10.1007/978-981-19-5482-5_30
Download citation
DOI: https://doi.org/10.1007/978-981-19-5482-5_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-5481-8
Online ISBN: 978-981-19-5482-5
eBook Packages: Computer ScienceComputer Science (R0)