Abstract
The paper aims to segment the lesion of non-proliferative diabetic retinopathy (NPDR) which occurred due to diabetes. The risk of loss of sight can be decreased by 95% with the timely diagnosis of the NPDR disease. The proposed work aimed to segment the NPDR lesion called ‘hard exudate’. Firstly, the fundus input image undergoes resizing by applying bi-cubic interpolation area method, and then the resized image is preprocessed with single channel extraction and median filter. Further, the NPDR lesion is segmented using k-means and fuzzy C-means (FCM) algorithms. By comparing the results of both segmentation algorithms, FCM shows the better result. The executions of the methods are evaluated using mean-squared error, structural similarity index measure, sensitivity, specificity and accuracy. The proposed FCM method for segmenting the ‘hard exudate’ lesion has achieved a better result of 95.05% accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
A. Pattanashetty, S. Nandyal, Diabetic retinopathy detection using image processing: a survey. Int. J. Comput. Sci. Network, pp. 661–666 (2016)
R. Shalini, S. Sasikala, A survey on detection of diabetic retinopathy, pp. 626–630 (2018). https://doi.org/10.1109/I-SMAC.2018.8653694
N.G. Ranamuka, R. Gayan, N. Meegama, Detection of hard exudates from diabetic retinopathy images using fuzzy logic. IET Image Process, pp. 121–130 (2012)
S.W. Franklin, S.E. Rajan, Diagnosis of diabetic retinopathy by employing image processing technique to detect exudates in retinal images. IET Image Process, pp. 601–609 (2013)
J.S. Lachure, A.V. Deorankar, S. Lachure, Automatic diabetic retinopathy using morphological operations. Int. J. Comput. Appl., pp. 22–24 (2015)
A. Elbalaoui, M. Fakir, Exudates detection in fundus images using meanshift segmentation and adaptive thresholding, in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization (2018)
A.L. Pal, S. Prabhu, N. Sampathila, Detection of abnormal features in digital fundus image using morphological approach for classification of diabetic retinopathy. Int. J. Innov. Res. Comput. Commun. Eng. pp. 901–909 (2015)
P. Hosanna Princye, V. Vijayakumari, Detection of exudates and feature extraction of retinal images using fuzzy clustering method. IET publications, pp. 388–394
J. Dileep, P. Manohar, Automatic detection of exudate in diabetic retinopathy using K-clustering algorithm. Int. J. Recent Innov. Trends Comput. Commun., pp. 2878–2882 (2015)
A. Sopharak, B. Uyyanonvara, S. Barman, Automatic exudate detection from non-dilated diabetic retinopathy retinal images using fuzzy C-means clustering. Sensors open access publications pp. 2148–2161 (2009). www.mdpi.com/journal/sensors
https://in.mathworks.com/help/vision/ug/interpolation-methods.html
https://www.sciencedirect.com/topics/engineering/median-filtering
ttps://en.wikipedia.org/wiki/Thresholding_(image_processing)
https://sites.google.com/site/dataclusteringalgorithms/k-means-clustering-algorithm
https://sites.google.com/site/dataclusteringalgorithms/fuzzy-c-means-clustering-algorithm
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shalini, Sasikala (2021). Fuzzy C-means for Diabetic Retinopathy Lesion Segmentation. In: Smys, S., Tavares, J.M.R.S., Bestak, R., Shi, F. (eds) Computational Vision and Bio-Inspired Computing. Advances in Intelligent Systems and Computing, vol 1318. Springer, Singapore. https://doi.org/10.1007/978-981-33-6862-0_17
Download citation
DOI: https://doi.org/10.1007/978-981-33-6862-0_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6861-3
Online ISBN: 978-981-33-6862-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)