Abstract
Diabetic retinopathy is one of the major causes of blindness in the world. The computer-based approaches play a vital role in early detection and diagnosis to avoid future complications and loss of vision. This paper discusses techniques to localize microaneurysms and exudates, the early signs of the disease. The retina fundus images are pre-processed to eliminate blood vessels and optic disk to detect lesions present in the retina. A set of morphological operations are carried out, to identify microaneurysms and exudates. The results are compared with ground truth images. The proposed work achieved an average sensitivity of 85.68% for exudate detection and 96.41% for microaneurysms detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Vislisel J, Oetting T (2010) Diabetic retinopathy: from one medical student to another. EyeRounds.org
Abramoff MD, Garvin MK, Sonka M (2010) Retinal imaging and image analysis. IEEE Rev Biomed Eng 3:169–208
Eadgahi MGF, Pourreza H (2012) Localization of hard EXs in retinal fundus image by mathematical morphology operations. In: 2nd International econference on computer and knowledge engineering (ICCKE), Mashhad, 18–19 Oct 2012, pp 185–189
Zhang X et al (2014) Exudate detection in colour retinal images for mass screening of DR. Medical Image Anal 18(7):1026–1043. ISSN:1361-8423
Shahin EM, Taha TE, Al-Nuaimy W, El Rabaie S, Zahran OF, El-Samie FEA (2012) Automated detection of DR in blurred digital fundus images. In: 8th International computer engineering conference (ICENCO), Cairo, pp 20–25
Usman Akram M et al (2013) Identification and classification of MA for early detection of DR. Pattern Recogn 46(1):107–116. ISSN 0031-3203
Şehirli E, Turan M, Dietzel A (2015) Automatic detection of microaneurysms in RGB retinal fundus images. Int J Sci Technol Res 1:1–8
Sopharak A et al. Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods. Comput. Med. Imaging Graph: Off J Comput Med Imaging Soc 32:720–727. https://doi.org/10.1016/j.compmedimag.2008.08.009
Sopharak A et al (2013) Simple hybrid method for fine microaneurysm detection from non-dilated diabetic retinopathy retinal images. Comput. Med. Imaging Graph: Off J Comput Med Imaging Soc 37:5–6:394–402
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66
Gonzalez RCW (2010) Digital image processing using Matlab. 2nd edn., pp 62–63
Decencière E et al (2013) TeleOphta: machine learning and image processing methods for teleophthalmology. IRBM. https://doi.org/10.1016/j.irbm.2013.01.010,2013-RetinalImagedatabase
Sridhar (2011) Digital image processing, 1st edn., pp 483–487
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ramakrishna, N., Kohir, V.V. (2021). Diabetic Retinopathy Detection at Early Stage Using a Set of Morphological Operations. In: Sekhar, G.C., Behera, H.S., Nayak, J., Naik, B., Pelusi, D. (eds) Intelligent Computing in Control and Communication. Lecture Notes in Electrical Engineering, vol 702. Springer, Singapore. https://doi.org/10.1007/978-981-15-8439-8_38
Download citation
DOI: https://doi.org/10.1007/978-981-15-8439-8_38
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-8438-1
Online ISBN: 978-981-15-8439-8
eBook Packages: Computer ScienceComputer Science (R0)