Automatic Diagnosis of Diabetic Retinopathy from Fundus Images

DOI

10.2991/978-94-6463-602-4_19How to use a DOI?

Keywords

Detection Diabetic Retinopathy; SVM Classification Approach; Segmentation Techniques; Fundus Images

Abstract

Detection of earliest symptoms of Diabetic Retinopathy and its prevention is challenging task in medical sciences. There are main three symptoms of Diabetic Retinopathy includes; Microaneurysm (MA), Hemorrhages (HA) and Exudates. Microaneurysm is the initial stage in which small round dots appears which losses partial eyesight and it is the leading cause of Hemorrhage. Hemorrhage being the advanced stage of Microaneurysm in which blood vessels bleed and insufficient intake of nutrients and oxygen to retina may cause poor vision. This study based on diagnosis of Hemorrhages at earlier stages through machine learning algorithm. Research design include pre-processing, texture feature extraction, and classification approach (SVM), and segmentation procedure using Gray Wolf Optimization using datasets. The following data sets are used i.e. DIARTDB0, DIARTDB1 and real data which is collected from civil hospital LUMHS Jamshoro. The results achieved with SVM showed the minimum false, high accuracy achieved through manifold testing and training. The achieved results have the sensitivity of 88.12%, specificity of 77.7% and accuracy of 85.35%.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sasuee Rajper
AU  - Sehreen Moorat
AU  - Natasha Mukhtiar
AU  - Sarmad Shams
PY  - 2024
DA  - 2024/12/24
TI  - Automatic Diagnosis of Diabetic Retinopathy from Fundus Images
BT  - Proceedings of the 4th International Conference on Key Enabling Technologies (KEYTECH 2024)
PB  - Atlantis Press
SP  - 132
EP  - 137
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-602-4_19
DO  - 10.2991/978-94-6463-602-4_19
ID  - Rajper2024
ER  -