Greedy segmentation based diabetic retinopathy identification using curvelet transform and scale invariant features
Author
Source
Journal of Engineering Research
Issue
Vol. 9, Issue 1 (31 Mar. 2021), pp.134-150, 17 p.
Publisher
Kuwait University Academic Publication Council
Publication Date
2021-03-31
Country of Publication
Kuwait
No. of Pages
17
Main Subjects
Information Technology and Computer Science
Abstract EN
Diabetic retinopathy (DR) is the major reason of vision loss in the active population.
It can usually be prevented by regulating the blood glucose and providing a timely treatment.
DR has clinical features recognized by the experts including the blood vessel area, exudates, neovascularization, hemorrhages and microaneurysm.
Because DR has some varieties and complexities due to its geometrical and haemodynamic features, it is hard to detect DR in time-consuming manual diagnosis.
In Computer Aided Diagnosis (CAD) systems, the fundus image features of DR are detected using computer vision techniques.
In this paper, a CAD system is proposed which distinguishes automatically whether the fundus is normal or has diabetic retinopathy disease.
Morphological operations like filtering, opening and dilation are applied to the fundus images for pre-process.
Then, Optic Disk (OD) segmentation is implemented using Greedy algorithm.
Because of the intensity of an OD is similar with some DR intensities, OD regions are eliminated in fundus images for an accurate feature extraction.
The features extracted with Curvelet Transform (CT) and Scale Invariant Feature Transform (SIFT) respectively are concatenated to provide a feature set that defines the fundus data optimally.
Then, the feature set is given to Support Vector Machines (SVM) method for classification purposes.
The proposed method has an accuracy of 92.8%, a sensitivity of 0.988% and a specificity of 0.80%.
American Psychological Association (APA)
Gorgel, Pelin. 2021. Greedy segmentation based diabetic retinopathy identification using curvelet transform and scale invariant features. Journal of Engineering Research،Vol. 9, no. 1, pp.134-150.
https://search.emarefa.net/detail/BIM-1494760
Modern Language Association (MLA)
Gorgel, Pelin. Greedy segmentation based diabetic retinopathy identification using curvelet transform and scale invariant features. Journal of Engineering Research Vol. 9, no. 1 (Mar. 2021), pp.134-150.
https://search.emarefa.net/detail/BIM-1494760
American Medical Association (AMA)
Gorgel, Pelin. Greedy segmentation based diabetic retinopathy identification using curvelet transform and scale invariant features. Journal of Engineering Research. 2021. Vol. 9, no. 1, pp.134-150.
https://search.emarefa.net/detail/BIM-1494760
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 148-150
Record ID
BIM-1494760