10Diabetic Retinopathy Detection by Retinal Blood Vessel Segmentation and Classification Using Ensemble Model
Gandla Shivakanth1*, K. Aruna Bhaskar2, Bechoo Lal2, A. Shivakumar Reddy2 and D. Manasa2
1Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Hyderabad, Telangana, India
2Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, KL University, Vijayawada, Andhra Pradesh, India
Abstract
Diabetic retinopathy is common problem to diabetic patients. According to the current statistics of world, 9% and above diabetic patients are suffering with partially or complete vision loss. Retinal blood vessels perform an imperative role in the diagnostic procedure of diabetic retinopathy. However, the segmentation of retinal vessels is critical for pathological reasoning. In this article, a novel ensemble approach was developed for accurate blood vessel segmentation and classification. The retinal images had been accumulated from Digital Retinal Images for Vessel Extraction (DRIVE) and STructured Analysis of the Retina (STARE) datasets. The ensemble approach is used to segment the retinal blood vessels using bio-inspired algorithms, Cuttlefish Algorithm (CFA) for segmentation of the fundus image. The features were then extracted from the segmented pictures using the Enhanced Local Binary Pattern (ELBP) and Inverse Difference Moment Normalized (IDMN) algorithms. The obtained feature values were lastly provided as the ...
Get Bio-Inspired Optimization for Medical Data Mining now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
