Efficient Segmentation of Retinal Blood Vessels in The Fundus Images Using Morphological Image Processing
Year: 2025
Type: article
Abstract: The segmentation of retinal blood vessels is critical in diagnosing and monitoring a variety of retinal disorders, such as hypertension, diabetes, glaucoma, and other ocular and cardiovascular problems. Retinal fundus pictures can aid in the early identification and management of these disorders by providing essential details about the status of the blood vessels in the retina. Manual evaluation of retinal fundus pictures by qualified ophthalmologists or experts takes time and requires competence. To address these issues, an automated system for the purpose of diagnosing and treating eye illnesses, a computerized image processing tool to divide the blood vessels that comprise of the retina. The vessel extraction methodology is carried out in three stages: preprocessing, blood vessel segmentation, and performance metric analysis. The green channel is extracted from the input image during preprocessing, and the contrast is enhanced using CLAHE. After preprocessing, the image undergoes a morphological operation followed by Otsu thresholding to segment the image has pixels that represent vessels and non-vessels, respectively. This method is validated on the DRIVE and HRF datasets, and the performance is measured in terms of accuracy, sensitivity, and specificity.
DOI: 10.14419/ryng1670
Institution: Saveetha University
Language: English
Topic: Retinal Imaging and Analysis
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4415104681