Automated Diagnosis of Hypertensive Retinopathy using Fundus Images

Clinical decision support system (CDSS) is proposed in this paper to diagnose hypertensive retinopathy from fundus images. Vessel segmentation, region of interest (ROI) detection, image normalization, classification of vessels, artery-vein ratio (AVR) calculation are few significant measures that resulted in promising outcomes which presents a preliminary step for the detection of hypertensive retinopathy (HR). All of these methods require the automation process to display the status of the person. This paper presents the approach how the required functionalities are integrated through a Graphical User Interface (GUI) which assists the medical professional to perform further treatment according to medical protocols. Performance analysis of the proposed system is done with the help of Inspire-AVR, VICAVR database. Ground truth values and practical values obtained by using the method are used for evaluating the performance of the algorithm. Sensitivity of 0.8571 is obtained in case of INSPIRE-AVR Database, 0.8 is obtained in VICAVR database. The Promising result obtained using the method, indicates its usefulness in mass screening operation. The Method developed helps in early identification of hypertensive retinopathy and helps as a first aid tool for ophthalmologist