Diagnosis of Early-Stage Diabetic Retinopathy in Digital Fundus Images

• Published in: 2022 Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT) pp. 1 - 5
• Main Authors: Lavanya, D, Derwin, D Jeba, Remya, R, Shan, B Priestly, Singh, O. Jeba, K, Umamaheswari
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21.04.2022
• Subjects: Cameras; Diabetic Retinopathy (DR); Feature extraction; Fluids; Fundus image; Image color analysis; Manuals; Microaneurysms (MAs); Region Of Interest (ROI); Retina; Retinopathy
• DOI: 10.1109/ICAECT54875.2022.9807977

Diabetic Retinopathy (DR) is a chronic disease that may cause vision loss in diabetic patients. A regular eye screening is essential to grade the stages of DR such as Microaneurysms (MAs), exudates and drusen in retinal images acquired using fundus camera. Microaneurysm is an early stage of DR, characterized by small red spots on the retina due to blood and fluid leakage from the weak capillary wall. Hence early detection is vital in preventing the diabetic retinopathy and this article explores an automatic screening system that focus on the early detection of DR which is referred as Microaneurysm. The proposed automatic decision system follow the stages of acquisition of color fundus images, pre-processing the input fundus image, manual selection of Microaneurysm area by Region Of Interest (ROI) and classification of diabetic retinopathy is more helpful for early detection and analysis of diabetic retinopathy. The detection process comprises of image pre-processing, feature extraction and classification methods. The proposed method has been applied to color fundus image in feature extraction, classification and provided with improved outcomes for detecting Microaneurysm.