Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Hemorrhage Diabetic Retinopathy Detection Based on Fundus Image Using Neural Network and FCM Segmentation

Rektorat UDINUS 2020 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2020
Goals
Record
6972ce77-5e55-46ec-882c-fb7fec61b15a
Published
2026-10-30

Universitas Dian Nuswantoro conducted research on the detection of Hemorrhage Diabetic Retinopathy using fundus images, involving Purwanithami, Hadapininglaksmi Astri; Atika Sari, Christy; Rachmawanto, Eko Hari; and Rosal Ignatius Moses Setiadi, De as activity participants. The research addressed a type of diabetes that attacks the blood vessels of the retina and may cause blindness, while early treatment can minimize this consequence. The activity proposed a method for detecting retinal blood vessels affected by Hemorrhage Diabetic Retinopathy through preprocessing, segmentation, and detection stages.

During preprocessing, an RGB fundus image was processed through selection of the green channel. Contrast enhancement was then performed using Contrast Limited Adaptive Histogram Equalization (CLAHE), followed by segmentation using Fuzzy C-Means (FCM). Detection was subsequently conducted using a Neural Network method. The experimental stage used 100 testing images divided into two classes, namely Hemorrhage and Non-Hemorrhage. The results reported that one image was detected incorrectly. Based on these results, the reported detection accuracy reached 99%. This activity contributes to the health research goal by addressing detection of a retinal condition associated with diabetes and by applying image-processing and neural-network methods to fundus-image analysis. The activity represents UDINUS research in developing a method for Hemorrhage Diabetic Retinopathy detection.

Reference https://www.scopus.com/pages/publications/85096876063?origin=resultslist