Work

Diabetic Retinopathy Detection Using Image Processing Techniques in Python

Year: 2025

Type: report

Abstract: This project implements an automated system to detect diabetic retinopathy (DR) from retinal fundus images using classical image processing techniques in Python. The code extracts key features such as blood vessels and exudates (bright lesions) from retinal images. By analyzing the number and area of white spots (exudates), the system decides whether signs of diabetic retinopathy are present. The pipeline uses OpenCV and scikit-image libraries for tasks such as contrast enhancement, morphological filtering, edge detection, and blob analysis. The system was tested on 10 retinal images with 100% accuracy (5 DR-positive and 5 DR-negative). This work demonstrates the potential of simple rule-based image analysis in early disease detection.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.15478837

Authors: Hassan, Arslan, Nasir, Arslan, ALI, HAMMAD

Institution: Khwaja Fareed University of Engineering and Information Technology

Language: English

Topic: Retinal Imaging and Analysis

Subfield: Radiology, Nuclear Medicine and Imaging

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: green

OpenAlex ID: W6912103205

Cites:

Cited by:

Related to: