Related Experiment Video
Updated: Aug 10, 2025
09:17
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
21.7K
Retinal Blood-Vessel Extraction Using Weighted Kernel Fuzzy C-Means Clustering and Dilation-Based Functions
1Technology and Business Information System Unit, Mahasarakham Business School, Mahasarakham University, Mahasarakham 44150, Thailand.
Diagnostics (Basel, Switzerland)
|February 11, 2023
Summary
This study introduces an improved method for automated blood vessel extraction in retinal images, crucial for diagnosing diabetic retinopathy (DR). The novel WKFCM-DBF approach enhances accuracy, especially in challenging low-intensity images and complex DR cases.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Automated blood vessel extraction is vital for diagnosing diabetic retinopathy (DR) and other eye diseases.
- Traditional methods struggle with low-intensity images, simultaneous extraction of micro/large vessels, and DR-affected vessels.
Purpose of the Study:
- To propose a robust preprocessing and novel blood vessel extraction method for enhanced accuracy in retinal images.
- To address limitations of existing methods in challenging diagnostic scenarios.
Main Methods:
- A three-stage approach combining Weighted Kernel Fuzzy C-Means (WKFCM) clustering and a Dilation-Based Function (DBF) model.
- Preprocessing enhances retinal images, followed by WKFCM for initial extraction, DBF for regional feature recognition, and thresholding for refinement.
Main Results:
- The WKFCM-DBF method achieved high performance across DRIVE, STARE, and DiaretDB0 datasets.
- Sensitivities, specificities, and accuracies consistently exceeded 98% on all tested datasets.
Conclusions:
- The proposed WKFCM-DBF method significantly improves automated blood vessel extraction accuracy.
- This technique offers a reliable solution for diagnosing DR and other retinal conditions, even with difficult image qualities.
