Related Experiment Video
Updated: Feb 22, 2026
04:04
Measuring Retinal Vessel Diameter from Mouse Fluorescent Angiography Images
Published on: May 19, 2023
1.3K
Tracking and diameter estimation of retinal vessels using Gaussian process and Radon transform
Masoud Elhami Asl1, Navid Alemi Koohbanani1, Alejandro F Frangi2
1Tarbiat Modares University, Faculty of Electrical and Computer Engineering, Tehran, Iran.
Journal of Medical Imaging (Bellingham, Wash.)
|September 20, 2017
Summary
This study introduces a novel method for retinal blood vessel analysis, accurately tracking vessels and estimating diameters using Gaussian processes and Radon transforms. The approach demonstrates high performance in detecting bifurcations and thin vessels, aiding ophthalmic pathology diagnosis.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computational Biology
Background:
- Accurate retinal blood vessel extraction is crucial for diagnosing ophthalmic diseases.
- Existing methods face challenges with noise, bifurcations, and thin vessel detection.
Purpose of the Study:
- To develop and evaluate a novel approach for blood vessel tracking and diameter estimation in retinal images.
- To improve the accuracy of computer-aided diagnosis for ophthalmic pathologies.
Main Methods:
- Utilizing Gaussian processes (GPs) to model vessel curvature and diameter.
- Employing Local Radon transform for robust feature extraction and GP training.
- Implementing multiple GPs for bifurcation detection and quantifying directional differences.
Main Results:
- The proposed method achieves high accuracy in tracking thin vessels and detecting bifurcations.
- Demonstrates robustness against noise, handling complex cases like central arterial reflex.
- Achieved average sensitivity of 75.67%, specificity of 97.46%, and MCC of 72.18% on multiple datasets.
Conclusions:
- The combination of Radon features and Gaussian processes offers a powerful tool for retinal blood vessel analysis.
- This method shows comparable performance to state-of-the-art techniques and enhances diagnostic capabilities.
