Related Experiment Video
Updated: May 4, 2026
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
Published on: March 12, 2022
Automatic segmentation and measurement of vasculature in retinal fundus images using probabilistic formulation
Yi Yin1, Mouloud Adel1, Salah Bourennane1
1Institut Fresnel, Ecole Centrale de Marseille, Aix-Marseille Université, Domaine Universitaire de Saint-Jérôme, 13397 Marseille, France.
Insights
This study presents a new method for automatically analyzing retinal blood vessels using probabilistic tracking. The approach achieves high accuracy in segmenting and measuring retinal vessels, aiding in computer-aided diagnosis.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Automatic analysis of retinal blood vessels is crucial for computer-aided diagnosis.
- Existing methods may struggle with diverse vessel structures and edge detection.
Purpose of the Study:
- To introduce a novel probabilistic tracking-based method for automatic retinal blood vessel segmentation.
- To evaluate the method's accuracy in vessel segmentation, width measurement, and structure identification.
Main Methods:
- Utilized a probabilistic tracking approach for vessel segmentation.
- Incorporated vessel edge detection across the entire retinal image.
- Employed a Bayesian method with maximum a posteriori (MAP) criterion for edge point detection.
Main Results:
- Achieved high accuracy in segmenting retinal blood vessels.
- Demonstrated precise width measurements and accurate vessel structure identification.
- Reported high sensitivity and specificity on publicly available datasets (STARE, DRIVE).
Conclusions:
- The proposed probabilistic tracking method offers a robust solution for automatic retinal vessel analysis.
- This technique shows significant potential for improving computer-aided diagnosis systems in ophthalmology.
Abstract:
The automatic analysis of retinal blood vessels plays an important role in the computer-aided diagnosis. In this paper, we introduce a probabilistic tracking-based method for automatic vessel segmentation in retinal images. We take into account vessel edge detection on the whole retinal image and handle different vessel structures. During the tracking process, a Bayesian method with maximum a posteriori (MAP) as criterion is used to detect vessel edge points. Experimental evaluations of the tracking algorithm are performed on real retinal images from three publicly available databases: STARE (Hoover et al., 2000), DRIVE (Staal et al., 2004), and REVIEW (Al-Diri et al., 2008 and 2009). We got high accuracy in vessel segmentation, width measurements, and vessel structure identification. The sensitivity and specificity on STARE are 0.7248 and 0.9666, respectively. On DRIVE, the sensitivity is 0.6522 and the specificity is up to 0.9710.
