Related Experiment Video
Updated: Jun 5, 2026
10:11
Fundus Photography as a Convenient Tool to Study Microvascular Responses to Cardiovascular Disease Risk Factors in Epidemiological Studies
Published on: October 22, 2014
Vessel boundary delineation on fundus images using graph-based approach.
Xiayu Xu1, Meindert Niemeijer, Qi Song
1Department of Biomedical Engineering, University of Iowa, Iowa City, IA 52242, USA.
IEEE Transactions on Medical Imaging
|January 11, 2011
Summary
This study introduces a novel graph-based algorithm for precise retinal vessel width measurement in fundus images. The method achieves subpixel accuracy, aiding in understanding vessel width variations in relation to the optic disc.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Accurate measurement of retinal vessel width is crucial for diagnosing and monitoring various eye conditions.
- Existing methods for retinal vessel segmentation and width measurement face challenges in accuracy and robustness.
Purpose of the Study:
- To develop and validate a novel graph-based algorithm for simultaneous segmentation of retinal vessel edges.
- To accurately measure retinal vessel width with subpixel precision.
Main Methods:
- The algorithm models simultaneous two-boundary segmentation as a 3-D surface segmentation problem.
- It converts this into finding a minimum closed set in a node-weighted graph.
- Initial segmentation is derived from a vessel probability image.
Main Results:
- The algorithm demonstrates robust performance in estimating vessel width with subpixel accuracy.
- Evaluation on the REVIEW database confirms its diameter measurement capabilities.
- The method was applied to analyze vessel width in 600 subjects.
Conclusions:
- The proposed graph-based algorithm offers a reliable and accurate method for retinal vessel width measurement.
- This technique has potential applications in clinical research for exploring correlations between vessel morphology and disease.
