Related Experiment Video
Updated: Dec 24, 2025
12:28
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
Published on: March 12, 2022
4.1K
An Effective Retinal Blood Vessel Segmentation by Using Automatic Random Walks Based on Centerline Extraction
Jianqing Gao1,2, Guannan Chen3,4, Wenru Lin5,6
1Smart Home Information Collection and Processing on Internet of Things Laboratory of Digital Fujian, Fujian Jiangxia University, Fuzhou 350108, China.
Biomed Research International
|April 14, 2020
Summary
This study introduces an automatic method for retinal blood vessel segmentation using random walk algorithms. The new approach enhances accuracy and sensitivity in detecting vessels in retinal images.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Retinal blood vessel analysis is crucial for diagnosing various eye diseases.
- Accurate segmentation of retinal vasculature is challenging due to complex morphology.
Purpose of the Study:
- To propose an automatic method for retinal blood vessel segmentation.
- To improve the sensitivity and accuracy of vessel detection in normal and pathological retinal images.
Main Methods:
- Utilized Hessian-based multiscale vascular enhancement filtering for vessel structure visualization.
- Employed a random walk algorithm for segmentation, robust to weak boundaries.
- Extracted vessel centerlines using normalized gradient vector field divergence and morphological methods to label seed points.
Main Results:
- The proposed method demonstrated high sensitivity in detecting retinal blood vessels.
- Experimental results on the STARE database showed superior performance compared to existing methods.
- The technique proved effective in segmenting vessels in both normal and abnormal retinal regions.
Conclusions:
- The developed random walk-based method offers a sensitive and accurate approach for retinal blood vessel segmentation.
- This automated technique has significant potential for clinical diagnosis of retinal diseases.
