Related Experiment Video
Updated: Mar 7, 2026
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
Published on: March 12, 2022
Selective Search and Intensity Context Based Retina Vessel Image Segmentation
Zhaohui Tang1, Jin Zhang2, Weihua Gui1
1School of Information Science and Engineering, Central South University, Changsha, Hunan, 410083, China.
Insights
A novel contextual feature, influence degree of average intensity, enhances retinal vessel segmentation for eye disease diagnosis. This computer-aided diagnosis method achieves high accuracy, comparable to state-of-the-art techniques.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer-Aided Diagnosis
Background:
- Accurate retinal vessel segmentation is crucial for diagnosing eye diseases.
- Existing methods may face challenges in precise vessel identification.
Purpose of the Study:
- To introduce a new contextual image feature for improved retinal vessel segmentation.
- To develop a computer-aided diagnosis approach for eye disease detection.
Main Methods:
- Proposed a novel feature: influence degree of average intensity.
- Utilized Hessian matrix for candidate region detection and accelerated segmentation.
- Constructed contextual feature vectors and employed a classifier for pixel-wise vessel/non-vessel classification.
Main Results:
- Demonstrated effectiveness using receiver operating characteristic analysis on DRIVE and STARE databases.
- Achieved high performance: average accuracy (0.9611 on DRIVE, 0.9547 on STARE), sensitivity (0.8174 on DRIVE, 0.7768 on STARE), and specificity (0.9747 on DRIVE, 0.9751 on STARE).
- Method is comparable to current state-of-the-art techniques.
Conclusions:
- The proposed influence degree of average intensity feature significantly improves retinal vessel segmentation.
- This method offers a promising approach for computer-aided diagnosis of eye diseases.
- The technique demonstrates robust performance on benchmark datasets.
Abstract:
In the framework of computer-aided diagnosis of eye disease, a new contextual image feature named influence degree of average intensity is proposed for retinal vessel image segmentation. This new feature evaluates the influence degree of current detected pixel decreasing the average intensity of the local row where that pixel located. Firstly, Hessian matrix is introduced to detect candidate regions, for the reason of accelerating segmentation. Then, the influence degree of average intensity of each pixel is extracted. Next, contextual feature vector for each pixel is constructed by concatenating the 8 feature neighbors. Finally, a classifier is built to classify each pixel into vessel or non-vessel based on its contextual feature. The effectiveness of the proposed method is demonstrated through receiver operating characteristic analysis on the benchmarked databases of DRIVE and STARE. Experiment results show that our method is comparable with the state-of-the-art methods. For example, the average accuracy, sensitivity, specificity achieved on the database DRIVE and STARE are 0.9611, 0.8174, 0.9747 and 0.9547, 0.7768, 0.9751, respectively.
