Related Experiment Video
Updated: Mar 6, 2026
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
Published on: March 12, 2022
Artery/vein classification of retinal blood vessels using feature selection
Insights
This study introduces a new method for classifying retinal vessels in fundus images to calculate the artery/vein ratio (AVR). The approach achieved 97.2% accuracy, aiding in diagnosing cardiovascular and retinal disorders.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Automated retinal vessel classification is crucial for diagnosing cardiovascular and retinal disorders.
- Accurate measurement of the artery/vein ratio (AVR) aids in early detection of abnormalities.
Purpose of the Study:
- To present a novel automated approach for retinal vessel classification.
- To compute the artery/vein ratio (AVR) for all blood vessel segments in fundus images.
Main Methods:
- Feature extraction followed by Random Forests (RF) for feature selection.
- Classification using a polynomial kernel Support Vector Machine (SVM).
- Training with 10-fold cross-validation on the VICAVR dataset and testing on an independent dataset.
Main Results:
- The Light plane of the LAB color space provided the most dominant feature for classification.
- Achieved an average Area Under the ROC Curve (AUC) of 97.2% over 100 runs.
- The algorithm demonstrated robustness and potential for similar accuracies across datasets.
Conclusions:
- The proposed method offers a robust and accurate solution for retinal vessel classification.
- This technique can be valuable for screening and diagnosing vessel abnormalities related to systemic diseases.
- The feature selection process enhances the reliability of the artery/vein ratio computation.
Abstract:
Automated classification of retinal vessels in fundus images is the first step towards measurement of retinal characteristics that can be used to screen and diagnose vessel abnormalities for cardiovascular and retinal disorders. This paper presents a novel approach to vessel classification to compute the artery/vein ratio (AVR) for all blood vessel segments in the fundus image. The features extracted are then subjected to a selection procedure using Random Forests (RF) where the features that contribute most to classification accuracy are chosen as input to a polynomial kernel Support Vector Machine (SVM) classifier. The most dominant feature was found to be the vessel information obtained from the Light plane of the LAB color space. The SVM is then subjected to one time training using 10-fold cross validation on images randomly selected from the VICAVR dataset before testing on an independent test dataset, derived from the same database. An Area Under the ROC Curve (AUC) of 97.2% was obtained on an average of 100 runs of the algorithm. The proposed algorithm is robust due to the feature selection procedure, and it is possible to get similar accuracies across many datasets.
