Related Experiment Video
Updated: Mar 8, 2026
Comparing Objective Conjunctival Hyperemia Grading and the Ocular Surface Disease Index Score in Dry Eye Syndrome During COVID-19
Published on: May 25, 2022
Defining the Optimal Region of Interest for Hyperemia Grading in the Bulbar Conjunctiva
María Luisa Sánchez Brea1, Noelia Barreira Rodríguez1, Antonio Mosquera González2
1VARPA Group, Department of Computer Science, University of A Coruna, A Coruna, Spain.
Insights
This study introduces a computer-aided method for grading conjunctival hyperemia (redness). The automated system accurately assesses severity using a refined region of interest, mimicking expert diagnosis.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Conjunctival hyperemia, or redness, is a key indicator of various ocular diseases.
- Current diagnosis relies on subjective visual comparison with photographic charts, leading to variability.
- Grading accuracy is dependent on the grader's experience, making it non-repeatable.
Purpose of the Study:
- To develop and refine a computer-aided methodology for objective conjunctival hyperemia grading.
- To address inaccuracies in conjunctival segmentation caused by illumination variations.
- To identify the most relevant features within specific conjunctival regions for reliable grading.
Main Methods:
- Proposed a three-stage computer-aided methodology: conjunctival segmentation, feature extraction (color, blood vessels), and regression for grading.
- Analyzed the relevance of features based on their location within the conjunctiva.
- Focused on a reliable region of interest (ROI) to improve grading accuracy.
Main Results:
- The refined methodology demonstrated improved accuracy in grading conjunctival hyperemia.
- Identifying the most relevant features within a specific ROI minimized segmentation inaccuracies.
- The automated procedure achieved expert-level performance in grading severity.
Conclusions:
- A computer-aided approach can objectively and reliably grade conjunctival hyperemia.
- Focusing on a limited, relevant region of interest enhances diagnostic accuracy.
- This method offers a repeatable and potentially more accurate alternative to subjective visual assessment.
Abstract:
Conjunctival hyperemia or conjunctival redness is a symptom that can be associated with a broad group of ocular diseases. Its levels of severity are represented by standard photographic charts that are visually compared with the patient's eye. This way, the hyperemia diagnosis becomes a nonrepeatable task that depends on the experience of the grader. To solve this problem, we have proposed a computer-aided methodology that comprises three main stages: the segmentation of the conjunctiva, the extraction of features in this region based on colour and the presence of blood vessels, and, finally, the transformation of these features into grading scale values by means of regression techniques. However, the conjunctival segmentation can be slightly inaccurate mainly due to illumination issues. In this work, we analyse the relevance of different features with respect to their location within the conjunctiva in order to delimit a reliable region of interest for the grading. The results show that the automatic procedure behaves like an expert using only a limited region of interest within the conjunctiva.
