Related Experiment Video
Updated: Jun 26, 2026
09:17
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
Level-set based automatic cup-to-disc ratio determination using retinal fundus images in ARGALI.
1Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore.
Summary
An automated method accurately measures the optic cup-to-disc ratio (CDR) from retinal images, aiding early glaucoma detection. This technique shows potential for widespread glaucoma screening by providing clinically acceptable results.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Glaucoma is a primary cause of irreversible blindness.
- Early detection of glaucoma is crucial for limiting disease progression.
- Manual determination of the optic cup-to-disc ratio (CDR) limits mass screening potential.
Purpose of the Study:
- To develop an automated method for determining the optic cup-to-disc ratio (CDR) from retinal fundus images.
- To integrate this method into the ARGALI system for automated glaucoma risk assessment.
Main Methods:
- A variational level-set approach was employed to segment the optic disc and cup.
- Preprocessing involved threshold analysis for initial contour estimation.
- Post-processing incorporated ellipse fitting to refine contours affected by retinal vasculature.
Main Results:
- The automated CDR determination method was tested on 104 images.
- Results demonstrated a clinically acceptable variation of up to 0.2 CDR units compared to manual grading.
- The method shows promise for application in mass glaucoma screening.
Conclusions:
- The proposed automated CDR determination method is effective for glaucoma screening.
- The technique offers a viable alternative to manual CDR assessment.
- This automated approach has the potential to improve early glaucoma detection rates.
