Related Experiment Video
Updated: Jul 10, 2026
09:17
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
Segmentation of optic nerve head using warping and RANSAC.
Sun Kwon Kim1, Hyoun-Joong Kong, Jong-Mo Seo
1Interdisciplinary Program, Biomedical Engineering Major, Graduate School of Seoul National University, Seoul, Korea.
Summary
This study introduces a new method for segmenting the optic nerve head in retinal images, crucial for detecting early glaucoma damage. The technique achieved 91% sensitivity and 78% positive predictability in identifying retinal nerve fiber layer defects.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Glaucoma is a leading cause of irreversible blindness worldwide.
- Early detection of glaucomatous optic nerve damage is critical for preserving vision.
- Retinal nerve fiber layer (RNFL) defects are early indicators of this damage.
Purpose of the Study:
- To develop and evaluate an automated method for segmenting the optic nerve head (ONH) in RNFL photographs.
- To establish the accuracy of the proposed ONH segmentation technique for early glaucoma diagnosis.
Main Methods:
- Image processing techniques including warping were employed.
- Random Sample Consensus (RANSAC) algorithm was utilized for robust ONH segmentation.
- The method was evaluated based on sensitivity and positive predictability.
Main Results:
- The proposed method demonstrated a sensitivity of 91% for optic nerve head segmentation.
- A positive predictability of 78% was achieved for the segmentation accuracy.
- Accurate ONH segmentation is a prerequisite for evaluating RNFL defects.
Conclusions:
- The developed warping and RANSAC-based method provides an effective approach for optic nerve head segmentation.
- This automated technique shows promise for improving early detection of glaucoma.
- Accurate segmentation is vital for quantitative analysis of RNFL and timely intervention.
