Related Experiment Video
Updated: Mar 21, 2026
12:22
Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT
Published on: August 4, 2018
9.1K
Automatic optic disc localization and segmentation in retinal images by a line operator and level sets
Fulong Ren1,2, Wei Li2, Jinzhu Yang1,2
1School of Information Science & Engineering, Northeastern University, Shenyang, Liaoning, China.
Summary
This study presents an effective method for accurately locating and segmenting the optic disc (OD) in retinal images, improving early eye disease detection.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Current methods struggle with optic disc (OD) localization and segmentation in retinal images.
- Challenges include imprecise boundaries, variable image contrast, and misleading edge features.
Purpose of the Study:
- To accurately locate the optic disc (OD).
- To precisely detect the optic disc (OD) boundary.
Main Methods:
- A multi-stage strategy was employed for OD detection.
- Candidate regions identified using high-intensity features and vessel convergence.
- Accurate OD localization via a line operator filter for circular brightness features.
- OD boundary estimation using an active contour model and ellipse fitting.
Main Results:
- Achieved 98.67% accuracy in OD identification.
- Demonstrated a mean distance of 2 pixels for OD boundary detection.
Conclusions:
- The proposed method enables fast, automatic, and accurate OD localization and boundary detection.
- Contributes to improved OD evaluation and automated screening for early eye diseases.
