Related Experiment Video
Updated: Apr 15, 2026
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.7K
Optic disc segmentation by balloon snake with texture from color fundus image
Jinyang Sun1, Fangjun Luan1, Hanhui Wu2
1School of Information & Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China.
International Journal of Biomedical Imaging
|April 11, 2015
Summary
This study introduces a new method for segmenting the optic nerve head in fundus images to improve glaucoma diagnosis. The novel approach achieves high accuracy, outperforming traditional methods for optic disc segmentation.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Glaucoma diagnosis relies on optic nerve head examination from fundus images.
- Optic nerve head segmentation is challenging due to fuzzy boundaries and peripapillary atrophy (PPA).
Purpose of the Study:
- To propose a novel and accurate method for optic nerve head segmentation in fundus images.
- To address the limitations of existing segmentation techniques, particularly concerning PPA and vessel interference.
Main Methods:
- Region of Interest (ROI) identification using template matching.
- Vessel erasing within the ROI via PDE inpainting for boundary smoothing.
- Optic disc segmentation utilizing image texture analysis and a clustering method to reduce noise.
- Employing a balloon snake model with image texture replacing image force and an internal initial contour to mitigate PPA effects.
Main Results:
- The proposed method demonstrates superior performance compared to traditional segmentation approaches.
- Achieved an average segmentation Dice coefficient of 94%.
Conclusions:
- The novel optic nerve head segmentation method is effective and accurate.
- This technique offers a significant improvement for glaucoma diagnosis support systems.
