Related Experiment Video
Updated: May 25, 2026
08:54
A Workflow to Quantitatively Determine Age-Related Macular Degeneration Lesion-Specific Variations in Fundus Autofluorescence
Published on: May 26, 2023
Computerized detection of peripapillary chorioretinal atrophy by texture analysis
Chisako Muramatsu1, Yuji Hatanaka, Akira Sawada
1Department of Intelligent Image Information, Graduate School of Medicine, Gifu University, Gifu 501-1194, Japan. chisa@fjt.info.gifu-u.ac.jp
Summary
Peripapillary chorioretinal atrophy (PPA) is a glaucoma risk factor. Computerized detection using texture analysis achieved 73% sensitivity and 95% specificity in identifying PPA in retinal images.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Peripapillary chorioretinal atrophy (PPA) is a known risk factor for glaucoma.
- PPA appears as bright regions in retinal fundus images, potentially causing errors in automated optic disc detection.
- Accurate identification of PPA is crucial for glaucoma risk assessment and improving optic disc segmentation algorithms.
Purpose of the Study:
- To develop and evaluate a computerized method for detecting peripapillary chorioretinal atrophy (PPA) in retinal fundus images.
- To assess the potential of automated PPA detection for glaucoma risk stratification.
- To improve the accuracy of automated optic disc segmentation by excluding PPA regions.
Main Methods:
- Texture analysis was employed to identify regions of PPA.
- The proposed method was tested on a dataset of retinal fundus images.
- Performance metrics including sensitivity and specificity were calculated to evaluate detection accuracy.
Main Results:
- The computerized detection method achieved a sensitivity of 73% for moderate to severe PPA.
- The specificity for detecting PPA regions was 95%.
- The texture analysis approach demonstrated effectiveness in differentiating PPA from other retinal structures.
Conclusions:
- The developed computerized method shows promise for the automated detection of PPA in retinal fundus images.
- Accurate PPA identification can aid in glaucoma risk assessment.
- This technique may enhance the performance of automated systems for optic disc analysis.
