Related Experiment Video
Updated: Dec 22, 2025
Author Spotlight: Understanding Age-Related Macular Degeneration Pathophysiology with QAF Workflow
Published on: May 26, 2023
Automatic detection of parapapillary atrophy and its association with children myopia
Hanxiang Li1, Huiqi Li1, Jieliang Kang1
1School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China.
Insights
An automatic algorithm accurately detects parapapillary atrophy (PPA) in retinal images. Changes in PPA, especially width, strongly correlate with myopia progression in children, aiding diagnosis.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computational Biology
Background:
- Parapapillary atrophy (PPA) is a key indicator in retinal fundus images.
- Understanding PPA's association with myopia is crucial for early diagnosis and prediction in children.
Purpose of the Study:
- To develop an automated algorithm for detecting and segmenting PPA in retinal images.
- To investigate the relationship between PPA characteristics and myopia development in pediatric populations.
Main Methods:
- An algorithm was developed for PPA identification and segmentation.
- Performance was evaluated against ophthalmologist annotations.
- Spearman correlation analysis assessed the association between PPA parameters and myopia indicators.
Main Results:
- The PPA identification accuracy reached 90.78%.
- PPA segmentation achieved an F1-score of 0.67.
- PPA parameters (area, ratio, width) showed significant correlations with myopia progression metrics (axial length, spherical equivalent).
- Maximal PPA width change demonstrated the strongest association (0.75) with the ratio of axial length to corneal curvature.
Conclusions:
- The automated algorithm provides reliable PPA measurements.
- Significant associations between PPA changes and childhood myopia progression were identified.
- Maximal PPA width is the most indicative parameter for myopia progression.
Background And Objective:
To develop an automatic parapapillary atrophy (PPA) detection algorithm in retinal fundus images and discuss the association between PPA and myopia to facilitate diagnosis and prediction of children myopia.
Methods:
The proposed algorithm consists of PPA identification and segmentation, which are evaluated by comparing with ophthalmologist's annotation. The association between PPA parameters and myopia is analyzed via Spearman correlation.
Results:
The accuracy of PPA identification reaches 90.78%. The F1-score of PPA segmentation is 0.67, and the Pearson correlation between the automatic measurement and ground truths for the area of PPA (APPA), the ratio (μ) of APPA to the area of optic disc (OD) and the maximal width of PPA (W) are 0.74, 0.60, and 0.69 (all p < 0.001). All these parameter changes are significantly correlated with the change of ratio of axial length to corneal curvature (ΔALCC), spherical equivalent (ΔSE), and axial length (ΔAL) (all p < 0.01), in which the highest association is 0.75 between ΔW (the change of W) and ΔALCC.
Conclusions:
The proposed algorithm can provide accurate PPA measurement. Strong association between the changes of PPA and the progress of children myopia are observed and the width of PPA has the best association among three PPA parameters.
