Related Experiment Video
Updated: Sep 3, 2025
08:27
Quantification of Oculomotor Responses and Accommodation Through Instrumentation and Analysis Toolboxes
Published on: March 3, 2023
1.0K
Automated Measurement of Ocular Movements Using Deep Learning-Based Image Analysis
Lixia Lou1, Yiming Sun1, Xingru Huang2
1Department of Ophthalmology, The Second Affiliated Hospital of Zhejiang University, School of Medicine, Hangzhou, China.
Current Eye Research
|July 28, 2022
Summary
A new deep learning method accurately measures ocular movements from photographs, showing excellent agreement with manual methods. This automated approach aids in diagnosing and managing motility disorders and reveals age-related changes in eye movement.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Clinical assessment of ocular movements is crucial for diagnosing and managing ocular motility disorders.
- Current methods for measuring ocular movements can be subjective and time-consuming.
Purpose of the Study:
- To develop and validate a deep learning-based image analysis tool for automatic measurement of ocular movements.
- To investigate the relationship between ocular movements and age in healthy individuals.
Main Methods:
- Photographs of 207 healthy volunteers (aged 5-60 years) were taken in cardinal gaze positions.
- Ocular movements were manually measured using ImageJ and automatically measured via a deep learning algorithm.
- Agreement between manual and automated measurements was assessed using correlation and Bland-Altman analyses.
Main Results:
- The deep learning method demonstrated excellent agreement with manual measurements, with intraclass correlation coefficients ranging from 0.802 to 0.848.
- Specific average measurements for six extraocular muscles were reported.
- Ocular movements were found to be negatively related to age in all cardinal gaze positions.
Conclusions:
- The automated deep learning approach provides objective and reliable measurements of ocular movements, comparable to manual methods.
- This technology has significant potential for improving the diagnosis and management of ocular motility disorders.
- The study identified age-related declines in ocular movement parameters.
