Enhanced Ocular Movement Analysis Through Deep Learning-Powered Image Processing
Main Article Content
Keywords
.
Abstract
Purpose: The clinical evaluation of ocular movements plays a crucial role in diagnosing and treating ocular motility disorders. This study introduces a novel deep learning-based image analysis technique for automatic measurement of ocular movements from photographs, aiming to explore the relationship between ocular movements and age.
Methods: A cohort of 207 healthy volunteers (414 eyes), spanning ages 5 to 60 years, participated in the study. Photographs were taken capturing cardinal gaze positions. Manual measurements of ocular movements were conducted using ImageJ with a modified limbus test, alongside automated measurements using our deep learning-based image analysis. Correlation analyses and BlandAltman analyses were performed to evaluate agreement between manual and automated measurements. Additionally, generalized estimating
References
2. Vivian, A. J., & Morris, R. J. (1993). Diagrammatic representation of strabismus. Eye, 7(4),565–571. doi:10.1038/eye.1993.123.
3. Kennard, C. (2007). Examine eye movements. Practical Neurology, 7(5), 326–330.doi:10.1136/jnnp.2007.124388.
4. Hanif, S., Rowe, F. J., & O’Connor, A. R. (2009). A comparative review of methods torecord ocular rotations. British & Irish Orthoptic Journal, 6(0), 47–51.doi:10.22599/bioj.8.5.
5. Mai, G. (2005). Grading system for hyperfunction and hypofunction of extraocular muscles. Chinese Journal of Ophthalmology, 41(7), 663–666.
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.