Presentation
3 April 2024 Semi-automatic analysis of donor cornea EC images using SSL and image editing software
Ved Shivade, Nathan Romig, John McCormick, Naomi Joseph, Jonathan Lass, Beth Benetz, David Wilson
Author Affiliations +
Abstract
In assessing Endothelial Cell Density (ECD), a critical measure of corneal health, eye bank technicians rely on manual methods that are time-consuming and potentially inconsistent, typically analyzing only 100-300 of nearly 1,000 captured endothelial cells per image. We introduce a self-supervised vision transformer model that accurately segments 100-1,263 cells and calculates ECDs, with a mean difference of 9.74% and 87% alignment with eye-bank-determined ECD. Integrated into a robust software-editor, our system offers an efficient approach to ECD analysis, presenting a significant value proposition for eye banks.
Conference Presentation
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ved Shivade, Nathan Romig, John McCormick, Naomi Joseph, Jonathan Lass, Beth Benetz, and David Wilson "Semi-automatic analysis of donor cornea EC images using SSL and image editing software", Proc. SPIE 12930, Medical Imaging 2024: Clinical and Biomedical Imaging, 129301A (3 April 2024); https://doi.org/10.1117/12.3009714
Advertisement
Advertisement
KEYWORDS
Image segmentation

Image analysis

Machine learning

Cornea

Eye

Eye models

Education and training

RELATED CONTENT

How do we search?
Proceedings of SPIE (September 22 1997)

Back to Top