Automatic Determination of Endothelial Cell Density From Donor Cornea Endothelial Cell Images
Translational Vision Science & Technology · 23.08.2024 · 13 (8) · 40
DOI: 10.1167/tvst.13.8.40 ↗Kurz gefasst
Fachartikel in der Zeitschrift Translational Vision Science & Technology, erschienen am 23.08.2024. Verfasst von Beth Ann M Benetz und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology and Visual Sciences, Case Western Reserve University, Cleveland, OH, USA. Hauptthemen laut MEDLINE: Endothelium, Corneal, Tissue Donors. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NCRR NIH HHS, NIBIB NIH HHS, NEI NIH HHS.
Abstract (Originalsprache)
Purpose
To determine endothelial cell density (ECD) from real-world donor cornea endothelial cell (EC) images using a self-supervised deep learning segmentation model.
Methods
Two eye banks (Eversight, VisionGift) provided 15,138 single, unique EC images from 8169 donors along with their demographics, tissue characteristics, and ECD. This dataset was utilized for self-supervised training and deep learning inference. The Cornea Image Analysis Reading Center (CIARC) provided a second dataset of 174 donor EC images based on image and tissue quality. These images were used to train a supervised deep learning cell border segmentation model. Evaluation between manual and automated determination of ECD was restricted to the 1939 test EC images with at least 100 cells counted by both methods.
Results
The ECD measurements from both methods were in excellent agreement with rc of 0.77 (95% confidence interval [CI], 0.75-0.79; P < 0.001) and bias of 123 cells/mm2 (95% CI, 114-131; P < 0.001); 81% of the automated ECD values were within 10% of the manual ECD values. When the analysis was further restricted to the cropped image, the rc was 0.88 (95% CI, 0.87-0.89; P < 0.001), bias was 46 cells/mm2 (95% CI, 39-53; P < 0.001), and 93% of the automated ECD values were within 10% of the manual ECD values.
Conclusions
Deep learning analysis provides accurate ECDs of donor images, potentially reducing analysis time and training requirements. Translational Relevance: The approach of this study, a robust methodology for automatically evaluating donor cornea EC images, could expand the quantitative determination of endothelial health beyond ECD.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Ophthalmology and Visual Sciences, Case Western Reserve University, Cleveland, OH, USA.
- Cornea Image Analysis Reading Center, University Hospitals Eye Institute, Cleveland, OH, USA.
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA.
- Eversight, Ann Arbor, MI, USA.
- Center for Vision and Eye Banking Research, Eversight, Cleveland, OH, USA.
- VisionGift, Portland, OR, USA.
Förderung
- NCRR NIH HHS
- NIBIB NIH HHS
- NEI NIH HHS
Zitieren
APA
Benetz, B. A. M., Shivade, V. S., Joseph, N. M., Romig, N. J., McCormick, J. C., Chen, J., Titus, M. S., Sawant, O. B., Clover, J. M., Yoganathan, N., Menegay, H. J., O'Brien, R. C., Wilson, D. L., & Lass, J. H. (2024). Automatic Determination of Endothelial Cell Density From Donor Cornea Endothelial Cell Images. Translational Vision Science & Technology, 13(8), 40. https://doi.org/10.1167/tvst.13.8.40
Vancouver
Benetz BAM, Shivade VS, Joseph NM, Romig NJ, McCormick JC, Chen J, et al. Automatic Determination of Endothelial Cell Density From Donor Cornea Endothelial Cell Images. Translational Vision Science & Technology. 2024;13(8):40. doi:10.1167/tvst.13.8.40
BibTeX
@article{Benetz2024,
author = {Benetz, Beth Ann M and Shivade, Ved S and Joseph, Naomi M and Romig, Nathan J and McCormick, John C and Chen, Jiawei and Titus, Michael S and Sawant, Onkar B and Clover, Jameson M and Yoganathan, Nathan and Menegay, Harry J and O'Brien, Robert C and Wilson, David L and Lass, Jonathan H},
title = {Automatic Determination of Endothelial Cell Density From Donor Cornea Endothelial Cell Images},
journal = {Translational Vision Science & Technology},
year = {2024},
volume = {13},
number = {8},
pages = {40},
doi = {10.1167/tvst.13.8.40}
}
EUVIMED