Optic Cup and Disc Segmentation of Fundus Images Using Artificial Intelligence Externally Validated With Optical Coherence Tomography Measurements
Translational Vision Science & Technology · 24.06.2025 · 14 (6) · 30
DOI: 10.1167/tvst.14.6.30 ↗Kurz gefasst
Fachartikel in der Zeitschrift Translational Vision Science & Technology, erschienen am 24.06.2025. Verfasst von Scott Kinder und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, University of Colorado Anschutz Medical Campus, Aurora, CO, USA. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Optic Disk, Artificial Intelligence, Glaucoma. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Purpose
To develop an artificial intelligence (AI) optic cup and disc segmentation pipeline for obtaining optic nerve head (ONH) measurements such as vertical cup-to-disc ratio (VCDR) from fundus images and externally validate performance against optical coherence tomography (OCT) measurements.
Methods
This diagnostic study used a retrospectively collected dataset of 27,252 fundus images associated with 12,477 OCT reports and 21,714 expert assessments of VCDR from electronic health records (EHRs) for 4289 patients inclusive of glaucoma suspects, primary and secondary glaucoma. The AI pipeline was trained on nine public glaucoma datasets and externally validated on a private hospital dataset and a publicly available dataset.
Results
AI VCDR predictions against OCT yielded mean absolute error (MAE), Pearson's R, and concordance correlation coefficient (CCC) values of 0.097 (95% confidence interval [CI], 0.095-0.099), 0.80 (95% CI, 0.79-0.81), and 0.66 (95% CI, 0.64-0.67), respectively. EHR VCDRs against OCT had MAE, Pearson's R, and CCC values of 0.086 (95% CI, 0.084-0.087), 0.77 (95% CI, 0.76-0.78), and 0.74 (95% CI, 0.73-0.75), respectively. The coefficient of variation (CV) of the AI pipeline on same-day images was 2.79%.
Conclusions
The proposed AI pipeline had strong correlation with OCT measurements and performed comparably to EHR assessments, with high repeatability. Increased diversity and cardinality of training data improved performance and generalizability to unseen datasets. Translational Relevance: AI pipelines for fundus images can provide ONH measurements such as VCDR near expert level in new patient populations without the need for additional model training.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Ophthalmology, University of Colorado Anschutz Medical Campus, Aurora, CO, USA.
- Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, USA.
Zitieren
APA
Kinder, S., McNamara, S., Clark, C., Bearce, B., Thakuria, U., Veturi, Y. A., Deitz, G., de Carlo Forest, T. E., Mandava, N., Kahook, M. Y., Singh, P., & Kalpathy-Cramer, J. (2025). Optic Cup and Disc Segmentation of Fundus Images Using Artificial Intelligence Externally Validated With Optical Coherence Tomography Measurements. Translational Vision Science & Technology, 14(6), 30. https://doi.org/10.1167/tvst.14.6.30
Vancouver
Kinder S, McNamara S, Clark C, Bearce B, Thakuria U, Veturi YA, et al. Optic Cup and Disc Segmentation of Fundus Images Using Artificial Intelligence Externally Validated With Optical Coherence Tomography Measurements. Translational Vision Science & Technology. 2025;14(6):30. doi:10.1167/tvst.14.6.30
BibTeX
@article{Kinder2025,
author = {Kinder, Scott and McNamara, Steve and Clark, Christopher and Bearce, Benjamin and Thakuria, Upasana and Veturi, Yoga Advaith and Deitz, Galia and de Carlo Forest, Talisa E and Mandava, Naresh and Kahook, Malik Y and Singh, Praveer and Kalpathy-Cramer, Jayashree},
title = {Optic Cup and Disc Segmentation of Fundus Images Using Artificial Intelligence Externally Validated With Optical Coherence Tomography Measurements},
journal = {Translational Vision Science & Technology},
year = {2025},
volume = {14},
number = {6},
pages = {30},
doi = {10.1167/tvst.14.6.30}
}
EUVIMED