Generalizability of Deep Neural Networks for Vertical Cup-to-Disc Ratio Estimation in Ultra-Widefield and Smartphone-Based Fundus Images
Translational Vision Science & Technology · 2024
DOI: 10.1167/tvst.13.4.6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Translational Vision Science & Technology, 2024. Verfasst von Boon Peng Yap und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore. Hauptthemen laut MEDLINE: Ophthalmology, Telemedicine. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Purpose
To develop and validate a deep learning system (DLS) for estimation of vertical cup-to-disc ratio (vCDR) in ultra-widefield (UWF) and smartphone-based fundus images.
Methods
A DLS consisting of two sequential convolutional neural networks (CNNs) to delineate optic disc (OD) and optic cup (OC) boundaries was developed using 800 standard fundus images from the public REFUGE data set. The CNNs were tested on 400 test images from the REFUGE data set and 296 UWF and 300 smartphone-based images from a teleophthalmology clinic. vCDRs derived from the delineated OD/OC boundaries were compared with optometrists' annotations using mean absolute error (MAE). Subgroup analysis was conducted to study the impact of peripapillary atrophy (PPA), and correlation study was performed to investigate potential correlations between sectoral CDR (sCDR) and retinal nerve fiber layer (RNFL) thickness.
Results
The system achieved MAEs of 0.040 (95% CI, 0.037-0.043) in the REFUGE test images, 0.068 (95% CI, 0.061-0.075) in the UWF images, and 0.084 (95% CI, 0.075-0.092) in the smartphone-based images. There was no statistical significance in differences between PPA and non-PPA images. Weak correlation (r = -0.4046, P < 0.05) between sCDR and RNFL thickness was found only in the superior sector.
Conclusions
We developed a deep learning system that estimates vCDR from standard, UWF, and smartphone-based images. We also described anatomic peripapillary adversarial lesion and its potential impact on OD/OC delineation. Translational Relevance: Artificial intelligence can estimate vCDR from different types of fundus images and may be used as a general and interpretable screening tool to improve community reach for diagnosis and management of glaucoma.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore.
- Department of Ophthalmology, Tan Tock Seng Hospital, Singapore, Singapore.
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore.
- National Healthcare Group Eye Institute, Singapore, Singapore.
Zitieren
APA
Yap, B. P., Kelvin, L. Z., Toh, E. Q., Low, K. Y., Rani, S. K., Goh, E. J. H., Hui, V. Y. C., Ng, B. K., & Lim, T. H. (2024). Generalizability of Deep Neural Networks for Vertical Cup-to-Disc Ratio Estimation in Ultra-Widefield and Smartphone-Based Fundus Images. Translational Vision Science & Technology. https://doi.org/10.1167/tvst.13.4.6
Vancouver
Yap BP, Kelvin LZ, Toh EQ, Low KY, Rani SK, Goh EJH, et al. Generalizability of Deep Neural Networks for Vertical Cup-to-Disc Ratio Estimation in Ultra-Widefield and Smartphone-Based Fundus Images. Translational Vision Science & Technology. 2024. doi:10.1167/tvst.13.4.6
BibTeX
@article{Yap2024,
author = {Yap, Boon Peng and Kelvin, Li Zhenghao and Toh, En Qi and Low, Kok Yao and Rani, Sumaya Khan and Goh, Eunice Jin Hui and Hui, Vivien Yip Cherng and Ng, Beng Koon and Lim, Tock Han},
title = {Generalizability of Deep Neural Networks for Vertical Cup-to-Disc Ratio Estimation in Ultra-Widefield and Smartphone-Based Fundus Images},
journal = {Translational Vision Science & Technology},
year = {2024},
doi = {10.1167/tvst.13.4.6}
}
EUVIMED