Keratoconus Detection-based on Dynamic Corneal Deformation Videos Using Deep Learning
Ophthalmology Science · 2024-03 · 4 (2) · 100380
DOI: 10.1016/j.xops.2023.100380 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ophthalmology Science, 2024-03. Verfasst von Hazem Abdelmotaal und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, Assiut University, Assuit, Egypt. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Objective
To assess the performance of convolutional neural networks (CNNs) for automated detection of keratoconus (KC) in standalone Scheimpflug-based dynamic corneal deformation videos.
Design
Retrospective cohort study.
Participants
We retrospectively analyzed datasets with records of 734 nonconsecutive, refractive surgery candidates, and patients with unilateral or bilateral KC.
Methods
We first developed a video preprocessing pipeline to translate dynamic corneal deformation videos into 3-dimensional pseudoimage representations and then trained a CNN to directly identify KC from pseudoimages. We calculated the model's KC probability score cut-off and evaluated the performance by subjective and objective accuracy metrics using 2 independent datasets. Main Outcome Measures: Area under the receiver operating characteristics curve (AUC), accuracy, specificity, sensitivity, and KC probability score.
Results
The model accuracy on the test subset was 0.89 with AUC of 0.94. Based on the external validation dataset, the AUC and accuracy of the CNN model for detecting KC were 0.93 and 0.88, respectively.
Conclusions
Our deep learning-based approach was highly sensitive and specific in separating normal from keratoconic eyes using dynamic corneal deformation videos at levels that may prove useful in clinical practice. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ophthalmology, Assiut University, Assuit, Egypt.
- Hospital de Olhos-CRO, Guarulhos, São Paulo, Brazil.
- Department of Ophthalmology and Visual Sciences, Paulista Medical School, Federal University of São Paulo, São Paulo, Brazil.
- Poostchi Ophthalmology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran.
- Ruhr University, Bochum, Germany.
- Zentrum für Refraktive Chirurgie, Muenster, Germany.
Zitieren
APA
Abdelmotaal, H., Hazarbassanov, R. M., Salouti, R., Nowroozzadeh, M. H., Taneri, S., Al-Timemy, A. H., Lavric, A., & Yousefi, S. (2024). Keratoconus Detection-based on Dynamic Corneal Deformation Videos Using Deep Learning. Ophthalmology Science, 4(2), 100380. https://doi.org/10.1016/j.xops.2023.100380
Vancouver
Abdelmotaal H, Hazarbassanov RM, Salouti R, Nowroozzadeh MH, Taneri S, Al-Timemy AH, et al. Keratoconus Detection-based on Dynamic Corneal Deformation Videos Using Deep Learning. Ophthalmology Science. 2024;4(2):100380. doi:10.1016/j.xops.2023.100380
BibTeX
@article{Abdelmotaal2024,
author = {Abdelmotaal, Hazem and Hazarbassanov, Rossen Mihaylov and Salouti, Ramin and Nowroozzadeh, M Hossein and Taneri, Suphi and Al-Timemy, Ali H and Lavric, Alexandru and Yousefi, Siamak},
title = {Keratoconus Detection-based on Dynamic Corneal Deformation Videos Using Deep Learning},
journal = {Ophthalmology Science},
year = {2024},
volume = {4},
number = {2},
pages = {100380},
doi = {10.1016/j.xops.2023.100380}
}
EUVIMED