EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Clinical Applications of Artificial Intelligence in Corneal Diseases

Omar Nusair iD, Hassan Asadigandomani iD, Hossein Farrokhpour, Fatemeh Moosaie, Zahra Bibak-Bejandi, Alireza Razavi iD, Kimia Daneshvar, Mohammad Soleimani iD

Vision · 18.08.2025 · 9 (3) · 71

DOI: 10.3390/vision9030071 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Vision, online erschienen am 18.08.2025. Verfasst von Omar Nusair und 7 weiteren Autor:innen. Beteiligte Einrichtung: Kittner Eye Center, Department of Ophthalmology, University of North Carolina, Chapel Hill, NC 27517, USA. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 262 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We evaluated the clinical applications of artificial intelligence models in diagnosing corneal diseases, highlighting their performance metrics and clinical potential. A systematic search was conducted for several disease categories: keratoconus (KC), Fuch’s endothelial corneal dystrophy (FECD), infectious keratitis (IK), corneal neuropathy, dry eye disease (DED), and conjunctival diseases. Metrics such as sensitivity, specificity, accuracy, and area under the curve (AUC) were extracted. Across the diseases, convolutional neural networks and other deep learning models frequently achieved or exceeded established diagnostic benchmarks (AUC > 0.90; sensitivity/specificity > 0.85–0.90), with a particularly strong performance for KC and FECD when trained on consistent imaging modalities such as anterior segment optical coherence tomography (AS-OCT). Models for IK and conjunctival diseases showed promise but faced challenges in heterogeneous image quality and limited objective training criteria. DED and tear film models benefited from multimodal data yet lacked direct comparisons with expert clinicians. Despite high diagnostic precision, challenges from heterogeneous data, a lack of standardization in disease definitions, imaging acquisition, and model training remain. The broad implementation of artificial intelligence must address these limitations to improve eye care equity.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligenceconjunctivacorneal diseasescorneal neuropathydeep learningdry eye diseaseinfectious keratitiskeratoconusmachine learningtear film

Autor:innen und Institutionen

  • Kittner Eye Center, Department of Ophthalmology, University of North Carolina, Chapel Hill, NC 27517, USA.
  • Department of Ophthalmology, University of California, San Francisco, CA 94143, USA.
  • Translational Ophthalmology Research Center, Farabi Eye Hospital, Tehran University of Medical Sciences, Tehran 1336616351, Iran.
  • Universal Scientific Education and Research Network (USERN), Tehran University of Medical Sciences, Tehran 1416634793, Iran.
  • Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, IL 60612, USA.
  • Eye Research Center, Farabi Eye Hospital, Tehran University of Medical Sciences, Tehran 1336616351, Iran.

ORCID-Profile: Omar Nusair, Hassan Asadigandomani, Alireza Razavi, Mohammad Soleimani

Zitieren

APA

Nusair, O., Asadigandomani, H., Farrokhpour, H., Moosaie, F., Bibak-Bejandi, Z., Razavi, A., Daneshvar, K., & Soleimani, M. (2025). Clinical Applications of Artificial Intelligence in Corneal Diseases. Vision, 9(3), 71. https://doi.org/10.3390/vision9030071

Vancouver

Nusair O, Asadigandomani H, Farrokhpour H, Moosaie F, Bibak-Bejandi Z, Razavi A, et al. Clinical Applications of Artificial Intelligence in Corneal Diseases. Vision. 2025;9(3):71. doi:10.3390/vision9030071

BibTeX
@article{Nusair2025,
  author = {Nusair, Omar and Asadigandomani, Hassan and Farrokhpour, Hossein and Moosaie, Fatemeh and Bibak-Bejandi, Zahra and Razavi, Alireza and Daneshvar, Kimia and Soleimani, Mohammad},
  title = {Clinical Applications of Artificial Intelligence in Corneal Diseases},
  journal = {Vision},
  year = {2025},
  volume = {9},
  number = {3},
  pages = {71},
  doi = {10.3390/vision9030071}
}
Kostenlos starten →