EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detection of Structural Glaucoma Progression with Deep Learning on Serial Optic Disc Photographs

Vahid Mohammadzadeh, Tyler Davis, Esteban Morales, Diana Salazar Vega, Daniela Khaliliyeh, Maral Namdari, Zhe Fei, Fabien Scalzo, Kouros Nouri-Mahdavi, Joseph Caprioli

Ophthalmology Glaucoma · 2026-09 · 9 (5) · 565-574

DOI: 10.1016/j.ogla.2026.03.005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ophthalmology Glaucoma, 2026-09. Verfasst von Vahid Mohammadzadeh und 9 weiteren Autor:innen. Beteiligte Einrichtung: Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California. Hauptthemen laut MEDLINE: Optic Disk, Deep Learning, Glaucoma, Photography. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research to Prevent Blindness.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To design a supervised deep learning (DL) model to detect glaucoma progression with serial optic disc photographs (DPs). DESIGN: A retrospective longitudinal cohort study. PARTICIPANTS: One thousand five hundred ten eyes (916 patients) with ≥2 years of follow-up and 2 pairs of DPs per eye were included. METHODS: Longitudinal series of DPs were labeled as having evidence of progression or stable by 2 ophthalmologists, and discrepancies were adjudicated by 2 glaucoma specialists. An automated cropping was applied centered on the optic disc to reduce less relevant information. The dataset was split into training and testing/validation sets with an 80/10/10 ratio. A twin convolutional neural network was designed to assess baseline and final DPs to detect glaucoma progression. MAIN OUTCOME MEASURES: Area under receiver operating characteristic curves (AUCs) for detection of glaucoma progression; sensitivity and specificity for automated classification compared to clinical classification as ground truth. RESULTS: Baseline visual field mean deviation (±standard deviation) was -4.0 (±5.6) dB. Twenty-two percent of eyes deteriorated based on the clinical review of DPs. The final DL model's AUC (95% confidence interval) for detection of glaucoma progression was 0.821 (0.764-0.887) with an overall accuracy for classification of 72% (66%-88%) with a sensitivity and specificity of 87% (60%-95%) and 68% (61%-93%), respectively. CONCLUSIONS: Our twin convolutional neural network model is able to detect glaucoma progression with clinically relevant accuracy. Deep learning is promising as an adjunctive method for clinical decision-making for detection of structural glaucoma progression. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Optic DiskDeep LearningGlaucomaPhotographyIntraocular PressureVisual FieldsHumansDisease ProgressionRetrospective StudiesFemaleMaleROC CurveMiddle AgedConvolutional Neural NetworksFollow-Up StudiesAged

Stichwörter der Autor:innen

Deep learningGlaucomaOptic disc photographsProgression

Autor:innen und Institutionen

  • Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California.
  • Department of Computer Science, University of California Los Angeles, Los Angeles, California.
  • Department of Ophthalmology, John Moran Eye Center, University of Utah, Salt Lake City, Utah.
  • Department of Statistics, University of California Riverside, Riverside, California.
  • Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California. Electronic address: caprioli@jsei.ucla.edu.

Förderung

  • Research to Prevent Blindness

Zitieren

APA

Mohammadzadeh, V., Davis, T., Morales, E., Vega, D. S., Khaliliyeh, D., Namdari, M., Fei, Z., Scalzo, F., Nouri-Mahdavi, K., & Caprioli, J. (2026). Detection of Structural Glaucoma Progression with Deep Learning on Serial Optic Disc Photographs. Ophthalmology Glaucoma, 9(5), 565-574. https://doi.org/10.1016/j.ogla.2026.03.005

Vancouver

Mohammadzadeh V, Davis T, Morales E, Vega DS, Khaliliyeh D, Namdari M, et al. Detection of Structural Glaucoma Progression with Deep Learning on Serial Optic Disc Photographs. Ophthalmology Glaucoma. 2026;9(5):565-574. doi:10.1016/j.ogla.2026.03.005

BibTeX
@article{Mohammadzadeh2026,
  author = {Mohammadzadeh, Vahid and Davis, Tyler and Morales, Esteban and Vega, Diana Salazar and Khaliliyeh, Daniela and Namdari, Maral and Fei, Zhe and Scalzo, Fabien and Nouri-Mahdavi, Kouros and Caprioli, Joseph},
  title = {Detection of Structural Glaucoma Progression with Deep Learning on Serial Optic Disc Photographs},
  journal = {Ophthalmology Glaucoma},
  year = {2026},
  volume = {9},
  number = {5},
  pages = {565--574},
  doi = {10.1016/j.ogla.2026.03.005}
}
Kostenlos starten →