EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting Visual Field Loss in Glaucoma Using OCT and Deep Learning: A Comparative Study of U-Net Variants

Kyoung Ohn, Jiwook Hwang, Jiwon Jung, Woong-Joo Whang

Ophthalmology Science · 2026-06 · 6 (6) · 101169

DOI: 10.1016/j.xops.2026.101169 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ophthalmology Science, 2026-06. Verfasst von Kyoung Ohn und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, Yeouido St. Mary's Eye Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Glaucoma is a chronic eye disease that progressively damages the optic nerve, leading to irreversible visual field (VF) loss. OCT and VF tests are essential for monitoring structural and functional changes in glaucoma. This study applies 3 deep learning models-R2 U-Net, Dense U-Net, and Nested U-Net (UNet++)-to predict VF outcomes using retinal nerve fiber layer (RNFL) thickness maps from OCT images.

Design

A retrospective cross-sectional study. Subjects: A total of 1640 patients with glaucoma diagnosed at a tertiary referral center were included. Only 1 eye (left eye) per patient was analyzed to avoid intereye correlation. Eyes included patients with early, moderate, and advanced glaucoma.

Methods

We used a dataset of OCT and VF data from 1640 glaucoma patients, divided into training, validation, and test sets. The 3 deep learning models were trained and evaluated using 5 performance metrics: mean squared error (MSE), mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and Fréchet inception distance (FID). The goal was to predict VF outcomes based on OCT-derived RNFL thickness maps. Main Outcome Measures: Accuracy and image quality of predicted VF maps compared with ground truth VF maps, assessed by MSE, MAE, PSNR, SSIM, and FID.

Results

R2 U-Net outperformed all other architectures, with the lowest MSE and MAE values and the highest SSIM and PSNR scores, indicating superior accuracy and image quality. Nested U-Net and Dense U-Net lagged, with Dense U-Net showing the lowest predictive accuracy.

Conclusions

This study is the first to apply generative artificial intelligence (AI) models, such as R2 U-Net, to predict VF loss based on OCT data, with both models demonstrating exceptional performance. These findings highlight the potential of generative AI to enhance glaucoma diagnosis and facilitate personalized treatment planning. Financial Disclosures: The authors have no proprietary or commercial interest in any materials discussed in this article.

Schlagwörter

Stichwörter der Autor:innen

Deep learningGenerative modelsGlaucomaOCTVisual field prediction

Autor:innen und Institutionen

  • Department of Ophthalmology, Yeouido St. Mary's Eye Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
  • PuzzleAI Co., Ltd., Seoul, Republic of Korea.

Zitieren

APA

Ohn, K., Hwang, J., Jung, J., & Whang, W. J. (2026). Predicting Visual Field Loss in Glaucoma Using OCT and Deep Learning: A Comparative Study of U-Net Variants. Ophthalmology Science, 6(6), 101169. https://doi.org/10.1016/j.xops.2026.101169

Vancouver

Ohn K, Hwang J, Jung J, Whang WJ. Predicting Visual Field Loss in Glaucoma Using OCT and Deep Learning: A Comparative Study of U-Net Variants. Ophthalmology Science. 2026;6(6):101169. doi:10.1016/j.xops.2026.101169

BibTeX
@article{Ohn2026,
  author = {Ohn, Kyoung and Hwang, Jiwook and Jung, Jiwon and Whang, Woong-Joo},
  title = {Predicting Visual Field Loss in Glaucoma Using OCT and Deep Learning: A Comparative Study of U-Net Variants},
  journal = {Ophthalmology Science},
  year = {2026},
  volume = {6},
  number = {6},
  pages = {101169},
  doi = {10.1016/j.xops.2026.101169}
}
Kostenlos starten →