EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Deep Learning Approaches to Predict Geographic Atrophy Progression Using Three-Dimensional OCT Imaging

Kenta Yoshida, Neha Anegondi, Adam Pely, Miao Zhang, Frederic Debraine, Karthik Ramesh, Verena Steffen, Simon S Gao, Catherine Cukras, Christina Rabe, Daniela Ferrara, Richard F Spaide und 3 weitere

Translational Vision Science & Technology · 2025

DOI: 10.1167/tvst.14.2.11 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Translational Vision Science & Technology, 2025. Verfasst von Kenta Yoshida und 14 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Pharmacology, Genentech, Inc., South San Francisco, CA, USA. Hauptthemen laut MEDLINE: Deep Learning, Geographic Atrophy, Imaging, Three-Dimensional, Tomography, Optical Coherence. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To evaluate the performance of various approaches of processing three-dimensional (3D) optical coherence tomography (OCT) images for deep learning models in predicting area and future growth rate of geographic atrophy (GA) lesions caused by age-related macular degeneration (AMD).

Methods

The study used OCT volumes of GA patients/eyes from the lampalizumab clinical trials (NCT02247479, NCT02247531, NCT02479386); 1219 and 442 study eyes for model development and holdout performance evaluation, respectively. Four approaches were evaluated: (1) en-face intensity maps; (2) SLIVER-net; (3) a 3D convolutional neural network (CNN); and (4) en-face layer thickness and between-layer intensity maps from a segmentation model. The processed OCT images and maps served as input for CNN models to predict baseline GA lesion area size and annualized growth rate.

Results

For the holdout dataset, the Pearson correlation coefficient squared (r2) in the GA growth rate prediction was comparable for all the evaluated approaches (0.33∼0.35). In baseline lesion size prediction, prediction performance was comparable (0.9∼0.91) except for the SLIVER-net (0.83). Prediction performance with only the thickness map of the ellipsoid zone (EZ) or retinal pigment epithelium (RPE) layer individually was inferior to using both. Addition of other layer thickness or intensity maps did not improve the prediction performance.

Conclusions

All explored approaches had comparable performance, which might have reached a plateau to predict GA growth rate. EZ and RPE layers appear to contain the majority of information related to the prediction. Translational Relevance: Our study provides important insights on the utility of 3D OCT images for GA disease progression predictions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGeographic AtrophyImaging, Three-DimensionalTomography, Optical CoherenceAgedFemaleHumansMaleDisease ProgressionMacular DegenerationNeural Networks, ComputerClinical Trials as Topic

Autor:innen und Institutionen

  • Clinical Pharmacology, Genentech, Inc., South San Francisco, CA, USA.
  • Clinical Imaging Group, Genentech, Inc., South San Francisco, CA, USA.
  • gRED Computational Science, Genentech, Inc., South San Francisco, CA, USA.
  • Product Development Ophthalmology, Genentech, Inc., South San Francisco, CA, USA.
  • Product Development Data Science, Genentech, Inc., South San Francisco, CA, USA.
  • Department of Ophthalmology, Roche Pharma Research and Early Development, F. Hoffmann-La Roche Ltd, Basel, Switzerland.

Zitieren

APA

Yoshida, K., Anegondi, N., Pely, A., Zhang, M., Debraine, F., Ramesh, K., Steffen, V., Gao, S. S., Cukras, C., Rabe, C., Ferrara, D., Spaide, R. F., Sadda, S. R., Holz, F. G., & Yang, Q. (2025). Deep Learning Approaches to Predict Geographic Atrophy Progression Using Three-Dimensional OCT Imaging. Translational Vision Science & Technology. https://doi.org/10.1167/tvst.14.2.11

Vancouver

Yoshida K, Anegondi N, Pely A, Zhang M, Debraine F, Ramesh K, et al. Deep Learning Approaches to Predict Geographic Atrophy Progression Using Three-Dimensional OCT Imaging. Translational Vision Science & Technology. 2025. doi:10.1167/tvst.14.2.11

BibTeX
@article{Yoshida2025,
  author = {Yoshida, Kenta and Anegondi, Neha and Pely, Adam and Zhang, Miao and Debraine, Frederic and Ramesh, Karthik and Steffen, Verena and Gao, Simon S and Cukras, Catherine and Rabe, Christina and Ferrara, Daniela and Spaide, Richard F and Sadda, SriniVas R and Holz, Frank G and Yang, Qi},
  title = {Deep Learning Approaches to Predict Geographic Atrophy Progression Using Three-Dimensional OCT Imaging},
  journal = {Translational Vision Science & Technology},
  year = {2025},
  doi = {10.1167/tvst.14.2.11}
}
Kostenlos starten →