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

Identifying Retinal Features Using a Self-Configuring CNN for Clinical Intervention

Daniel S Kermany, Wesley Poon, Anaya Bawiskar, Natasha Nehra, Orhun Davarci, Glori Das, Matthew Vasquez, Shlomit Schaal, Raksha Raghunathan, Stephen T C Wong

Investigative Ophthalmology & Visual Science · 2025

DOI: 10.1167/iovs.66.6.55 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Investigative Ophthalmology & Visual Science, 2025. Verfasst von Daniel S Kermany und 9 weiteren Autor:innen. Beteiligte Einrichtung: Translational Biophotonics Laboratory, Department of Systems Medicine and Bioengineering, Houston Methodist Neal Cancer Center, Houston, Texas, Unite…. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Retinal Diseases, Retina, Deep Learning. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NEI NIH HHS, NCI NIH HHS, NINDS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Retinal diseases are leading causes of blindness worldwide, necessitating accurate diagnosis and timely treatment. Optical coherence tomography (OCT) has become a universal imaging modality of the retina in the past 2 decades, aiding in the diagnosis of various retinal conditions. However, the scarcity of comprehensive, annotated OCT datasets, that are labor-intensive to assemble, has hindered the advancement of artificial intelligence (AI)-based diagnostic tools.

Methods

To address the lack of annotated OCT segmentation datasets, we introduce OCTAVE, an extensive 3D OCT dataset with high-quality, pixel-level annotations for anatomic and pathological structures. Additionally, we provide similar annotations for four independent public 3D OCT datasets, enabling their use as external validation sets. To demonstrate the potential of this resource, we train a deep learning segmentation model using the self-configuring no-new-U-Net (nnU-Net) framework and evaluate its performance across all four external validation sets.

Results

The OCTAVE dataset collected consists of 198 OCT volumes (3762 B-scans) used for training and 221 OCT volumes (4109 B-scans) for external validation. The trained deep learning model demonstrates clinically significant performance across all retinal structures and pathological features.

Conclusions

We demonstrate robust segmentation performance and generalizability across independently collected datasets. OCTAVE bridges the gap in publicly available datasets, supporting the development of AI tools for precise disease detection, monitoring, and treatment guidance. This resource has the potential to improve clinical outcomes and advance AI-driven retinal disease management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Optical CoherenceRetinal DiseasesRetinaDeep LearningNeural Networks, ComputerHumansImaging, Three-Dimensional

Autor:innen und Institutionen

  • Translational Biophotonics Laboratory, Department of Systems Medicine and Bioengineering, Houston Methodist Neal Cancer Center, Houston, Texas, United States.
  • T. T. & W. F. Chao Center for BRAIN, Department of Systems Medicine and Bioengineering, Houston Methodist Neal Cancer Center, Houston, Texas, United States.
  • Department of Biomedical Engineering, Texas A&M University, College Station, Texas, United States.
  • College of Medicine, Texas A&M Health Science Center, Bryan, Texas, United States.
  • School of Engineering Medicine, Texas A&M University, Houston, Texas, United States.
  • Department of Ophthalmology, Houston Methodist Academic Institute, Houston, Texas, United States.

Förderung

  • NEI NIH HHS
  • NCI NIH HHS
  • NINDS NIH HHS

Zitieren

APA

Kermany, D. S., Poon, W., Bawiskar, A., Nehra, N., Davarci, O., Das, G., Vasquez, M., Schaal, S., Raghunathan, R., & Wong, S. T. C. (2025). Identifying Retinal Features Using a Self-Configuring CNN for Clinical Intervention. Investigative Ophthalmology & Visual Science. https://doi.org/10.1167/iovs.66.6.55

Vancouver

Kermany DS, Poon W, Bawiskar A, Nehra N, Davarci O, Das G, et al. Identifying Retinal Features Using a Self-Configuring CNN for Clinical Intervention. Investigative Ophthalmology & Visual Science. 2025. doi:10.1167/iovs.66.6.55

BibTeX
@article{Kermany2025,
  author = {Kermany, Daniel S and Poon, Wesley and Bawiskar, Anaya and Nehra, Natasha and Davarci, Orhun and Das, Glori and Vasquez, Matthew and Schaal, Shlomit and Raghunathan, Raksha and Wong, Stephen T C},
  title = {Identifying Retinal Features Using a Self-Configuring CNN for Clinical Intervention},
  journal = {Investigative Ophthalmology & Visual Science},
  year = {2025},
  doi = {10.1167/iovs.66.6.55}
}
Kostenlos starten →