EUVIMEDEUVIMED entdecken
Crossref

Robust detection of retinal neovascularization in widefield optical coherence tomography

Jinyi Hao, Jie Wang, Liqin Gao, Tristan T. Hormel, Yukun Guo, An-Lun Wu, Christina J. Flaxel, Steven T. Bailey, Kotaro Tsuboi, Thomas S. Hwang, Yali Jia

Optica · 20.04.2026 · 13 (4) · 628

DOI: 10.1364/optica.584955 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optica, online erschienen am 30.03.2026. Verfasst von Jinyi Hao und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Institutes of Health, Research to Prevent Blindness, Jennie P. Weeks Endowed Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retinal neovascularization (RNV) is a vision threatening development in diabetic retinopathy (DR). Vision loss associated with RNV is preventable with timely intervention, making RNV clinical screening and monitoring a priority. Optical coherence tomography (OCT) angiography (OCTA) provides high-resolution imaging and high-sensitivity detection of RNV lesions. With recent commercial devices introducing widefield OCTA imaging to the clinic, the technology stands to improve early detection of RNV pathology. However, to meet clinical requirements, these imaging capabilities must be combined with effective RNV detection and quantification, but existing algorithms for OCTA images are optimized for conventional, i.e., narrow, fields of view. Here, we present a novel, to our knowledge, approach for RNV diagnosis and staging on widefield OCT/OCTA. Unlike conventional methods dependent on multi-layer retinal segmentation, our model reframes RNV identification as a direct binary localization task. Our fully automated approach was trained and validated on 634 widefield scans (17×17 to 26×21mm) collected from multiple devices at multiple clinics. Our method achieved a device-dependent area under curve (AUC) ranging from 0.96 to 0.99 for RNV diagnosis, and mean intersection over union (IOU) ranging from 0.76 to 0.88 for segmentation. We also demonstrate our method’s ability to monitor lesion growth longitudinally. Our results indicate that deep learning-based analysis for widefield OCTA images could offer a valuable means for improving RNV screening and management.

Förderung

  • National Institutes of Health
  • Research to Prevent Blindness
  • Jennie P. Weeks Endowed Fund
  • Malcolm M. Marquis, MD Endowed Fund for Innovation
  • Edward N. & Della L. Thome Memorial Foundation
  • Bright Focus Foundation

Zitieren

APA

Hao, J., Wang, J., Gao, L., Hormel, T. T., Guo, Y., Wu, A., Flaxel, C. J., Bailey, S. T., Tsuboi, K., Hwang, T. S., & Jia, Y. (2026). Robust detection of retinal neovascularization in widefield optical coherence tomography. Optica, 13(4), 628. https://doi.org/10.1364/optica.584955

Vancouver

Hao J, Wang J, Gao L, Hormel TT, Guo Y, Wu A, et al. Robust detection of retinal neovascularization in widefield optical coherence tomography. Optica. 2026;13(4):628. doi:10.1364/optica.584955

BibTeX
@article{Hao2026,
  author = {Hao, Jinyi and Wang, Jie and Gao, Liqin and Hormel, Tristan T. and Guo, Yukun and Wu, An-Lun and Flaxel, Christina J. and Bailey, Steven T. and Tsuboi, Kotaro and Hwang, Thomas S. and Jia, Yali},
  title = {Robust detection of retinal neovascularization in widefield optical coherence tomography},
  journal = {Optica},
  year = {2026},
  volume = {13},
  number = {4},
  pages = {628},
  doi = {10.1364/optica.584955}
}
Kostenlos starten →