EUVIMEDEUVIMED entdecken
Open Access

Retinal layer segmentation in OCT images with a 2.5D cross-slice feature fusion module for glaucoma assessment

Hyunwoo Kim, Heesuk Kim, Chaewon Lee, Wungrak Choi, Jae-Sang Hyun iD

Biomedical Optics Express · 01.07.2026 · 17 (7) · 3576

DOI: 10.1364/boe.599609 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Optics Express, online erschienen am 11.06.2026. Verfasst von Hyunwoo Kim und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, Yonsei University, Seoul, 03722, Republic of Korea. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Research Foundation of Korea, Yonsei University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For accurate glaucoma diagnosis and monitoring, reliable retinal layer segmentation in OCT images is essential. However, existing 2D segmentation methods often suffer from slice-to-slice inconsistencies due to the lack of contextual information across adjacent B-scans. 3D segmentation methods are better for capturing slice-to-slice context, but they require expensive computational resources. To address these limitations, we propose a 2.5D segmentation framework that incorporates a novel cross-slice feature fusion (CFF) module into a U-Net-like architecture. The CFF module fuses inter-slice features to effectively capture contextual information, enabling consistent boundary detection across slices and improved robustness in noisy regions. The framework was validated on both a clinical dataset and the publicly available DUKE DME dataset. Compared to other segmentation methods without the CFF module, the proposed method achieved an 8.56% reduction in mean absolute distance and a 13.92% reduction in root mean square error, demonstrating improved segmentation accuracy and robustness. Overall, the proposed 2.5D framework balances contextual awareness and computational efficiency, enabling anatomically reliable retinal layer delineation for automated glaucoma evaluation and potential clinical applications.

Autor:innen und Institutionen

  • Department of Mechanical Engineering, Yonsei University, Seoul, 03722, Republic of Korea.
  • Institute of Vision Research, Department of Ophthalmology, Yonsei University College of Medicine, Seoul, 03722, Republic of Korea.
  • Yonsei University College of Medicine, Seoul, 03722, Republic of Korea.
  • wungrakchoi@yuhs.ac.
  • hyun.jaesang@yonsei.ac.kr.

ORCID-Profile: Jae-Sang Hyun

Förderung

  • National Research Foundation of Korea
  • Yonsei University

Zitieren

APA

Kim, H., Kim, H., Lee, C., Choi, W., & Hyun, J. S. (2026). Retinal layer segmentation in OCT images with a 2.5D cross-slice feature fusion module for glaucoma assessment. Biomedical Optics Express, 17(7), 3576. https://doi.org/10.1364/boe.599609

Vancouver

Kim H, Kim H, Lee C, Choi W, Hyun JS. Retinal layer segmentation in OCT images with a 2.5D cross-slice feature fusion module for glaucoma assessment. Biomedical Optics Express. 2026;17(7):3576. doi:10.1364/boe.599609

BibTeX
@article{Kim2026,
  author = {Kim, Hyunwoo and Kim, Heesuk and Lee, Chaewon and Choi, Wungrak and Hyun, Jae-Sang},
  title = {Retinal layer segmentation in OCT images with a 2.5D cross-slice feature fusion module for glaucoma assessment},
  journal = {Biomedical Optics Express},
  year = {2026},
  volume = {17},
  number = {7},
  pages = {3576},
  doi = {10.1364/boe.599609}
}
Kostenlos starten →