EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Anatomical Landmark Localization in Anterior Segment OCT Images Using an Efficient Deep Learning Framework

Liangqi Zheng, Yingping Deng, Zhiyong Huang, Jing Tang, Li Chen

Sensors · 06.08.2026 · 26 (15) · 4982

DOI: 10.3390/s26154982 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.08.2026. Verfasst von Liangqi Zheng und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Aeronautics and Astronautics, Sichuan University, Chengdu 610207, China. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Deep Learning, Anterior Eye Segment, Image Processing, Computer-Assisted. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Department of Sichuan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anterior segment optical coherence tomography (AS-OCT) is essential for structural assessment of the anterior eye, yet automated landmark localization remains challenged by pervasive speckle noise, indistinct tissue interfaces, and labor-intensive manual annotation with notable inter-observer variability. This study presents NSE YOLO, an enhanced YOLOv11 framework for high-precision landmark localization in AS-OCT images after implantable collamer lens (ICL) implantation. It integrates a dual-branch NewConv module for multi-scale feature extraction, a dual-additive residual self-attention block (SABlock) to suppress background interference, and a Mamba-based EfficientViMBlock embedded in the C3k2 module to balance global contextual modeling and computational efficiency. Validated on 672 expert-annotated postoperative ICL images from 60 patients, NSE YOLO achieved an mAP@0.5 of 90.7% and mAP@0.5:0.95 of 85.1%, outperforming the YOLOv11 baseline by 5.2% and 6.6% with only 2.86 million parameters. Bland–Altman analysis showed negligible systematic bias and narrow limits of agreement for anterior chamber depth. For iridocorneal angle measurements, directional deviations and wider limits of agreement were observed, with performance approaching the level of inter-observer variability among human annotators. NSE YOLO enables automated quantification of anterior chamber depth and bilateral iridocorneal angles for post-ICL follow-up assessment, providing preliminary technical validation supporting further external and device-level evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Optical CoherenceDeep LearningAnterior Eye SegmentImage Processing, Computer-AssistedAnatomic LandmarksHumansDetection AlgorithmsAlgorithms

Stichwörter der Autor:innen

YOLOv11 architectureattention mechanismlightweight networkoptical coherence tomography (OCT)pose-point estimation

Autor:innen und Institutionen

  • School of Aeronautics and Astronautics, Sichuan University, Chengdu 610207, China.
  • Ophthalmology Department of West China Hospital, Sichuan University, Chengdu 610041, China.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Department of Sichuan Province

Zitieren

APA

Zheng, L., Deng, Y., Huang, Z., Tang, J., & Chen, L. (2026). Automated Anatomical Landmark Localization in Anterior Segment OCT Images Using an Efficient Deep Learning Framework. Sensors, 26(15), 4982. https://doi.org/10.3390/s26154982

Vancouver

Zheng L, Deng Y, Huang Z, Tang J, Chen L. Automated Anatomical Landmark Localization in Anterior Segment OCT Images Using an Efficient Deep Learning Framework. Sensors. 2026;26(15):4982. doi:10.3390/s26154982

BibTeX
@article{Zheng2026,
  author = {Zheng, Liangqi and Deng, Yingping and Huang, Zhiyong and Tang, Jing and Chen, Li},
  title = {Automated Anatomical Landmark Localization in Anterior Segment OCT Images Using an Efficient Deep Learning Framework},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {15},
  pages = {4982},
  doi = {10.3390/s26154982}
}
Kostenlos starten →