Feasibility study of deep-learning-based models for automated macular hole segmentation using optical coherence tomography B-scans
Applied Optics · 2025
DOI: 10.1364/ao.553308 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Optics, 2025. Verfasst von Shuyu Chen und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Deep Learning, Retinal Perforations, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Natural Science Foundation of Beijing Municipality, National Natural Science Foundation of China, Beijing Institute of Technology.
Abstract (Originalsprache)
We aim to evaluate the feasibility of deep-learning (DL)-based models for automated macular hole (MH) segmentation using optical coherence tomography (OCT) B-scans. Four DL-based OCT B-scan segmentation models with different architectures, including ResNet-50 or EfficientNet backbones, feature pyramid network (FPN) or weighted bi-directional FPN (BiFPN) necks, and FPN head, namely Model 1 (ResNet-50, FPN, FPN), Model 2 (ResNet-50, BiFPN, FPN), Model 3 (EfficientNet, FPN, FPN), and Model 4 (EfficientNet, BiFPN, FPN), were developed, followed by their implementations on 3295 paired OCT B-scans and labels belonging to MH and non-MH. The mean intersection over union (IOU) values (0.969, 0.968, 0.975, and 0.977 for Models 1–4) indicate the best performance of Model 4. The percentage proportion of OCT B-scans with IOU values between 0.8 and 1 reached 94.33%, 95.32%, 100%, and 100% for MH, choroid, retina, and intraretinal cysts (IRCs), respectively, demonstrating the potential of the four DL-based models developed for automated MH segmentation from OCT B-scans.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Natural Science Foundation of Beijing Municipality
- National Natural Science Foundation of China
- Beijing Institute of Technology
- The Humboldt Research Fellowship for Experienced Researchers
Zitieren
APA
Chen, S., E, S., Sun, H., Jin, E., & Wang, J. (2025). Feasibility study of deep-learning-based models for automated macular hole segmentation using optical coherence tomography B-scans. Applied Optics. https://doi.org/10.1364/ao.553308
Vancouver
Chen S, E S, Sun H, Jin E, Wang J. Feasibility study of deep-learning-based models for automated macular hole segmentation using optical coherence tomography B-scans. Applied Optics. 2025. doi:10.1364/ao.553308
BibTeX
@article{Chen2025,
author = {Chen, Shuyu and E, Shenchao and Sun, Hui and Jin, Enzhong and Wang, Jianfeng},
title = {Feasibility study of deep-learning-based models for automated macular hole segmentation using optical coherence tomography B-scans},
journal = {Applied Optics},
year = {2025},
doi = {10.1364/ao.553308}
}
EUVIMED