EUVIMEDEUVIMED entdecken
Crossref

Zero-Shot Enhancement With Cross-Modal Applicability for Low-Light Vis-$\mu$OCT Images

Shujiang Chen, Yanshuo Li, Hua Wei, Fuwang Wu, Weiye Song

IEEE Transactions on Biomedical Engineering · 2026-03 · 73 (3) · 1072-1079

DOI: 10.1109/tbme.2025.3597643 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2026-03. Verfasst von Shujiang Chen und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Image Processing, Computer-Assisted, Image Enhancement. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, Shandong ProvinceOutstanding Youth Science Fund Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: Optical coherence tomography (OCT) is a rapid and non-destructive imaging technique, but image brightness decreases when imaging deep tissues or under low power and short exposure due to insufficient backscattered light. This issue is more pronounced in visible-light micro-OCT (vis-$\mu$OCT), where shorter wavelengths increase scattering and limit penetration, restricting its application. METHOD: In this paper, we propose Dif-NIR, a novel framework for enhancing low-light OCT images. The framework begins with a preliminary denoising stage. Image enhancement is then performed using a neural implicit representation (NIR) network, in which pixel values are incorporated as auxiliary input to mitigate the oversmoothing effect of fully connected layers. To enable unsupervised learning, custom-designed loss functions is employed. The proposed method is validated through qualitative and quantitative comparisons on a self-collected en face image dataset. To further assess its generalizability, we also performed experiments on B-scan images and retinal images acquired from other OCT devices. RESULT: On the en face image dataset, Dif-NIR outperforms existing methods in terms of visual quality, SNR (58.99 dB), CNR (49.56 dB), and NIQE (9.0553). It also effectively generalizes to OCT B-scan images and retinal images acquired by other devices. CONCLUSION: The proposed network effectively mitigates unpredictable brightness degradation, producing clearer and better-illuminated images while exhibiting strong generalization capability. SIGNIFICANCE: The network effectively reveals deep-layer information in OCT images and can be applied to expand its usage scenarios to cost-effective and high-speed imaging settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Optical CoherenceImage Processing, Computer-AssistedImage EnhancementHumansRetinaFaceAlgorithmsNeural Networks, ComputerDatabases, Factual

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province
  • Shandong ProvinceOutstanding Youth Science Fund Project
  • Taishan Scholar Foundation of Shandong Province
  • Key Technology Research and Development Program of Shandong Province

Zitieren

APA

Chen, S., Li, Y., Wei, H., Wu, F., & Song, W. (2026). Zero-Shot Enhancement With Cross-Modal Applicability for Low-Light Vis-$\mu$OCT Images. IEEE Transactions on Biomedical Engineering, 73(3), 1072-1079. https://doi.org/10.1109/tbme.2025.3597643

Vancouver

Chen S, Li Y, Wei H, Wu F, Song W. Zero-Shot Enhancement With Cross-Modal Applicability for Low-Light Vis-$\mu$OCT Images. IEEE Transactions on Biomedical Engineering. 2026;73(3):1072-1079. doi:10.1109/tbme.2025.3597643

BibTeX
@article{Chen2026,
  author = {Chen, Shujiang and Li, Yanshuo and Wei, Hua and Wu, Fuwang and Song, Weiye},
  title = {Zero-Shot Enhancement With Cross-Modal Applicability for Low-Light Vis-$\mu$OCT Images},
  journal = {IEEE Transactions on Biomedical Engineering},
  year = {2026},
  volume = {73},
  number = {3},
  pages = {1072--1079},
  doi = {10.1109/tbme.2025.3597643}
}
Kostenlos starten →