Bayesian-neural-network-based strain estimation approach for optical coherence elastography
Optica · 20.09.2024 · 11 (9) · 1334
DOI: 10.1364/optica.534933 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optica, online erschienen am 18.09.2024. Verfasst von Yulei Bai und 6 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: Natural Science Foundation of Guangdong Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Strain estimation is critical for quantitative elastography in quasi-static phase-sensitive optical coherence elastography (PhS-OCE). Deep-learning methods have achieved exceptional performance in estimating high-quality strain distributions. However, they cannot often assess their predictive accuracy and reliability rigorously. To navigate these challenges, a Bayesian-neural-network (BNN)-based strain estimation is proposed. The method can provide the uncertainty distribution of the results beyond achieving high-quality strain estimation. Such an uncertainty distribution can assess the reliability of the strain results. Moreover, the uncertainty degree can function as an indicator for compensating for phase decorrelation and thus significantly enhancing the SNR and dynamic range of PhS-OCE. Thermal and three-point bending deformation experiments validated that the predicted uncertainty distribution can effectively address phase decorrelation and allow for a more comprehensive understanding of the estimated strain results.
Förderung
- Natural Science Foundation of Guangdong Province
- National Natural Science Foundation of China
Zitieren
APA
Bai, Y., Zhang, K., Mo, R., Ni, Z., He, Z., Xie, S., & Dong, B. (2024). Bayesian-neural-network-based strain estimation approach for optical coherence elastography. Optica, 11(9), 1334. https://doi.org/10.1364/optica.534933
Vancouver
Bai Y, Zhang K, Mo R, Ni Z, He Z, Xie S, et al. Bayesian-neural-network-based strain estimation approach for optical coherence elastography. Optica. 2024;11(9):1334. doi:10.1364/optica.534933
BibTeX
@article{Bai2024,
author = {Bai, Yulei and Zhang, Kangyang and Mo, Rui and Ni, Zihao and He, Zhaoshui and Xie, Shengli and Dong, Bo},
title = {Bayesian-neural-network-based strain estimation approach for optical coherence elastography},
journal = {Optica},
year = {2024},
volume = {11},
number = {9},
pages = {1334},
doi = {10.1364/optica.534933}
}
EUVIMED