Hybrid transformer-CNN network-driven optical-scanning undersampling for photoacoustic remote sensing microscopy
Photoacoustics · 2025-04 · 42 · 100697
DOI: 10.1016/j.pacs.2025.100697 ↗Kurz gefasst
Fachartikel in der Zeitschrift Photoacoustics, 2025-04. Verfasst von Yihan Pi und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin 300072, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Science Fund for Distinguished Young Scholars of Tianjin Municipality, National Natural Science Foundation of China, Chinese Academy of Sciences The Wang Lab.
Abstract (Originalsprache)
Imaging speed is critical for photoacoustic microscopy as it affects the capability to capture dynamic biological processes and support real-time clinical applications. Conventional approaches for increasing imaging speed typically involve high-repetition-rate lasers, which pose a risk of thermal damage to samples. Here, we propose a deep-learning-driven optical-scanning undersampling method for photoacoustic remote sensing (PARS) microscopy, accelerating imaging acquisition while maintaining a constant laser repetition rate and reducing laser dosage. We develop a hybrid Transformer-Convolutional Neural Network, HTC-GAN, to address the challenges of both nonuniform sampling and motion misalignment inherent in optical-scanning undersampling. A mouse ear vasculature image dataset is created through our customized galvanometer-scanned PARS system to train and validate HTC-GAN. The network successfully restores high-quality images from 1/2-undersampled and 1/4-undersampled data, closely approximating the ground truth images. A series of performance experiments demonstrate that HTC-GAN surpasses the basic misalignment compensation algorithm, and standalone CNN or Transformer networks in terms of perceptual quality and quantitative metrics. Moreover, three-dimensional imaging results validate the robustness and versatility of the proposed optical-scanning undersampling imaging method across multiscale scanning modes. Our method achieves a fourfold improvement in PARS imaging speed without hardware upgrades, offering an available solution for enhancing imaging speed in other optical-scanning microscopic systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin 300072, China.
- Center for Terahertz Waves, Tianjin University, Tianjin 300072, China.
- Infectious Diseases Department, Second Affiliated Hospital of Tianjin University of Traditional Chinese Medicine, Tianjin, China.
- State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin 300072, China.
- Georgia Tech Shenzhen Institute (GTSI), Tianjin University, Shenzhen 518067, China.
Förderung
- Science Fund for Distinguished Young Scholars of Tianjin Municipality
- National Natural Science Foundation of China
- Chinese Academy of Sciences The Wang Lab
Zitieren
APA
Pi, Y., Chen, J., Ding, K., Zhang, T., Zhang, H., Zhang, B., Guo, J., Tian, Z., & Li, J. (2025). Hybrid transformer-CNN network-driven optical-scanning undersampling for photoacoustic remote sensing microscopy. Photoacoustics, 42, 100697. https://doi.org/10.1016/j.pacs.2025.100697
Vancouver
Pi Y, Chen J, Ding K, Zhang T, Zhang H, Zhang B, et al. Hybrid transformer-CNN network-driven optical-scanning undersampling for photoacoustic remote sensing microscopy. Photoacoustics. 2025;42:100697. doi:10.1016/j.pacs.2025.100697
BibTeX
@article{Pi2025,
author = {Pi, Yihan and Chen, Jijing and Ding, Kaixuan and Zhang, Tongyan and Zhang, Hao and Zhang, Bingxue and Guo, Junhao and Tian, Zhen and Li, Jiao},
title = {Hybrid transformer-CNN network-driven optical-scanning undersampling for photoacoustic remote sensing microscopy},
journal = {Photoacoustics},
year = {2025},
volume = {42},
pages = {100697},
doi = {10.1016/j.pacs.2025.100697}
}
EUVIMED