Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 3, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.3K

Robust denoising of low-fluence single-shot PAM using spatial attention-enhanced deep learning.

Zhituo Tu, Yuchen Sun, Tianxiang Zuo

    Optics Letters
    |May 1, 2026
    PubMed
    Summary

    This study introduces a novel denoising framework using a spatial attention-enhanced 3D U-Net to improve photoacoustic microscopy (PAM) imaging. The method significantly boosts signal-to-noise ratio (SNR) for clearer microvasculature visualization in demanding applications.

    Related Concept Videos

    Deconvolution01:20

    Deconvolution

    764
    Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
    Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
    764

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Biological factors contributing to divergent cortical abnormalities in adolescent and adult psychiatric disorders.

    Translational psychiatry·2026
    Same author

    Drug-Induced Noninfectious Myocarditis/Pericarditis: A Real-World Pharmacovigilance Study Using the FAERS Database.

    Cardiovascular toxicology·2026
    Same author

    Mesoporous polydopamine-based biomimetic nanodelivery systems: recent advances in precision therapy.

    International journal of pharmaceutics·2026
    Same author

    An HSP90-inhibitory thermosensitive hydrogel enhances photothermal therapy against triple-negative breast cancer.

    Colloids and surfaces. B, Biointerfaces·2026
    Same author

    An Epithelial-Mesenchymal Transition-Based Prognostic Model for Survival Prediction in Lung Adenocarcinoma: COL5A2 and ZEB2.

    Current gene therapy·2026
    Same author

    Autofocusing optical-resolution photoacoustic microscopy.

    Ultrasonics·2026

    Area of Science:

    • Biomedical Optics
    • Medical Imaging
    • Machine Learning in Medicine

    Background:

    • Photoacoustic microscopy (PAM) offers label-free imaging of microvasculature.
    • Time-resolved PAM applications face challenges with low signal-to-noise ratio (SNR) due to limited laser energy and acquisition noise.
    • High-speed volumetric scanning and in vivo microcirculation monitoring require enhanced image quality.

    Purpose of the Study:

    • To develop a volumetric denoising framework for improving PAM image quality.
    • To enhance the SNR and fidelity of PAM imaging, especially in low-fluence or rapid acquisition scenarios.
    • To leverage deep learning and transfer learning for robust vascular feature extraction.

    Main Methods:

    • A spatial attention-enhanced 3D U-Net architecture was developed for volumetric denoising.

    Related Experiment Videos

    Last Updated: May 3, 2026

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    1.3K
  • A 3D patch-based learning approach incorporated spatial attention mechanisms to exploit volumetric correlations.
  • Transfer learning was employed, pre-training on leaf vein phantoms and fine-tuning on in vivo mouse ear vasculature data.

    • Main Results:

    • The proposed framework significantly improved peak signal-to-noise ratio (PSNR) from 18.93 dB to 29.76 dB.
    • Structural similarity index (SSIM) improved from 0.3943 to 0.9008, indicating enhanced image fidelity.
    • An overall SNR enhancement exceeding 13 dB was achieved compared to single-shot images.

    Conclusions:

    • The spatial attention-enhanced 3D U-Net effectively denoises PAM data by distinguishing vascular features from noise.
    • The transfer learning strategy successfully addressed data scarcity, enabling effective model training.
    • This approach facilitates high-fidelity PAM imaging for challenging time-resolved and high-speed volumetric applications.