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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Discovery and biological evaluation of HS13 as a novel covalent ligand targeting the NSD2-PWWP1 domain.

Bioorganic & medicinal chemistry·2026
Same author

Commentary: C6-7 Corpectomy for Clipping of Ruptured Anterior Radiculomedullary Artery Aneurysm.

Operative neurosurgery (Hagerstown, Md.)·2026
Same author

High-fidelity three-dimensional reconstruction of musculoskeletal tissues via diffusion based ultrasonic computed tomography.

Medical image analysis·2026
Same author

Therapeutic targets for diabetic nephropathy identified by druggable genome mendelian randomization: the role of the gut microbiota-metabolite axis.

Frontiers in endocrinology·2026
Same author

Identification of novel covalent ligands that disrupt Acetyl-Lysine binding to the SETDB1 tudor domain.

Biochemical and biophysical research communications·2026
Same author

Region-Adaptive Null Subtraction Imaging Using Generalized Coherence Factor for Coherent Plane Wave Compounding.

Ultrasonic imaging·2026

Related Experiment Video

Updated: Jun 21, 2025

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.0K

Reconstructing Cancellous Bone From Down-Sampled Optical-Resolution Photoacoustic Microscopy Images With Deep

Jingxian Wang1, Boyi Li2, Tianhua Zhou3

  • 1Human Phenome Institute, Fudan University, Shanghai, China.

Ultrasound in Medicine & Biology
|July 7, 2024
PubMed
Summary

Researchers developed a Photoacoustic Dense Attention U-Net (PADA U-Net) to enhance optical-resolution photoacoustic microscopy (OR-PAM) bone imaging. This AI model improves image quality without slowing down imaging speed, aiding early bone disease diagnosis.

Keywords:
BoneConvolutional neural networkDeep learningPhotoacoustic microscopyUnder-sampled

More Related Videos

Three-dimensional Optical-resolution Photoacoustic Microscopy
08:31

Three-dimensional Optical-resolution Photoacoustic Microscopy

Published on: May 3, 2011

18.2K
Analysis and Imaging of Osteocytes
10:19

Analysis and Imaging of Osteocytes

Published on: November 29, 2024

686

Related Experiment Videos

Last Updated: Jun 21, 2025

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.0K
Three-dimensional Optical-resolution Photoacoustic Microscopy
08:31

Three-dimensional Optical-resolution Photoacoustic Microscopy

Published on: May 3, 2011

18.2K
Analysis and Imaging of Osteocytes
10:19

Analysis and Imaging of Osteocytes

Published on: November 29, 2024

686

Area of Science:

  • Biomedical Imaging
  • Medical Technology
  • Artificial Intelligence in Medicine

Background:

  • Bone diseases significantly impact bone tissue microstructure.
  • Optical-resolution photoacoustic microscopy (OR-PAM) offers high spatial resolution for bone imaging.
  • A key limitation of OR-PAM is the spatiotemporal trade-off, hindering its clinical application.

Purpose of the Study:

  • To enhance OR-PAM image quality for bone tissue.
  • To overcome the spatiotemporal trade-off in OR-PAM.
  • To improve the early diagnosis and treatment of bone diseases.

Main Methods:

  • Proposed the Photoacoustic Dense Attention U-Net (PADA U-Net) model.
  • Utilized PADA U-Net for reconstructing full-scanning images from under-sampled OR-PAM data.
  • Validated the model on resolution test targets and bovine cancellous bone samples.

Main Results:

  • PADA U-Net successfully reconstructed full-scanning images from under-sampled OR-PAM data.
  • Achieved significant improvements in Peak Signal-to-Noise Ratio (2.325 dB) and Structural Similarity Index Measure (0.117) compared to bilinear interpolation at a [4, 1] down-sampling ratio.
  • Demonstrated effective image reconstruction across various sparsity levels.

Conclusions:

  • The PADA U-Net model robustly reconstructs OR-PAM images from sparse data.
  • This AI-driven approach addresses the speed-resolution trade-off in OR-PAM.
  • The method holds promise for advancing the early detection and management of bone pathologies.