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: Jul 12, 2026

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

Spatially-informed deep learning for full-field ultrasonic nondestructive evaluation.

Cole N Maxwell1, Joshua R Tempelman2, Erica M Jacobson1

  • 1Engineering Institute, Los Alamos National Laboratory, Los Alamos, NM 87545, United States of America.

Ultrasonics
|July 9, 2026
PubMed
Summary

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

Ceralasertib Monotherapy in Patients with ATM-Altered Advanced Solid Tumors or Metastatic Castration-Resistant Prostate Cancer: Data from the Phase IIa PLANETTE Study.

Cancer research communications·2026
Same author

External Validation, Recalibration, and Extension of a Prediction Model of Early Acute Kidney Injury in Critically Ill Children Using Multicenter Data.

Critical care explorations·2026
Same author

Impaired Cerebral Autoregulation in Pediatric Patients with ECMO: A Retrospective Analysis of ECMO Time Periods and Association with Neurologic Injury.

Neurocritical care·2026
Same author

EHR Sampling Interval Bias Detection and Burden of Blood Pressure Excursions: Implications for Clinical Decision Support and Model Validity in Pediatric ECMO.

Information (Basel)·2026
Same author

Efficacy of the ATR Inhibitor Ceralasertib in Patients with ARID1A-Deficient Gynecologic and Other Solid Tumor Malignancies.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Continuous Hemodynamic Response to Angiotensin II in Critically Ill Pediatric Patients: A Single Center Cohort Study.

The journal of pediatric pharmacology and therapeutics : JPPT : the official journal of PPAG·2025

This study introduces a deep learning model for accurate material thickness estimation using ultrasonic waves. The novel approach improves reliability by considering spatial context and surface geometry, outperforming existing methods.

Area of Science:

  • Non-destructive testing
  • Ultrasonic material characterization
  • Deep learning applications

Background:

  • Current ultrasonic methods for material thickness estimation are unreliable due to geometric variations.
  • Existing techniques fail to account for response warping and scaling with scanning position.

Purpose of the Study:

  • To develop a robust deep learning model for accurate local material thickness estimation.
  • To overcome limitations of traditional methods by incorporating spatial context and geometric invariance.

Main Methods:

  • A deep learning model combining full-field quadrature components and range data via early fusion.
  • Utilizing deformable convolution layers for improved spatial invariance and local surface projection.
  • Developing a simulation pipeline for generating training data with varied thickness and orientation.
Keywords:
Acoustic steady-state excitation spatial spectroscopyDeep learningDeformable convolutionMachine learningSensor fusionUltrasonic nondestructive evaluation

Related Experiment Videos

Last Updated: Jul 12, 2026

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

Main Results:

  • The proposed model, integrating early fusion and deformable convolutions, significantly outperformed other configurations.
  • The deep learning approach demonstrated superior performance compared to a non-machine learning baseline on experimental data.
  • The model accurately estimated material thickness across diverse scanning positions, orientations, and distances.

Conclusions:

  • The developed deep learning approach offers a more reliable method for material thickness estimation in non-destructive testing.
  • Combining early fusion and deformable convolutions is key to improving accuracy and spatial invariance.
  • This technique shows promise for real-world applications in structural health monitoring and material inspection.