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

Recent advances in spore-killing technologies: A comprehensive review on killing effect, mechanism and application in food matrices.

Food microbiology·2026
Same author

FERPIR promotes cardiomyocyte survival and attenuates cardiac remodeling after myocardial infarction.

Cell death & disease·2026
Same author

A Modified Neonatal Mouse Cardiac Apicoectomy Model: Reproducibility and High Survival Rates.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026
Same author

Towards transparent and interpretable screening: multi-biofluid FTIR spectroscopy with LLM-Augmented explainability for pancreatic cancer detection.

Methods (San Diego, Calif.)·2026
Same author

Multifunctional starch-based composite film with methylcellulose and tannic acid for extending shelf life of fresh-cut pears.

International journal of biological macromolecules·2026
Same author

Multi-omics prediction of key proteases regulating scar formation and neural repair after spinal cord injury.

Neural regeneration research·2026

Related Experiment Video

Updated: Oct 3, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K

Deep learning inversion with supervision: A rapid and cascaded imaging technique.

Junkai Tong1, Min Lin2, Xiaocen Wang1

  • 1State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, 92 Weijin Road, Tianjin 300072, China.

Ultrasonics
|February 15, 2022
PubMed
Summary

Deep learning inversion with supervision (DLIS) offers a novel solution for inverse problems, significantly reducing training data needs for corrosion mapping in guided wave tomography. This method achieves reliable, high-accuracy thickness maps, even for complex defects.

Keywords:
Deep learning inversionMachine learningQuantitative imagingUltrasonic imaging

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Stereotaxic Viral Injection and Gradient-Index Lens Implantation for Deep Brain In Vivo Calcium Imaging
11:11

Stereotaxic Viral Injection and Gradient-Index Lens Implantation for Deep Brain In Vivo Calcium Imaging

Published on: October 8, 2021

6.2K

Related Experiment Videos

Last Updated: Oct 3, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Stereotaxic Viral Injection and Gradient-Index Lens Implantation for Deep Brain In Vivo Calcium Imaging
11:11

Stereotaxic Viral Injection and Gradient-Index Lens Implantation for Deep Brain In Vivo Calcium Imaging

Published on: October 8, 2021

6.2K

Area of Science:

  • Engineering
  • Computer Science
  • Materials Science

Background:

  • Machine learning shows promise for inverse problems.
  • Deep learning requires extensive training data for reliable results.
  • Corrosion mapping in guided wave tomography presents an inverse problem.

Purpose of the Study:

  • To introduce a novel deep learning inversion with supervision (DLIS) method.
  • To apply DLIS for corrosion mapping in guided wave tomography.
  • To evaluate DLIS performance against other deep learning algorithms.

Main Methods:

  • Developed and implemented the deep learning inversion with supervision (DLIS) algorithm.
  • Applied DLIS to corrosion mapping in plate-like structures using guided wave tomography.
  • Compared DLIS performance with existing deep learning methods using experimental data.

Main Results:

  • DLIS effectively reduces the required training dataset size compared to other deep learning algorithms.
  • The method significantly reduces nonlinearity between the global minimum and observed wave field.
  • Reconstruction accuracy for thickness maps using experimental data is high and reliable.
  • The DLIS method demonstrates potential for extension to 3D applications.

Conclusions:

  • DLIS is a promising approach for solving inverse problems, particularly in corrosion mapping.
  • The method offers improved efficiency in terms of training data requirements.
  • DLIS shows potential for applications in non-destructive evaluation, biomedical imaging, and geophysical prospecting.