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

Electromagnetic Imaging of Anisotropic Objects Using a Self-Attention Perceptual Generative Adversarial Network.

Sensors (Basel, Switzerland)·2026
Same author

Wideband monopole MIMO antenna with pattern diversity and wide beamwidth coverage in elevation plane for C-band applications.

Scientific reports·2026
Same author

Design of a textile-based UHF RFID sensor for high read range and multilevel diaper moisture sensing.

Scientific reports·2025
Same author

Radio propagation modeling and measurement of uneven terrain model.

Scientific reports·2025
Same author

Transverse Electric Inverse Scattering of Conductors Using Artificial Intelligence.

Sensors (Basel, Switzerland)·2025
Same author

Convolutional Neural Network-Based Electromagnetic Imaging of Uniaxial Objects in a Half-Space.

Sensors (Basel, Switzerland)·2025

Related Experiment Video

Updated: May 25, 2025

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

2.6K

Electromagnetic Imaging in Half-Space Using U-Net with the Iterative Modified Contrast Scheme.

Chien-Ching Chiu1, Ching-Lieh Li1, Po-Hsiang Chen1

  • 1Department of Electrical and Computer and Engineering, Tamkang University, New Taipei City 251301, Taiwan.

Sensors (Basel, Switzerland)
|February 26, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a U-Net deep learning model combined with an iterative modified contrast scheme (IMCS) to improve inverse scattering problems (ISPs). The novel approach enhances image accuracy and noise immunity for better subsurface structure reconstruction.

Keywords:
U-Netinverse scattering problemiterative modified contrast schemestructural similarity

More Related Videos

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

264
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.4K

Related Experiment Videos

Last Updated: May 25, 2025

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

2.6K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

264
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.4K

Area of Science:

  • Geophysics
  • Electrical Engineering
  • Computer Science

Background:

  • Inverse scattering problems (ISPs) are crucial for subsurface imaging but face challenges with accuracy and noise.
  • Traditional iterative modified contrast scheme (IMCS) methods require significant iterations for acceptable results.
  • Deep learning offers potential for enhancing image reconstruction in geophysical and engineering applications.

Purpose of the Study:

  • To develop an improved method for solving inverse scattering problems in a half-space.
  • To enhance the accuracy and noise resilience of subsurface structure reconstruction.
  • To leverage deep learning (U-Net) to optimize the iterative modified contrast scheme (IMCS).

Main Methods:

  • Implementation of a U-Net deep learning architecture integrated with the iterative modified contrast scheme (IMCS).
  • Utilizing contrast functions within IMCS to improve target visibility and internal structure reconstruction.
  • Comparative analysis of U-Net with 3-iteration IMCS against traditional 200-iteration IMCS.

Main Results:

  • The U-Net with 3-iteration IMCS significantly improves the accuracy of reconstructed images compared to 200-iteration IMCS.
  • The proposed method demonstrates enhanced detection of contrast boundaries and improved structural similarity (SSI).
  • Robust performance is maintained even under conditions of significant Gaussian noise, ensuring reliable reconstruction.

Conclusions:

  • Combining U-Net deep learning with IMCS offers a powerful and efficient solution for inverse scattering problems.
  • The U-Net-IMCS approach provides superior accuracy, noise immunity, and structural similarity in subsurface imaging.
  • This method represents a significant advancement for applications requiring high-fidelity reconstruction from scattering data.