Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

[Advances in the clinical management of acute severe ulcerative colitis].

Zhejiang da xue xue bao. Yi xue ban = Journal of Zhejiang University. Medical sciences·2026

Same author

Exploration of Copper Halide Linear-Array Detector Prototype for Security Checks.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Machine Learning in Microwave Medical Imaging and Lesion Detection.

Diagnostics (Basel, Switzerland)·2025

Same author

Ultra-Broad Emission Copper Halide Scintillator-Based X-Ray Imager.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2024

Same author

Multi-Time-Scale Optimal Scheduling Strategy for Marine Renewable Energy Based on Deep Reinforcement Learning Algorithm.

Entropy (Basel, Switzerland)·2024

Same author

Capillary Manganese Halide Needle-Like Array Scintillator with Isolated Light Crosstalk for Micro-X-Ray Imaging.

Advanced materials (Deerfield Beach, Fla.)·2024

Same journal

Improved Microwave Imaging with the Extended Born Iterative Method.

IEEE transactions on antennas and propagation·2026

Same journal

Enhanced Gain Extrapolation Technique: A Third-Order Scattering Approach For High-Accuracy Antenna Gain, Sparse Sampling, At Fresnel Distances.

IEEE transactions on antennas and propagation·2025

Same journal

A Free-Space Measurement Method for the Low-Loss Dielectric Characterization Without Prior Need for Sample Thickness Data.

IEEE transactions on antennas and propagation·2024

Same journal

Novel Numerical Basis Sets for Electromagnetic Field Expansion in Arbitrary Inhomogeneous Objects.

IEEE transactions on antennas and propagation·2023

Same journal

Dielectric Breast Phantoms by Generative Adversarial Network.

IEEE transactions on antennas and propagation·2023

Same journal

Millimeter-wave Channel-Sounder Performance Verification using Vector Network Analyzer in a Controlled RF Channel.

IEEE transactions on antennas and propagation·2022

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 2, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Microwave Imaging by Deep Learning Network: Feasibility and Training Method.

Wenyi Shao¹, Yong Du¹

¹Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, MD 21287 USA.

IEEE Transactions on Antennas and Propagation

|June 11, 2021

Summary

This summary is machine-generated.

This study introduces a novel deep learning method for microwave imaging, simplifying complex image reconstruction. The two-stage neural network approach effectively converts microwave signals into high-resolution images, improving reconstruction accuracy.

Keywords:

Autoencoder convolutional neural net deep learning microwave imaging scattered fields

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

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

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Nov 2, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

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

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

Published on: November 30, 2022

Area of Science:

Electromagnetics
Computational Imaging
Machine Learning

Background:

Microwave imaging requires complex signal processing for accurate reconstruction.
Deep learning offers potential for improving inverse problems in imaging.
Traditional methods like DBIM and PCM have limitations in speed and accuracy.

Purpose of the Study:

To investigate a deep-learning-based method for microwave image reconstruction.
To develop a two-stage neural network for mapping microwave signals to high-resolution images.
To reduce the training difficulty of deep learning networks for inverse reconstruction tasks.

Main Methods:

A 24x24 antenna array at 4 GHz was used to acquire microwave signals.
An autoencoder was developed to compress high-resolution images (128x128) into low-dimensional vectors (256x1).
A second neural network mapped microwave signals to these compressed features, forming a full reconstruction network.

Main Results:

The developed deep learning network successfully reconstructed 128x128 images from microwave signals.
The two-stage training method demonstrated reduced training difficulty for deep learning networks (DLN).
Validation using simulation and experimental data showed robust performance across various object configurations and dielectric properties (2-6).

Conclusions:

The proposed deep learning method offers an effective approach for microwave image reconstruction.
The two-stage training strategy simplifies the development of DLN for inverse problems.
The method shows promise compared to conventional techniques like DBIM and PCM.