Related Experiment Video
Updated: Dec 28, 2025
08:08
Evaluating Targeting Accuracy in the Focal Plane for an Ultrasound-guided High-intensity Focused Ultrasound Phased-array System
Published on: March 6, 2019
5.6K
A unified deep network for beamforming and speckle reduction in plane wave imaging: A simulation study
1Department of Non Destructive Testing, Soreq Nuclear Research Center, Yavne 81800, Israel; Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel.
Ultrasonics
|February 12, 2020
Summary
This study introduces a deep learning method to enhance ultrasound image quality. The novel approach integrates beamforming and speckle reduction, significantly improving resolution and contrast for faster, clearer ultrasound imaging.
Area of Science:
- Medical Imaging
- Ultrasound Technology
- Deep Learning Applications
Background:
- Plane Wave Imaging offers high frame rates but suffers from reduced image quality.
- Existing methods struggle to balance speed and clarity in ultrasound imaging.
Purpose of the Study:
- To develop a learning-based approach for improving ultrasound image quality.
- To integrate beamforming and speckle reduction into a single deep convolutional network.
Main Methods:
- A deep convolutional neural network was designed incorporating physical ultrasound image formation principles.
- The network includes trainable beamforming, envelope detection, and log-signal speckle reduction stages.
- The model was trained using simulated ultrasound data.
Main Results:
- The method achieved axial and lateral Full-Width-Half-Maximum (FWHM) resolutions of 0.22 mm and 0.35 mm respectively.
- A Contrast to Noise Ratio (CNR) of 16.75 was obtained on experimental datasets.
- The learning-based approach demonstrated superior image quality compared to traditional methods.
Conclusions:
- Deep learning effectively enhances ultrasound image quality in Plane Wave Imaging.
- Integrating beamforming and speckle reduction in a single network is a viable strategy.
- The proposed method offers a promising solution for high-quality, high-frame-rate ultrasound imaging.
