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

Precision prebiotics: Engineering food-derived polysaccharides to target specific SCFA-producing taxa for neuroprotection via the microbiota-gut-brain axis.

Current research in food science·2026

Same author

A Multi-Task Segmentation and Classification Network Based on Ultrasound Images for Predicting the Grading of Ascites in the Abdominal Cavity.

Ultrasonic imaging·2026

Same author

Targeting the Myocardial Microenvironment: Novel Antiviral Strategies and Therapeutic Perspectives for Coxsackievirus B-Induced Myocarditis.

Journal of the American Heart Association·2026

Same author

Developing High Performance N-Oxygenase for Azomycin Synthesis through Ancestral Sequence Reconstruction.

ACS synthetic biology·2026

Same author

Application of single-cell transcriptomic technology in cell fate determination of embryonic liver.

Histology and histopathology·2026

Same author

High-fidelity three-dimensional reconstruction of musculoskeletal tissues via diffusion based ultrasonic computed tomography.

Medical image analysis·2026

Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026

Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026

Same journal

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026

Same journal

Relative spectral and frication-based descriptors as numerical indicators of place of articulation shifts in fricatives produced by Polish children.

Computer methods and programs in biomedicine·2026

Same journal

Leaflet resection improves valve expansion and hemodynamic performance in redo TAVI with balloon- and self-expanding transcatheter heart valve configurations.

Computer methods and programs in biomedicine·2026

Same journal

Spectral super-resolution for Parkinson's voice via representation-level methods under mixed-reality acquisition.

Computer methods and programs in biomedicine·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 20, 2025

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population

Published on: January 31, 2025

A multi-task neural network for full waveform ultrasonic bone imaging.

Peiwen Li¹, Tianyu Liu², Heyu Ma²

¹Department of Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai 200438, China.

Computer Methods and Programs in Biomedicine

|May 1, 2025

Summary

This summary is machine-generated.

This study introduces CEDD-Unet, a novel deep learning approach for high-resolution bone imaging using ultrasound. CEDD-Unet significantly improves speed-of-sound (SOS) reconstruction accuracy and reduces artifacts compared to existing methods.

Keywords:

Bone imaging Deep learning Full waveform inversion (FWI)Multitask learning Ultrasound imaging

More Related Videos

Non-invasive Parenchymal, Vascular and Metabolic High-frequency Ultrasound and Photoacoustic Rat Deep Brain Imaging

Non-invasive Parenchymal, Vascular and Metabolic High-frequency Ultrasound and Photoacoustic Rat Deep Brain Imaging

Published on: March 2, 2015

Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments

Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments

Published on: June 28, 2024

Related Experiment Videos

Last Updated: May 20, 2025

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population

Published on: January 31, 2025

Non-invasive Parenchymal, Vascular and Metabolic High-frequency Ultrasound and Photoacoustic Rat Deep Brain Imaging

Non-invasive Parenchymal, Vascular and Metabolic High-frequency Ultrasound and Photoacoustic Rat Deep Brain Imaging

Published on: March 2, 2015

Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments

Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments

Published on: June 28, 2024

Area of Science:

Biomedical Engineering
Medical Imaging
Artificial Intelligence

Background:

Ultrasound bone imaging is challenging due to bone's complex structure and acoustic properties.
Traditional full waveform inversion (FWI) for bone imaging produces artifacts and requires high computational resources.

Purpose of the Study:

To develop a deep learning-based FWI approach for high-resolution ultrasonic bone imaging.
To overcome limitations of traditional FWI in bone imaging, such as local minima trapping and computational burden.

Main Methods:

Proposed a novel Convolutional LSTM (ConvLSTM) and Efficient Multi-scale Attention (EMA) enhanced Dual-Decoder U-Net (CEDD-Unet).
CEDD-Unet reconstructs the speed-of-sound (SOS) model and identifies bone-soft tissue boundaries.
Utilized ultrasound radio frequency (RF) signals for multi-scale feature extraction.

Main Results:

CEDD-Unet outperformed existing methods in accuracy (lower MAE) and image quality (higher SSIM, PSNR) on human and mouse bone datasets.
Achieved clearer bone boundaries, reduced artifacts, and improved consistency with ground truth.
Demonstrated reduced computational cost and eliminated the need for an initial model compared to traditional FWI.

Conclusions:

CEDD-Unet shows significant promise for high-resolution bone imaging using ultrasound.
The method can reconstruct accurate, sharp-edged skeletal SOS models.
This deep learning approach offers a potential advancement in musculoskeletal ultrasound imaging.