Search research articles

Related Concept Videos

Ultrasonography

Ultrasonography

Ultrasonography is an imaging technique that uses high-frequency sound waves to visualize the body's internal structures. It is a non-invasive and safe procedure that does not involve the use of ionizing radiation, making it widely used in various medical fields. Ultrasonography is used to study heart function, blood flow in the neck or extremities, certain conditions such as gallbladder disease, and fetal growth and development.
During an ultrasonography procedure, a handheld device called...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Automated pneumatic tourniquet for hemorrhage control evaluated using an adaptive testing platform.

Frontiers in medical technology·2026

Same author

Deep Learning-Based Tracking of Neurovascular Features Toward Semi-Automated Ultrasound-Guided Peripheral Nerve Blocks by Non-Specialists.

Bioengineering (Basel, Switzerland)·2026

Same author

Comparison of Controller Logics for Automating Vasopressor Administration Using a Hardware-in-Loop Test Platform.

Bioengineering (Basel, Switzerland)·2026

Same author

Validation of a Wearable Photoplethysmography-Based Sensor for Compensatory Reserve Measurement Monitoring in Simulated Human Hemorrhage.

Sensors (Basel, Switzerland)·2026

Same author

Breaking the Black Box: Interpretable AI Achieves Superior Hemorrhage Detection with the Compensatory Reserve Measurement.

IEEE journal of biomedical and health informatics·2026

Same author

Experimental evaluation of a real-time implementation of compensatory reserve measurement in a human model of hemorrhagic shock.

Frontiers in bioengineering and biotechnology·2026

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

Search research articles

Related Experiment Video

Updated: Sep 22, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

An image classification deep-learning algorithm for shrapnel detection from ultrasound images.

Eric J Snider¹, Sofia I Hernandez-Torres², Emily N Boice²

¹Engineering Technology and Automation Combat Casualty Care Research Team, United States Army Institute of Surgical Research, Ft. Sam Houston, TX, USA. eric.j.snider3.civ@mail.mil.

Scientific Reports

|May 19, 2022

Summary

Artificial intelligence, specifically a convolutional neural network, accurately detects shrapnel in ultrasound images. This AI tool enhances trauma diagnosis where expert interpretation is limited.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Sep 22, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Ultrasound imaging is crucial for non-invasive injury diagnosis, especially when advanced tools are unavailable.
Interpreting ultrasound images requires expertise, which may be lacking in resource-limited or emergency settings.
Artificial intelligence (AI) offers potential solutions for automating ultrasound image analysis and diagnosis.

Purpose of the Study:

To develop and evaluate an AI-powered convolutional neural network (CNN) for detecting shrapnel in ultrasound images.
To assess the algorithm's performance on both tissue phantoms and animal tissue models.
To establish a framework for AI-driven trauma imaging analysis.

Main Methods:

An image classification CNN was designed to detect shrapnel in ultrasound images.
The algorithm was trained and validated using ultrasound images of shrapnel embedded in tissue-mimicking phantoms and swine thigh tissue.
Algorithm architecture was optimized by minimizing validation loss and maximizing the F1 score.

Main Results:

The CNN achieved an F1 score of 0.95 and an area under the ROC curve of 0.95 when trained on tissue phantom data.
The algorithm demonstrated over 90% accuracy for 8 different shrapnel types in phantom studies.
When trained on swine tissue data, the algorithm achieved even higher performance metrics, with F1 and area under the ROC curve of 0.99.

Conclusions:

The developed AI algorithm exhibits high accuracy in classifying shrapnel in ultrasound images across both phantom and animal tissue models.
This AI framework shows promise for improving trauma diagnosis in resource-scarce environments by automating image interpretation.
The approach can be extended to other critical trauma applications, such as detecting internal bleeding, to enhance emergency medical care.