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

Ultrasound II: Endoscopic Ultrasound and FibroScan

Ultrasound II: Endoscopic Ultrasound and FibroScan

Endoscopic Ultrasound (EUS) and FibroScan are valuable diagnostic tools in gastroenterology and hepatology, each with specific applications and techniques.
Endoscopic Ultrasound (EUS):

Imaging Studies II: Ultrasonography

Imaging Studies II: Ultrasonography

IntroductionUltrasonography, or renal ultrasound, is a noninvasive medical imaging technique that uses high-frequency sound waves to visualize the kidneys, ureters, bladder, and surrounding tissues.Indications for Urinary System UltrasonographyUrinary system ultrasonography is indicated in various clinical scenarios, such as:Kidney Stones (Urolithiasis): To detect and monitor the size and presence of kidney or urinary tract stones.Hydronephrosis: To assess the dilation of the renal pelvis and...

Ultrasound I: Abdominal Ultrasonography

Ultrasound I: Abdominal Ultrasonography

Introduction:
Abdominal ultrasonography, commonly known as abdominal ultrasound, is a vital, non-invasive medical imaging technique widely used in healthcare.
Procedure:
This diagnostic tool allows the clinician to visually inspect internal structures within the abdomen, including vital organs such as the liver, gallbladder, pancreas, kidneys, and spleen.
The abdominal ultrasound process begins with applying a special gel to the patient's skin over the abdomen. This gel enhances the...

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

Evaluation of the Toxicity and Efficacy of an Adeno-Associated Viral Vector Expressing <i>BEST1</i> Delivered by Subretinal Injection in a Canine Model of Human Bestrophinopathy.

Human gene therapy·2026

Same author

The critical role of the endogenous immune compartment after CAR T cell therapy in recurrent GBM.

Cell·2026

Same author

Ultrasound Radiomics in Pediatric Imaging: Current Applications, Challenges, and Future Directions Toward Clinical Implementation.

Diagnostics (Basel, Switzerland)·2026

Same author

Fostering cell-cell interactions and integrating angiocrine factors to promote the development of salivary microtissues in 3D.

Bioengineering & translational medicine·2026

Same author

Automated Detection of Pediatric Pneumonia via Clinically Driven AI Analysis of Lung Ultrasound.

Ultrasound quarterly·2026

Same author

HLA-E single-chain trimer shields gene-edited allogeneic CAR T cells from NK cell attack.

Blood advances·2026

Same journal

Rodent Social Behavior Recognition Using a Global Context-Aware Vision Transformer Network.

AI (Basel, Switzerland)·2026

Same journal

Artificial Intelligence at the Intersection of Chemistry and Materials Science.

AI (Basel, Switzerland)·2026

Same journal

Monitoring Substance Use with Fitbit Biosignals: A Case Study on Training Deep Learning Models Using Ecological Momentary Assessments and Passive Sensing.

AI (Basel, Switzerland)·2025

Same journal

Audio-Based Emotion Recognition Using Self-Supervised Learning on an Engineered Feature Space.

AI (Basel, Switzerland)·2024

Same journal

Can Artificial Intelligence Aid Diagnosis by Teleguided Point-of-Care Ultrasound? A Pilot Study for Evaluating a Novel Computer Algorithm for COVID-19 Diagnosis Using Lung Ultrasound.

AI (Basel, Switzerland)·2023

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 27, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting

Laith R Sultan¹, Theodore W Cary², Maryam Al-Hasani¹

¹Ultrasound Research Laboratory, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.

AI (Basel, Switzerland)

|September 28, 2022

Summary

This summary is machine-generated.

Machine learning in medical imaging requires independent data. This study found normal liver ultrasound images were independent, but diseased liver images were not, highlighting the need for independence testing before using sequential data for training.

Keywords:

independent data liver disease machine learning medical imaging quantitative ultrasound

More Related Videos

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Published on: July 21, 2023

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

Related Experiment Videos

Last Updated: Aug 27, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Published on: July 21, 2023

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

Area of Science:

Medical imaging
Machine learning
Data science

Background:

Machine learning (ML) models for medical imaging require independent datasets for reliable training and testing.
Sequential imaging data, common in time-series medical imaging, often exhibits inherent correlations, leading to data interdependence.
Data leakage and poor generalizability can occur if interdependent data is used without proper validation.

Purpose of the Study:

To evaluate statistical measures for testing the independence of sequential ultrasound image data from the same patient.
To assess the impact of data independence on machine learning model performance for liver disease diagnosis.
To provide recommendations for ensuring data generalizability and preventing data leakage in medical imaging ML.

Main Methods:

Analysis of 1180 B-mode liver ultrasound images (5903 regions of interest) from normal, fibrosis, and steatosis groups.
Extraction of computer-based texture features for training machine learning models (logistic regression and random forest).
Application of Jenson-Shannon (JS) divergence to evaluate the independence of image regions within the dataset.

Main Results:

High diagnostic performance achieved: AUC of 0.928 for two-category diagnosis (logistic regression) and AUC of 0.917 for multicategory classification (random forest).
JS divergence indicated independence among normal liver ultrasound images.
JS divergence revealed a lack of independence among ultrasound images from liver fibrosis and steatosis pathologies.

Conclusions:

Data independence is crucial for the generalizability of machine learning models in medical imaging.
Sequential ultrasound images from diseased livers (fibrosis, steatosis) exhibit interdependence, necessitating independence testing.
Statistical tests for independence should be applied to sequential medical image data from the same subject before ML model training to prevent data leakage.