Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Enhancing the fine-scale prediction of pine wilt disease through the integration of a multihead attention mechanism.

Pest management science·2026
Same author

Epithelial MLCK deficiency alleviates alcohol-associated liver disease via dendritic-Th17 cell axis.

JHEP reports : innovation in hepatology·2026
Same author

Targeting Endogenous Lipophagy: A Novel Strategy to Enhance MSC Osteogenesis and Mineralization for Senile Osteoporosis Therapy.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

A comparison of microvascular flow imaging and contrast-enhanced ultrasound for the assessment of early chronic kidney disease.

Clinical hemorheology and microcirculation·2026
Same author

Integrated transcriptomic and proteomic analyses reveal immune activation and suppressed oxidative phosphorylation modules in chronic neck injection-site lesions of finishing pigs.

Research in veterinary science·2026
Same author

Ultrasensitive and Rapid Detection of Pesticide Residues in Vegetables by Aptamer-Functionalized Carbon Nanotube Field-Effect Transistor Biosensors.

Journal of agricultural and food chemistry·2026

Related Experiment Video

Updated: Mar 6, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

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

Published on: April 21, 2023

2.4K

Differentiation of Benign and Malignant Cervical Lymph Nodes Using a Multi-Modal Ultrasound-Based Machine Learning

Mingru Gao1, Yuping Guo1, Xiao Tian2

  • 1Department of Ultrasound, The Fourth Affiliated Hospital of Harbin Medical University, Harbin, China.

Journal of Ultrasound in Medicine : Official Journal of the American Institute of Ultrasound in Medicine
|March 5, 2026
PubMed
Summary
This summary is machine-generated.

A machine learning (ML) model using multi-modal ultrasound effectively differentiates benign from malignant cervical lymph nodes. Shapley additive explanations (SHAP) offer visual interpretations, supporting clinical decision-making.

Keywords:
SHAPbenign and malignantlymph nodesmachine learningmulti‐modal ultrasound

More Related Videos

High-frequency Ultrasound Imaging of Mouse Cervical Lymph Nodes
10:02

High-frequency Ultrasound Imaging of Mouse Cervical Lymph Nodes

Published on: July 25, 2015

19.8K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

835

Related Experiment Videos

Last Updated: Mar 6, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

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

Published on: April 21, 2023

2.4K
High-frequency Ultrasound Imaging of Mouse Cervical Lymph Nodes
10:02

High-frequency Ultrasound Imaging of Mouse Cervical Lymph Nodes

Published on: July 25, 2015

19.8K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

835

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Cervical lymph node assessment is crucial for cancer staging and treatment.
  • Distinguishing benign from malignant lymph nodes can be challenging with conventional imaging.
  • Multi-modal ultrasound offers comprehensive data for improved diagnostic accuracy.

Purpose of the Study:

  • To evaluate a machine learning (ML) model using multi-modal ultrasound features for differentiating benign from malignant cervical lymph nodes.
  • To assess the diagnostic performance of the ML model compared to experienced physicians.
  • To provide visual explanations for the ML model's predictions using SHAP.

Main Methods:

  • Retrospective study of 190 patients with cervical lymph node lesions.
  • Utilized 2D ultrasound, color Doppler flow imaging (CDFI), microvascular flow imaging (MVFI), and contrast-enhanced ultrasound (CEUS).
  • Developed and compared 10 ML algorithms, with performance evaluated using AUC, accuracy, sensitivity, specificity, and F1 score. SHAP was used for interpretation.

Main Results:

  • The Gradient Boosting Machine (GBM) model achieved the highest diagnostic performance (AUC=0.987).
  • The GBM model significantly outperformed an experienced ultrasound physician (AUC=0.904).
  • SHAP analysis identified CEUS enhancement pattern, L/S ratio, age, PI, and VI as key predictive features.

Conclusions:

  • The GBM model accurately differentiates benign from malignant cervical lymph nodes using multi-modal ultrasound.
  • SHAP provides transparent, visual interpretations of model decisions.
  • This approach integrates multi-modal data with explainable AI, offering a reliable tool for clinical decision-making.