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 Experiment Video

Updated: Jul 12, 2026

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

Ultrasonographic feature selection and pattern classification for cervical lymph nodes using support vector machines.

Junhua Zhang1, Yuanyuan Wang, Yi Dong

  • 1Electronic Engineering Department, Fudan University, Shanghai 200433, China.

Computer Methods and Programs in Biomedicine
|August 28, 2007
PubMed
Summary

A novel rough margin based support vector machine (RMSVM) classifier enhances ultrasound diagnosis accuracy for cervical lymph nodes. This computer-aided diagnosis algorithm shows potential to outperform radiologist performance.

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

Safety and efficacy of consolidative stereotactic radiotherapy for oligo-residual EGFR-mutant non-small cell lung cancer after first-line third-generation EGFR-tyrosine kinase inhibitors: a single-arm, phase 2 trial.

EClinicalMedicine·2024
Same author

Exposure to ambient polycyclic aromatic hydrocarbons and early-onset female breast cancer in a case-control study in Ontario, Canada.

Environmental epidemiology (Philadelphia, Pa.)·2024
Same author

Scatterer spacing based on Gabor atoms matched from harmonic ultrasound echoes to improve assessment of microwave-induced thermal lesions.

Medical physics·2024
Same author

Establishment of efficient system for bagasse bargaining: Combining fractionation of saccharides, recycling of high-viscosity solvent and dismantling.

Bioresource technology·2024
Same author

Postoperative Radiotherapy in Curatively Resected Esophageal Squamous Cell Carcinoma With Occult Recurrent Laryngeal Nerve Lymph Node Metastasis.

Cancer control : journal of the Moffitt Cancer Center·2024
Same author

5-Aminolevulinic acid photodynamic therapy is a safe and effective treatment for female patients with intractable vulvar lichen sclerosus.

Photodiagnosis and photodynamic therapy·2024

Area of Science:

  • Medical imaging analysis
  • Machine learning in diagnostics
  • Biomedical signal processing

Background:

  • Accurate diagnosis of cervical lymph nodes via ultrasound is crucial for patient management.
  • Traditional diagnostic methods can be subjective and prone to inter-observer variability.
  • Developing automated tools can aid clinicians in improving diagnostic accuracy.

Purpose of the Study:

  • To propose a novel Rough Margin based Support Vector Machine (RMSVM) classifier for improved ultrasound diagnosis of cervical lymph nodes.
  • To evaluate the performance of RMSVM against classical Support Vector Machine (SVM) and General Regression Neural Network (GRNN).
  • To assess the impact of feature selection using Recursive Feature Elimination (RFE) on classifier performance.

Main Methods:

More Related Videos

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

Ultrasonographic Evaluation of Breast Cancer-related Lymphedema
05:44

Ultrasonographic Evaluation of Breast Cancer-related Lymphedema

Published on: January 12, 2017

Related Experiment Videos

Last Updated: Jul 12, 2026

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

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

Ultrasonographic Evaluation of Breast Cancer-related Lymphedema
05:44

Ultrasonographic Evaluation of Breast Cancer-related Lymphedema

Published on: January 12, 2017

  • Extraction of 36 ultrasonographic features from 110 cervical lymph node images.
  • Implementation and comparison of three classifiers: classical SVM, GRNN, and RMSVM.
  • Application of Recursive Feature Elimination (RFE) for feature selection with SVM and RMSVM.
  • Performance evaluation using the normalized area under the receiver operating characteristic curve (A(z)).

    • Main Results:

    • All tested classifiers demonstrated improved performance with feature selection.
    • The RMSVM classifier, utilizing 13 features selected by RMSVM-based RFE, achieved the highest diagnostic performance.
    • The best RMSVM model yielded an A(z) of 0.859, surpassing the radiologist's performance of A(z) = 0.787.

    Conclusions:

    • Feature selection significantly benefits the diagnostic accuracy of machine learning classifiers for cervical lymph node ultrasound.
    • The proposed RMSVM classifier demonstrates superior performance compared to classical SVM and GRNN, with or without feature selection.
    • The developed computer-aided diagnosis algorithm holds significant potential for enhancing the accuracy of ultrasound-based cervical lymph node diagnoses.