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 Videos

3-D ultrasound texture classification using run difference matrix.

Wei-Ming Chen1, Ruey-Feng Chang, Shou-Jen Kuo

  • 1Department of Information Management, National Dong Hwa University, Hualien, Taiwan.

Ultrasound in Medicine & Biology
|June 7, 2005
PubMed
Summary

This study introduces a novel texture classification method for three-dimensional (3-D) ultrasound breast imaging. The new approach significantly improves the accuracy of diagnosing malignant versus benign breast tumors using 3-D run difference matrix and neural networks.

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

2025 Update of the Taiwan Expert Consensus on Hormone Receptor-Positive Metastatic Breast Cancer Management.

Journal of breast cancer·2026
Same author

Dual-Phase Computed Tomography-Based Deep Learning Architecture for Three-Year Survival Prediction in Hepatocellular Carcinoma.

Journal of imaging informatics in medicine·2026
Same author

Prognostic Factors and Biomarker Performance in Patients with Colorectal Cancer Receiving Reduced-Dose 5-Fluorouracil Therapy: A Retrospective Cohort Analysis.

Journal of clinical medicine·2026
Same author

Long-term oncologic outcomes of minimal access (endoscopic or Robotic Assisted) nipple-sparing mastectomy compared with conventional approach in breast cancer - a propensity score matching analysis.

International journal of surgery (London, England)·2025
Same author

Detection and tracking of a gauze sponge in minimally invasive surgery using a YOLO and R-CNN based model.

Medical & biological engineering & computing·2025
Same author

Predicting Radiotherapy Outcomes with Deep Learning Models Through Baseline and Adaptive Simulation Computed Tomography in Patients with Pharyngeal Cancer.

Cancers·2025

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Conventional two-dimensional (2-D) ultrasound limitations in simultaneously visualizing tumor surface features and internal architecture.
  • Diagnosis reliance on physician experience, impacting consistency.
  • Emergence of three-dimensional (3-D) ultrasound for enhanced anatomical visualization.

Purpose of the Study:

  • To develop and evaluate a novel texture classification approach for 3-D ultrasound breast image analysis.
  • To improve the diagnostic accuracy of distinguishing malignant from benign breast tumors.
  • To leverage the Run Difference Matrix (RDM) and neural networks for enhanced 3-D breast US diagnosis.

Main Methods:

  • Implementation of a texture classification method using the Run Difference Matrix (RDM) algorithm.

Related Experiment Videos

  • Integration of neural networks for analyzing 3-D ultrasound (US) breast image data.
  • Testing the proposed method on a database of 54 malignant and 161 benign breast tumors.

    • Main Results:

    • The proposed 3-D RDM method achieved an area index A(z) under the ROC curve of 0.9680.
    • Overall accuracy of the method was 91.9%, with sensitivity of 88.9% and specificity of 93.5%.
    • High positive predictive value (87.3%) and negative predictive value (94.3%) were reported.

    Conclusions:

    • The developed 3-D RDM texture classification method shows significant promise for improving the accuracy of breast tumor diagnosis using 3-D ultrasound.
    • This approach offers a more objective and comprehensive analysis compared to conventional 2-D methods.
    • The findings suggest potential for enhanced clinical decision-making in breast cancer screening and diagnosis.