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

AI-Enabled Mapping of Structure-Hazard Relationships for Emerging Contaminants.

Environment & health (Washington, D.C.)·2026
Same author

Predicting the progression of proliferative diabetic retinopathy: Pathophysiology, imaging phenotypes, and determinants of disease persistence despite therapy.

Survey of ophthalmology·2026
Same author

Pictilisib and nutrient stress synergize to induce methuosis via PI(4,5)P<sub>2</sub>-dependent macropinocytic dysregulation in cancer cells.

Cell death & disease·2026
Same author

Importance of Frailty Assessment, Liver Screening, and Interdisciplinary Coordination in Prevention of Chronic Liver Disease.

Geriatrics & gerontology international·2026
Same author

Digital adiabatic evolution is universally accurate.

Nature communications·2026
Same author

Exponential Lindbladian fast forwarding and exponential amplification of certain Gibbs state properties.

Reports on progress in physics. Physical Society (Great Britain)·2026

Related Experiment Video

Updated: Jan 1, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Automatic Identification of Breast Ultrasound Image Based on Supervised Block-Based Region Segmentation Algorithm and

Wen-Xuan Liao, Ping He, Jin Hao

    IEEE Journal of Biomedical and Health Informatics
    |December 24, 2019
    PubMed
    Summary

    This study uses deep learning and breast ultrasound images for accurate breast cancer diagnosis. The combined model achieved a 92.95% recognition rate, aiding early detection and improving patient outcomes.

    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

    2.2K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    707

    Related Experiment Videos

    Last Updated: Jan 1, 2026

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.3K
    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

    2.2K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    707

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Oncology

    Background:

    • Breast cancer is a leading cause of cancer death in women.
    • Early diagnosis significantly improves treatment success and survival rates.
    • Ultrasound imaging is a key tool for breast tumor assessment.

    Purpose of the Study:

    • To develop and evaluate a deep learning model for classifying breast tumors as benign or malignant using ultrasound images.
    • To assess the effectiveness of combining B-mode ultrasound and strain elastography features for improved diagnostic accuracy.
    • To validate the performance of an automated segmentation algorithm against manual segmentation.

    Main Methods:

    • Tumor regions were segmented from breast ultrasound (BUS) images using a supervised block-based region segmentation algorithm.
    • A VGG-19 deep learning network, pre-trained on ImageNet, was employed for tumor classification.
    • A combined feature model integrated depth features from B-mode ultrasound and strain elastography data.

    Main Results:

    • The automated segmentation algorithm demonstrated accuracy comparable to manual segmentation.
    • The combined feature model achieved a correct recognition rate of 92.95%.
    • The area under the curve (AUC) for the combined model reached 0.98, indicating high diagnostic performance.

    Conclusions:

    • Deep learning combined with ultrasound imaging offers a promising approach for accurate breast tumor diagnosis.
    • Automated segmentation can effectively replace manual segmentation in clinical workflows.
    • Integrating B-mode ultrasound and strain elastography features enhances diagnostic accuracy for breast cancer detection.