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: May 1, 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

2.6K

Syn-Net: A Synchronous Frequency-Perception Fusion Network for Breast Tumor Segmentation in Ultrasound Images.

Guangzhe Zhao, Xingguo Zhu, Xueping Wang

    IEEE Journal of Biomedical and Health Informatics
    |March 3, 2025
    PubMed
    Summary

    We developed Syn-Net, a novel deep learning model for accurate breast tumor segmentation in ultrasound images. It effectively handles image complexity, noise, and intensity variations, improving diagnostic capabilities.

    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

    Development and clinical application of a primary cancer organoid-PBMC co-culture system for personalized immunotherapy.

    Drug resistance updates : reviews and commentaries in antimicrobial and anticancer chemotherapy·2026
    Same author

    L-2-Hydroxyglutarate sensitizes ferroptosis through ATF3/CHAC1-mediated glutathione degradation in hepatocellular carcinoma.

    Cell death & disease·2026
    Same author

    Yellowing treatment transforms sensory profile of Qianlin cha (<i>Camellia cuspidata</i>): Key aroma compounds and quality enhancement.

    Food chemistry: X·2026
    Same author

    The "metamorphosis" of alum sludge for phosphate adsorption: Deciphering the interlayer microenvironment construction and molecular mechanism of intercalated layered double hydroxides.

    Environmental research·2026
    Same author

    AGCECDA: attention-guided heterogeneous graph collaborative embedding for circRNA-drug sensitivity association prediction.

    BMC biology·2026
    Same author

    Rapid Detection of Chicken Infectious Anemia Virus Using a One-Tube RPA-CRISPR/Cas12a System.

    Veterinary sciences·2026

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Biomedical Engineering

    Background:

    • Accurate breast tumor segmentation in ultrasound images is vital for diagnosis and treatment planning.
    • Ultrasound images present challenges like speckle noise, variable tumor morphology, and similar intensity distributions, hindering precise segmentation.
    • Existing deep learning methods struggle with the inherent complexities of ultrasound breast tumor imaging.

    Purpose of the Study:

    • To propose a novel deep learning network, the Synchronous Frequency-perception Fusion Network (Syn-Net), for precise breast tumor segmentation in ultrasound images.
    • To address the challenges posed by complex ultrasound image characteristics, including noise and intensity variations.
    • To improve the accuracy and reliability of automated breast tumor segmentation.

    More Related Videos

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    996
    A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy
    09:21

    A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy

    Published on: April 17, 2026

    31

    Related Experiment Videos

    Last Updated: May 1, 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

    2.6K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    996
    A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy
    09:21

    A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy

    Published on: April 17, 2026

    31

    Main Methods:

    • Designed a synchronous dual-branch encoder for simultaneous extraction of local and global image features.
    • Introduced a Frequency-perception Cross-Feature Fusion (FrCFusion) Block utilizing Discrete Cosine Transform (DCT) to fuse multi-frequency features and mitigate intensity similarities.
    • Developed a Full-Scale Deep Supervision method to correct speckle noise influence and guide feature learning.

    Main Results:

    • Extensive experiments on three public ultrasound breast tumor datasets demonstrated Syn-Net's superior performance.
    • Compared to 14 state-of-the-art methods, Syn-Net showed enhanced sensitivity to image variations, tumor characteristics, and noise.
    • Achieved superior Dice scores on the BUSI and Dataset B datasets, outperforming existing approaches.

    Conclusions:

    • Syn-Net effectively addresses the challenges in ultrasound breast tumor segmentation.
    • The proposed network demonstrates robust performance across diverse ultrasound images and tumor types.
    • Syn-Net offers a promising advancement for accurate and reliable automated breast tumor segmentation in clinical practice.