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

Chemical and sensory profiling of fermented, washed, and artificially flavored coffee beans: Insights into flavour quality, authenticity, and food safety implications.

Food chemistryĀ·2026
Same author

Design, synthesis, biological evaluation, DFT and molecular docking studies of novel isoxazolines containing cyclic amide.

Bioorganic chemistryĀ·2026
Same author

Air-permeable hydrogels through viscoelastic phase separation of aerogels.

NatureĀ·2026
Same author

Post-stroke acute heart failure in patients with large vessel occlusion undergoing endovascular treatment: A pooled analysis of individual patient data from multicenter studies with mediation analysis.

PLoS medicineĀ·2026
Same author

High-definition transcranial direct current stimulation enhances exercise-induced hypoalgesia in patients with chronic low back pain.

iScienceĀ·2026
Same author

PEGylated thymosin Ī²4 is a thiol-site-specific prodrug treating myocardial infarction in vivo.

Bioengineering & translational medicineĀ·2026

Related Experiment Video

Updated: Jun 18, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.5K

Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI.

Lei Zhou, Yuzhong Zhang, Jiadong Zhang

    IEEE Transactions on Medical Imaging
    |July 29, 2024
    PubMed
    Summary

    A new hybrid deep learning network combines CNNs and transformers for accurate breast tumor segmentation in DCE-MRI scans. This method improves efficiency and aids in identifying HER2-positive subtypes, matching manual segmentation accuracy.

    More Related Videos

    Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model
    06:24

    Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model

    Published on: April 18, 2015

    15.1K
    Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
    10:25

    Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

    Published on: September 25, 2019

    47.9K

    Related Experiment Videos

    Last Updated: Jun 18, 2025

    Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
    15:48

    Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

    Published on: December 15, 2014

    22.5K
    Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model
    06:24

    Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model

    Published on: April 18, 2015

    15.1K
    Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
    10:25

    Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

    Published on: September 25, 2019

    47.9K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Biomedical Engineering

    Background:

    • Accurate breast tumor segmentation in dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) is crucial for diagnosing breast disease.
    • Current segmentation methods often require complex networks, leading to high computational costs.
    • There is a need for efficient and accurate automated segmentation techniques.

    Purpose of the Study:

    • To develop a hybrid deep learning network balancing computational cost and segmentation performance for DCE-MRI.
    • To improve the accuracy and efficiency of automated breast tumor segmentation.
    • To evaluate the utility of automated segmentation in subtype identification (e.g., HER2 status).

    Main Methods:

    • A hybrid network combining convolution neural network (CNN) and transformer layers within an encoder-decoder architecture.
    • Implementation of 3D transformer layers to capture global dependencies in bottleneck features.
    • Introduction of parallel encoder subnetworks for enhanced efficiency.
    • Integration of a prototype learning guided prediction module using online clustering for improved discriminative capability.

    Main Results:

    • The proposed hybrid network demonstrated superior performance compared to state-of-the-art methods on private and public DCE-MRI datasets.
    • The network achieved a balance between segmentation accuracy and computational cost.
    • Automated tumor masks generated by the network were effective in identifying HER2-positive from HER2-negative subtypes with accuracy comparable to manual segmentation.

    Conclusions:

    • The hybrid CNN-transformer network offers an efficient and accurate solution for automated breast tumor segmentation in DCE-MRI.
    • The method shows potential for clinical applications, including aiding in breast cancer subtype classification.
    • This approach advances automated medical image analysis for improved breast cancer diagnosis and management.