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 5, 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

A Hybrid Model for Ultrasound Image-Based Breast Cancer Diagnosis Using EfficientNet-V2 and Vision Transformer.

Zainab Qahtan Mohammed1, Amel Tuama Alhussainy2, Ihsan Salman Jasim1

  • 1Department of Computer Science, College of Basic Education, Diyala University, Diyala 32001, Iraq.

Diagnostics (Basel, Switzerland)
|May 4, 2026
PubMed
Summary

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

A Symmetric Encoder-Decoder Network with Enhanced Group-Shuffle Modules for Robust Lung Nodule Detection in CT Scans.

Biomimetics (Basel, Switzerland)·2026
Same author

Inertial Sensor-Based Recognition of Field Hockey Activities Using a Hybrid Feature Selection Framework.

Sensors (Basel, Switzerland)·2025
Same author

Enhanced structural tunability and high sensitivity of a THz metasurface absorber for precise automotive fuel characterization.

Scientific reports·2025
Same author

Dumbbell shaped structure loaded modified circular ring resonator based perfect metamaterial absorber for S, X and Ku band microwave sensing applications.

Scientific reports·2024
Same author

Automated Glaucoma Screening and Diagnosis Based on Retinal Fundus Images Using Deep Learning Approaches: A Comprehensive Review.

Diagnostics (Basel, Switzerland)·2023
Same author

Enhancement of Ultrasound B-Mode Image Quality Using Nonlinear Filtered-Multiply-and-Sum Compounding for Improved Carotid Artery Segmentation.

Diagnostics (Basel, Switzerland)·2023
This summary is machine-generated.

A new hybrid deep learning model improves breast cancer detection in ultrasound images, achieving 97.95% accuracy. This AI framework combines convolutional neural networks and transformers for more reliable breast cancer classification.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Breast cancer is a leading global health concern for women.
  • Ultrasound imaging aids detection in dense breast tissue but suffers from subjectivity and variability.
  • Artificial intelligence (AI) is crucial for enhancing diagnostic accuracy in medical imaging.

Purpose of the Study:

  • To introduce a hybrid deep learning framework for breast cancer classification using ultrasound images.
  • To leverage the strengths of both convolutional neural networks (CNNs) and transformers for improved analysis.
  • To address the limitations of traditional ultrasound interpretation through AI-driven solutions.

Main Methods:

  • Developed a hybrid deep learning architecture combining a Vision Transformer (ViT) encoder and an EfficientNetV2-RW-S feature extractor.
Keywords:
Efficient Netbreast cancerclassificationhybrid modelultrasoundvision transformer

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

Related Experiment Videos

Last Updated: May 5, 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
  • Utilized the Breast Ultrasound Image Dataset (BUSI dataset) for training and evaluation.
  • Integrated CNNs for fine-grained morphological details and transformers for long-range dependencies.

    • Main Results:

    • The hybrid model achieved a high classification accuracy of 97.95%.
    • Outperformed standalone ViT (89%) and CNN (80%) models.
    • Significantly reduced computational complexity by decreasing tokens from 197 to 10, lowering memory and cost.

    Conclusions:

    • The proposed hybrid deep learning framework offers improved diagnostic and computational analysis for breast cancer detection.
    • This AI-driven approach shows potential for integration into clinical settings.
    • The study highlights the benefits of combining different neural network architectures for enhanced medical image analysis.