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: Mar 29, 2026

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

2.0K

A Novel Hybrid CNN-ViT-Based Bi-Directional Cross-Guidance Fusion-Driven Breast Cancer Detection Model.

Abdul Rahaman Wahab Sait1, Yazeed Alkhurayyif2

  • 1Department of Documents and Archive, Center of Documents and Administrative Communication, King Faisal University, P.O. Box 400, Al-Ahsa 31982, Saudi Arabia.

Life (Basel, Switzerland)
|March 28, 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

Artificial Intelligence-Powered Chronic Obstructive Pulmonary Disease Detection Techniques-A Review.

Diagnostics (Basel, Switzerland)·2025
Same author

Deep Learning-Powered Down Syndrome Detection Using Facial Images.

Life (Basel, Switzerland)·2025
Same author

Correction: Shaikh et al. A Review of Artificial Intelligence-Based Down Syndrome Detection Techniques. <i>Life</i> 2025, <i>15</i>, 390.

Life (Basel, Switzerland)·2025
Same author

Diabetic Foot Ulcers Detection Model Using a Hybrid Convolutional Neural Networks-Vision Transformers.

Diagnostics (Basel, Switzerland)·2025
Same author

A Review of Artificial Intelligence-Based Down Syndrome Detection Techniques.

Life (Basel, Switzerland)·2025
Same author

Ensemble learning driven Kolmogorov-Arnold Networks-based Lung Cancer classification.

PloS one·2024

This study introduces a novel dual-stream AI framework for mammography, enhancing breast cancer detection accuracy. The model integrates local and global feature analysis for improved diagnostic decision-making in computer-aided screening systems.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Accurate breast cancer identification from mammography is crucial for reducing mortality.
  • Automated analysis faces challenges from subtle lesions, dense breasts, and modality variations.
  • Existing Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) struggle with unified representations.

Purpose of the Study:

  • To develop a robust dual-stream framework for improved mammographic analysis.
  • To enhance diagnostic decision-making by integrating local and global feature extraction.
  • To overcome limitations of standard CNNs and ViTs in breast cancer detection.

Main Methods:

  • A dual-stream framework combining ConvNeXt for local features and Swin Transformer V2 for global context.
Keywords:
Bi-directional cross-guidance fusionbreast cancer detectionexplainable deep learninghybrid CNN–ViTmammography image analysisprototype-based classification

Related Experiment Videos

Last Updated: Mar 29, 2026

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

2.0K
  • Implementation of a Bi-Directional Cross-Guidance (BDCG) mechanism for feature interaction.
  • Utilizing a Prototype-Anchored Similarity Head (PASH) for stable, distance-based classification.

    • Main Results:

    • Achieved high accuracy (98.8%) and F1 score (97.2%) on Dataset 1, outperforming existing models.
    • Demonstrated strong performance (97.0% accuracy, 95.1% F1 score) on heterogeneous Dataset 2.
    • Showcased lower inference time (8.3 ms/image) and resilience to domain shift.

    Conclusions:

    • The proposed framework effectively integrates multi-scale features and prototype-driven classification for robust mammographic analysis.
    • Structural multi-scale feature interaction and prototype-driven classification are valuable for AI in mammography.
    • The framework shows potential for reliable application in computer-aided breast cancer screening systems.