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 Videos

A Hybrid Multi-CNN Feature Fusion and LASSO Optimization Approach for High-Performance Breast Cancer Classification.

Tawfiq Beghriche1, Mohamed Djerioui2, Youcef Brik2

  • 1Department of Electronics, Faculty of Technology, University of M'sila University Pole, Road Bordj Bou Arreridj, M'sila, 28000, Algeria. tawfiq.beghriche@univ-msila.dz.

Journal of Imaging Informatics in Medicine
|March 30, 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

RDE-DR: robust deep ensemble CNNs for automated diabetic retinopathy detection from fundus images.

Scientific reports·2026
Same author

Two-Stage Hybrid Convolutional-Transformer Models for Breast Cancer Histopathology.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

A novel deep neural network-based technique for network embedding.

PeerJ. Computer science·2024
Same author

A decision fusion method based on classification models for water quality monitoring.

Environmental science and pollution research international·2022
Same author

Handover Management for Drones in Future Mobile Networks-A Survey.

Sensors (Basel, Switzerland)·2022
Same author

Social media-based COVID-19 sentiment classification model using Bi-LSTM.

Expert systems with applications·2022
Same journal

Kolmogorov-Arnold Guided Local-Global Attention for Medical Image Classification.

Journal of imaging informatics in medicine·2026
Same journal

Artificial Intelligence-Assisted Inner Ear Computed Tomography Analysis: Radiomics-Based Comparison of Affected and Unaffected Ears in Idiopathic Sudden Sensorineural Hearing Loss.

Journal of imaging informatics in medicine·2026
Same journal

High Adoption, Higher Expectations: A Cross-Sectional Survey of Radiologist Engagement with Artificial Intelligence in the United Arab Emirates.

Journal of imaging informatics in medicine·2026
Same journal

Complex-valued Multi-scale Hybrid Attention Network for Fast MRI via Sparsified Data Learning.

Journal of imaging informatics in medicine·2026
Same journal

Automatic Phase and Sequence Identification in Gd-EOB-DTPA-Enhanced Liver MRI Using Deep Convolutional and Sequential Learning.

Journal of imaging informatics in medicine·2026
Same journal

Ultrasound-Based AI in Predicting Hormone Receptor Status in Breast Cancer: Is "Digital Biopsy" Possible.

Journal of imaging informatics in medicine·2026
See all related articles
This summary is machine-generated.

A new hybrid deep learning model combining three CNNs (MobileNetV2, DenseNet121, InceptionV3) significantly improves breast cancer detection accuracy. This approach enhances early diagnosis by integrating diverse features for more robust breast cancer classification.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Breast cancer is a leading cause of mortality in women globally.
  • Early and accurate detection is crucial for improving survival rates.
  • Deep learning, especially CNNs, shows potential in medical image analysis but single models have limitations.

Purpose of the Study:

  • To develop a hybrid deep learning model for robust breast cancer diagnosis using breast ultrasound images.
  • To leverage the complementary strengths of multiple CNNs to overcome limitations of single-model approaches.
  • To enhance the interpretability and generalizability of the diagnostic model.

Main Methods:

  • A hybrid approach combining MobileNetV2, DenseNet121, and InceptionV3 was employed.
Keywords:
Breast cancer detectionDeep learningFeature fusionFeature selectionLASSO regressionTransfer learningUltrasound images

Related Experiment Videos

  • Features were extracted from 780 breast ultrasound images (BUSI dataset) and fused into a high-dimensional vector.
  • LASSO-driven feature selection was applied to the fused representation, followed by five-fold cross-validation.

    • Main Results:

    • The hybrid model achieved high performance metrics: 99.23% accuracy, 98.57% sensitivity, 99.54% specificity, 99.07% precision, 98.80% F1-score, and 0.9985 AUC.
    • The proposed method outperformed existing state-of-the-art techniques on the evaluated dataset.
    • Feature fusion and selection mitigated overfitting and improved model generalizability.

    Conclusions:

    • The hybrid deep learning model demonstrates superior performance for breast cancer diagnosis from ultrasound images.
    • This approach offers a promising tool for accurate and early breast cancer detection.
    • Future research should involve validation on larger, multicenter datasets.