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: Jun 13, 2026

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells
10:37

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

Published on: August 22, 2025

Federated Privacy-Preserving Multi-Modal Deep Learning for Breast Cancer Diagnosis: A Physics-Aware Approach.

Ahmed Lateef Salih Al-Karawi1,2, Hayder Mohammedqasim1, Rüya Yılmaz3

  • 1Department of Computer Engineering, Faculty of Engineering, Istanbul Aydin University, Istanbul 34295, Turkey.

Diagnostics (Basel, Switzerland)
|June 12, 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

Diagnosing Coronary Artery Disease on the Basis of Hard Ensemble Voting Optimization.

Medicina (Kaunas, Lithuania)·2022
Same author

Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem.

Medicina (Kaunas, Lithuania)·2021
Same journal

Correction: Luca et al. Global and Regional Diagnostic Results of Progress Toward Cervical Cancer Elimination, According to the WHO Strategy: A Systematic Literature Review with Narrative Synthesis. <i>Diagnostics</i> 2026, <i>16</i>, 1224.

Diagnostics (Basel, Switzerland)·2026
Same journal

Association Between Systemic Inflammatory Response Biomarkers and Disease Activity in Systemic Lupus Erythematosus: A Multi-Center Retrospective Study.

Diagnostics (Basel, Switzerland)·2026
Same journal

Vertebrogenic Low Back Pain and Basivertebral Nerve Ablation: A Review of Mechanisms, Imaging-Driven Selection, and Clinical Outcomes.

Diagnostics (Basel, Switzerland)·2026
Same journal

Multivalvular Carcinoid Heart Disease: The Role of Echocardiography in Diagnosis and Selection for Heterotopic Bicaval Valve Implantation.

Diagnostics (Basel, Switzerland)·2026
Same journal

Data-Efficient and Explainable Multimodal Survival Prediction in NSCLC Using Deep Image Embeddings, Clinical Variables, and Gradient-Boosted Trees.

Diagnostics (Basel, Switzerland)·2026
Same journal

Anomalous Left Coronary Artery from the Pulmonary Artery: Cinematic Volume Rendering Technique for Enhanced Anatomic Visualization.

Diagnostics (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces a multi-modal breast cancer classification pipeline using deep learning and federated learning, achieving high accuracy across ultrasound, MRI, and mammography. The pipeline optimizes data processing and communication for potential clinical deployment.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Breast cancer is a leading cause of mortality in women globally.
  • Existing breast cancer classification methods often lack multi-modal integration and efficient federated learning strategies.
  • Standard preprocessing techniques can be optimized for different imaging modalities (ultrasound, MRI, mammography) in breast cancer detection.

Purpose of the Study:

  • To develop and evaluate a multi-modal breast cancer classification pipeline.
  • To integrate deep learning models with federated learning for privacy-preserving analysis.
  • To assess the impact of preprocessing and federated learning algorithms on diagnostic performance and efficiency.

Main Methods:

  • A multi-modal pipeline combining modality-specific deep learning models and late-fusion inference.
Keywords:
FP16-FedAvgSCAFFOLDbreast cancercommunication overheaddeployment-aware evaluationfederated learningkey-slice extractionlate fusionmulti-modal imagingphysically motivated preprocessingstatistical validation

Related Experiment Videos

Last Updated: Jun 13, 2026

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells
10:37

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

Published on: August 22, 2025

  • Federated learning evaluation using FedAvg, FedProx, SCAFFOLD, FedNova, and FP16-FedAvg under IID and non-IID conditions.
  • Cross-validation across ultrasound (BUSI), MRI (DUKE), and mammography (CBIS-DDSM) datasets.

    • Main Results:

    • Per-modality models achieved accuracies of 92.50% (ultrasound), 90.63% (MRI), and 92.00% (mammography).
    • Weighted late fusion improved accuracy to 93.10%.
    • FP16 transmission significantly reduced bandwidth (-84.9%) with no performance loss; SCAFFOLD showed highest non-IID accuracy (90.50%).

    Conclusions:

    • The developed pipeline demonstrates technical validity and identifies deployment-relevant trade-offs for multi-modal breast cancer classification.
    • Federated learning, particularly SCAFFOLD, shows promise for non-IID data, and FP16 optimizes communication efficiency.
    • External validation is crucial before clinical deployment due to simulation-based evaluation and potential annotation needs.