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 28, 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

Bidirectional Perceptual Multimodal Interaction Network Based on Contrastive Learning for Breast Cancer pCR

Jingjing Feng1, Zongli Jiang1, Jinli Zhang1

  • 1College of Computer Science, Beijing University of Technology, Beijing 100124, China.

Tomography (Ann Arbor, Mich.)
|May 26, 2026
PubMed
Summary
This summary is machine-generated.

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

Genetic Mutation and Epigenetic Silencing Drive Antigen-Negative Relapse in CD7 CAR-T Treated T-cell Lymphoid Malignancies.

Blood cancer discovery·2026
Same author

CD7 chimeric antigen receptor T cells in patients with relapsed or refractory CD7-positive acute myeloid leukemia.

Leukemia·2026
Same author

Factors Influencing Anxiety and Depression Symptoms in Patients With Acute Ischaemic Stroke and the Development and Validation of a Risk Prediction Model.

Actas espanolas de psiquiatria·2026
Same author

Cultivation of Chlorella sorokiniana with Simulated Flue Gas and Utilization of the Biomass as Fertilizer.

Applied biochemistry and biotechnology·2026
Same author

Association between triglyceride glucose-body mass index and chronic diarrhea: A cross-sectional study of NHANES 2005-2010 data.

Gastroenterologia y hepatologia·2026
Same author

Structural characterization, lipid-lowering activity, and emulsifying properties of polysaccharides derived from wheat pericarp via Ganoderma lucidum solid-state fermentation.

Food research international (Ottawa, Ont.)·2026

A new AI model, BPMINet, accurately predicts breast cancer treatment response using MRI and clinical data. This improves personalized medicine by overcoming data challenges for better patient outcomes.

Area of Science:

  • Artificial Intelligence in Medicine
  • Medical Imaging Analysis
  • Oncology

Background:

  • Accurate prediction of pathological complete response (pCR) is crucial for personalized breast cancer treatment.
  • Existing deep learning models struggle with tumor heterogeneity and data misalignment, limiting prediction accuracy.
  • Novel multimodal approaches are needed to integrate diverse data types for improved breast cancer response prediction.

Purpose of the Study:

  • To develop a novel multimodal network for accurate prediction of pCR after neoadjuvant chemotherapy (NAC).
  • To address semantic misalignment between DCE-MRI and clinical data for enhanced breast cancer treatment response prediction.
  • To improve the generalization performance of pCR prediction models.

Main Methods:

Keywords:
breast cancercontrastive learningmultimodal fusionpCR prediction

Related Experiment Videos

Last Updated: May 28, 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

  • Proposed Bidirectional Perceptual Multimodal Interaction Network (BPMINet) utilizing contrastive learning.
  • Implemented a bidirectional cross-modal attention (BiCMA) mechanism for effective multimodal feature fusion.
  • Integrated a multimodal contrast-aware feature enhancement (MCFE) module and a dual-loss strategy for optimized pCR prediction.

    • Main Results:

    • BPMINet demonstrated superior performance across seven metrics on two multicenter datasets.
    • Achieved significant improvements in AUC (5.17%) and accuracy (5.24%) on the MAMA-MIA dataset compared to baselines.
    • Showcased substantial gains in AUC (11.72%) and accuracy (7.38%) on the ISPY1 dataset.

    Conclusions:

    • BPMINet achieves optimal performance in predicting breast cancer pathological complete response.
    • The model exhibits strong generalization capabilities for multimodal pCR prediction.
    • Confirms the superiority of BPMINet for personalized breast cancer treatment decisions.