Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 27, 2025Physics in Medicine and BiologyOpen Access

Foundation-model–based multimodal transformer framework for survival analysis in HER2-stratified breast cancer

View Full Paper
Ask AI
Bookmark
Share

Authors

QLQiang LiSWShansong WangMSMojtaba Safari

Discussion

Loading...

Member takes

Overview

Multimodal transformer improves survival prediction in HER2-positive breast cancer, highlighting tumor heterogeneity.

Key Points

  • The model achieved a concordance index (C-index) of 0.857, indicating strong prediction accuracy.
  • Risk stratification effectively separated high-risk and low-risk groups with log-rank p < 0.01.
  • The model integrates clinical narratives, molecular features, and whole-slide images for better accuracy.
  • The framework enhances prognostic accuracy by addressing tumor heterogeneity through multimodal fusion.

Cite This Study

Li et al. (2025) studied this question.

synapsesocial.com/papers/68d7cc66eebfec0fc523885ehttps://doi.org/10.1088/1361-6560/ae0be6
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Comprehensive Multimodal Deep Learning Survival Prediction Enabled by a Transformer Architecture: A Multicenter Study in Glioblastoma2024 · 1 citations
  2. 2MM-SurvNet: Deep Learning-Based Survival Risk Stratification in Breast Cancer Through Multimodal Data Fusion2024 · 1 citations
  3. 3An Interpretable Multi-Dataset Learning Framework for Breast Cancer Prediction Using Clinical and Biomedical Tabular Data2026 · 2 citations
  4. 4BioFusionNet: Deep Learning-Based Survival Risk Stratification in ER+ Breast Cancer Through Multifeature and Multimodal Data Fusion2024 · 4 citations
  5. 5Selective multimodal deep learning for reliable breast cancer subtype classification from histopathology and genomic data2026 · 3 citations