New Transformer model integrates diverse data for breast cancer prediction

Researchers have developed a novel Transformer model designed to integrate diverse data types for improved breast cancer subtype classification and survival prediction. This approach addresses limitations in existing methods by enabling fine-grained token-level interactions across different data modalities, rather than treating them as monolithic feature vectors. The model also employs structured token exchange for cross-modal fusion and optimizes classification and survival objectives jointly, introducing a shared regularization signal. AI

IMPACT This research could lead to more accurate and personalized cancer treatments by improving the analysis of complex patient data.

RANK_REASON The item is an academic paper detailing a new model and methodology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• computer science
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• Litmaps
• machine learning
• ScienceCast
• scite Smart Citations
• Token-Level Cross-Modal Transformer with Contrastive Multi-Task Learning for Breast Cancer Subtype Classification and Survival Prediction

• paper
• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →