Research map / Vision-language and multimodal / Cross-modal learning
Bridging Radiology and Pathology Foundation Models via Concept-Based Multimodal Co-Adaptation
Yihang Chen, Yanyan Huang, Fuying Wang, Maximus Yeung, Yuming Jiang, Shujun Wang, Lequan Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add context prompt (cross-domain guidance) (ablation) | CTF · Center1-GC survival | C-index: 0.629 -> 0.665 | Improved |
| add shared prompt (ablation) | CTF · Center1-GC survival | C-index: 0.653 -> 0.665 | Improved |
| add global prompt (ablation) | CTF · Center1-GC survival | C-index: 0.642 -> 0.665 | Improved |
| add context prompt (ablation) | CTF · Center1-GC grading | AUC: 0.635 -> 0.660 | Improved |
| use dynamic concept tuning instead of static concepts (ablation) | CTF · Center1-GC survival | C-index: 0.586 -> 0.665 | Improved |
| add co-adaptive prompts to static concepts (ablation) | Static Concepts · Center1-GC survival | C-index: 0.638 -> 0.665 | Improved |
| use prognostic diversity-aware selection instead of random (ablation) | CTF · Center1-GC survival | C-index: 0.622 -> 0.665 | Improved |
| use diversity-aware selection instead of top-MI (ablation) | CTF · Center1-GC survival | C-index: 0.646 -> 0.665 | Improved |
| use random concept selection (ablation) | CTF · Center1-GC grading | AUC: 0.660 -> 0.654 | No clear effect |
| use expert BiomedCLIP+CONCH instead of general CLIP+CLIP (ablation) | CTF · Center1-GC survival | C-index: 0.621 -> 0.665 | Improved |
| swap pathology encoder to MUSK (ablation) | CTF · Center1-GC survival | C-index: 0.665 -> 0.680 | Improved |
| swap pathology encoder to PLIP (ablation) | CTF · Center1-GC survival | C-index: 0.665 -> 0.627 | Hurt |
Closest papers by meaning
- Perturbating, Tuning, and Collaborating: Harnessing Vision Foundation Models for Single Domain Generalization on Medical Imaging (AAAI 2025 · similarity 0.86)
- A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis (NeurIPS 2024 · similarity 0.86)
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis (ICLR 2026 · similarity 0.85)
- Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement (NeurIPS 2024 · similarity 0.85)
- Interactive Medical Image Analysis with Concept-based Similarity Reasoning (CVPR 2025 · similarity 0.85)
- When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
