AR
Data & Repro
armored-cart-design-agent
Design armored CAR-T cells with cytokine payloads and resistance mechanisms.
FreedomIntelligence/OpenClaw-Medical-SkillsView
Data & Repro
MU
multimodal-radpath-fusion-agent
Maintainer FreedomIntelligence · Last updated April 1, 2026
Fuse radiology and pathology imaging for integrated cancer phenotyping.
Original source
FreedomIntelligence/OpenClaw-Medical-Skills
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/multimodal-radpath-fusion-agent
- Maintainer
- FreedomIntelligence
- License
- MIT
- Last updated
- April 1, 2026
Skill Snapshot
Key Details From SKILL.md
Key Notes
- The Multimodal Radpath Fusion Agent integrates diverse clinical data sources including radiology imaging (CT, MRI, PET), digital pathology whole slide images, genomic profiling, and electronic health records using state-of-the-art multimodal deep learning for comprehensive cancer diagnosis, treatment response prediction, and prognostic modeling.
- When integrating radiology and pathology for unified tumor assessment.
- For treatment response prediction using multimodal imaging.
- To predict molecular features from imaging (imaging genomics).
- When building comprehensive prognostic models.
Source Doc
Excerpt From SKILL.md
Core Capabilities
-
Radiology-Pathology Fusion: Integrate macro and microscopic views.
-
Imaging-Genomics Correlation: Predict molecular features from imaging.
-
Treatment Response Prediction: Multi-modal response modeling.
-
Survival Prediction: Comprehensive prognostic models.
-
Tumor Characterization: Integrate phenotype from all modalities.
-
Clinical Decision Support: AI-assisted tumor board recommendations.
Supported Modalities
| Modality | Data Type | Features Extracted |
|---|---|---|
| CT | DICOM volumes | Radiomics, deep features |
| MRI | Multi-sequence DICOM | Texture, perfusion, ADC |
| PET | SUV maps | Metabolic features |
| H&E WSI | SVS/NDPI images | Histology, spatial patterns |
| IHC | Stained slides | Biomarker quantification |
| WES/WGS | VCF | Mutations, TMB, signatures |
| RNA-seq | Expression matrix | Pathway signatures |
| Clinical | EHR data | Demographics, labs, history |
Fusion Architectures
| Architecture | Method | Best For |
|---|---|---|
| AMRI-Net | Attention fusion | Radiology focus |
| PathOmCLIP | Contrastive learning | Path-omics alignment |
| SMuRF | Swin Transformer | Multi-region integration |
| MultiModal Transformer | Self-attention | All modalities |
| GNN Fusion | Graph networks | Spatial relationships |
Use cases
- When integrating radiology and pathology for unified tumor assessment.
- For treatment response prediction using multimodal imaging.
- To predict molecular features from imaging (imaging genomics).
- When building comprehensive prognostic models.
Not for
- Do not rely on this catalog entry alone for installation or maintenance details.
Upstream Related Skills
- Radiomics_Pathomics_Fusion_Agent - Imaging-specific fusion
- Pathology_AI/CONCH_Agent - Pathology foundation model
- Pan_Cancer_MultiOmics_Agent - Genomic integration
- Virtual_Lab_Agent - AI research coordination
Related skills
Related skills
AR
Data & Repro
arxiv-search
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.
FreedomIntelligence/OpenClaw-Medical-SkillsView
AU
Data & Repro
autonomous-oncology-agent
Autonomous oncology research agent: literature mining, trial matching, biomarker analysis, and treatment hypothesis generation.
FreedomIntelligence/OpenClaw-Medical-SkillsView
BI
Data & Repro
bio-cfdna-preprocessing
Preprocesses cell-free DNA sequencing data including adapter trimming, alignment optimized for short fragments, and UMI-aware duplicate remo…
FreedomIntelligence/OpenClaw-Medical-SkillsView