MUSK (Stanford, vision-language pathology)
A model that reads slides and clinical text together to predict who will respond to immunotherapy.
Nature 2025: pretrained on 50M pathology images and 1B pathology-related text tokens; predicted immunotherapy response and prognosis across cancers better than single-modality models.
How it works
MUSK uses masked multimodal pretraining that unifies image and text tokens.
- Multimodal
- Immunotherapy response prediction
- Retrospective validation
Latest papers
topQuery for this technology: (TITLE:"MUSK" OR ABSTRACT:"MUSK" OR TITLE:"Stanford, vision-language pathology" OR ABSTRACT:"Stanford, vision-language pathology") AND (cancer OR tumor OR tumour OR oncology OR carcinoma OR lymphoma OR leukemia OR leukaemia OR myeloma OR sarcoma OR melanoma OR glioma). Results are unfiltered search hits about MUSK (Stanford, vision-language pathology), not a curated reading list.