CHIEF (Harvard, Yu Lab)
A pathology model trained across 19 cancer types that predicts survival and mutations from slides.
Nature 2024: pretrained on 15M tiles then 60,530 slides; validated on 19,400 slides from 24 hospitals for detection, origin, genomic prediction and prognosis.
Generic schematic · not to scale · placeholder for the ai computation front
Flagged finding · Neural network
How it works
Weakly supervised slide-level learning with anatomical-site text embeddings.
Strengths
- Broad external validation
Limitations
- Research release
Since
2024
Latest papers
topLatest papers · live from Europe PMC
Query for this technology: (TITLE:"CHIEF" OR ABSTRACT:"CHIEF" OR TITLE:"Harvard, Yu Lab" OR ABSTRACT:"Harvard, Yu Lab") 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 CHIEF (Harvard, Yu Lab), not a curated reading list.