Training Dataset
Cross-source consensus on Training Dataset from 1 sources and 4 claims.
1 sources · 4 claims
Preparation
Where it comes from
Highlighted claims
- The dataset came from a multi-center, multi-disease Enable Medicine cohort with 7,600 mIF tissue slices. — Linking spatial biology and clinical histology via Haiku
- Of the 7,600 mIF slices, 3,554 had co-registered H&E and clinical metadata and 4,046 were mIF-only. — Linking spatial biology and clinical histology via Haiku
- The paired pretraining set included 26,669,005 tri-modal patches from 3,218 tissue sections. — Linking spatial biology and clinical histology via Haiku
- Patient-level splitting was used to prevent leakage between training and held-out testing. — Linking spatial biology and clinical histology via Haiku