Biological spatial priors based on MSI histology, when injected into TransMIL with foundation model features, improve cross-site generalization for MSI prediction from H&E WSIs, with peripheral distance encoding achieving high internal AUC and perfect external specificity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Biological Spatial Priors Regularize Foundation Model Representations for Cross-Site MSI Generalization in Colorectal Cancer
Biological spatial priors based on MSI histology, when injected into TransMIL with foundation model features, improve cross-site generalization for MSI prediction from H&E WSIs, with peripheral distance encoding achieving high internal AUC and perfect external specificity.