CHRep improves spatial gene expression prediction from H&E slides via topology-preserving representation learning plus post-hoc calibration, reporting up to 39.5% higher Pearson correlation and reduced errors under leave-one-slide-out evaluation across three cohorts.
Benchmarking the translational potential of spatial gene expression prediction from histology,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CHRep: Cross-modal Histology Representation and Post-hoc Calibration for Spatial Gene Expression Prediction
CHRep improves spatial gene expression prediction from H&E slides via topology-preserving representation learning plus post-hoc calibration, reporting up to 39.5% higher Pearson correlation and reduced errors under leave-one-slide-out evaluation across three cohorts.