CMRCNet uses contrastive learning plus cross-modal mask reconstruction to predict spatial gene expression from whole-slide histopathology images, improving PCC over prior methods by 6-11% on average.
2 Boxplot of gene PCC distribution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Spatial Transcriptomics Expression Prediction from Histopathology Based on Cross-Modal Mask Reconstruction and Contrastive Learning
CMRCNet uses contrastive learning plus cross-modal mask reconstruction to predict spatial gene expression from whole-slide histopathology images, improving PCC over prior methods by 6-11% on average.