Extended Data Fig. 9: Text-to-image retrieval performances for Recall@50.
From: A visual–language foundation model for pathology image analysis using medical Twitter
a, Image retrieval performances for Recall@50 within each of the pathology subspecialty-specific hashtags. b, Two-sided Spearman correlations between the number of candidates and fold changes for Recall@50 when comparing the PLIP model with random and CLIP, respectively. In regression plots, the regression estimates are displayed with 95% confidence intervals in grey or purple colors.
