Figure 3 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Benchmark of sCellST a. Overview of the benchmarking approach. Each slide is used for training and then the model is evaluated on the two remaining slides. b. H&E slides from the PDAC Visium dataset. c. Benchmark results: each boxplot represents the distribution of Pearson / Spearman correlation coefficient on all genes.
Source publication
Advancing our understanding of tissue organization and its disruptions in disease remains a key focus in biomedical research. Histological slides stained with Hematoxylin and Eosin (H&E) provide an abundant source of morphological information, while Spatial Transcriptomics (ST) enables detailed, spatially-resolved gene expression (GE) analysis, tho...
Contexts in source publication
Context 1
... there is currently no method that specifically targets single-cell GE prediction from Visium data, we performed spot-level comparisons, even though this was not the primary objective of our method. We used 3 pancreatic ductal adenocarcinoma (PDAC) Visium slides ( Fig.3b) from [30]. ...
Context 2
... processes small patches from the spot images and predicts GE for each patch, which is then aggregated at the spot level. As shown in our experiments, sCellST outperforms both methods (Fig.3c), which was unexpected given that sCellST was not optimized for this task. ...
