Multi-Laboratory Hematoxylin and Eosin Staining Variance Supervised Machine Learning Dataset

We provide the generated dataset used for supervised machine learning in the related article. The data are in tabular format and contain all principal components and ground truth labels per tissue type. Tissue type codes used are; C1 for kidney, C2 for skin, and C3 for colon. 'PC' stands for the principal component. For feature extraction specifications, please see the original design in the related article. Features have been extracted independently for each tissue type.