Table 2.

Class makeup of training/testing dataset splits. This table describes the percent makeup of each of the three classes (stroma, epithelium, and lumen) used to train and test the classifiers.

	Stroma (%)	Epithelium (%)	Lumen (%)
MG training set	$\sim 60$	$\sim 20$	$\sim 20$
HG training set	$\sim 75$	$\sim 21$	$\sim 4$
MG test set	$\sim 64$	$\sim 26$	$\sim 10$
HG test set	$\sim 70$	$\sim 24$	$\sim 6$