Primary Investigation of Deep Learning Models for Japanese “Group Classification” of Whole-Slide Images of Gastric Endoscopic Biopsy

Table 3

Test accuracy of five different models.

Model	AUC	Acc (%)
ResNet50	0.988	89.5
VGG16	0.970	83.1
VGG19	0.949	76.6
Xception	0.894	66.2
InceptionV3	0.881	63.0

The models were trained on Dataset 1.