BMC Cancer

Table 2 ViT, VGG16 and ConvNet model evaluation for the 3-class scenario

From: Artificial intelligence based vision transformer application for grading histopathological images of oral epithelial dysplasia: a step towards AI-driven diagnosis

	Precision			Recall			F1-score
Models	ViT	VGG16	ConvNet	ViT	VGG16	ConvNet	ViT	VGG16	ConvNet
Low risk	0.97	0.88	0.84	0.89	0.81	0.91	0.93	0.84	0.87
High risk	0.88	0.81	0.89	0.97	0.87	0.82	0.92	0.84	0.85
Normal	1.00	0.94	0.95	1.00	0.96	0.93	1.00	0.95	0.94
Accuracy							0.94	0.86	0.88
Macro average	0.95	0.87	0.89	0.95	0.88	0.89	0.95	0.88	0.89
Weighted average	0.95	0.87	0.88	0.94	0.86	0.88	0.94	0.86	0.88

Back to article page

ISSN: 1471-2407

Contact us

Submission enquiries: bmccancer@biomedcentral.com
General enquiries: ORSupport@springernature.com