Lung Cancer Nodules Detection via an Adaptive Boosting Algorithm Based on Self-Normalized Multiview Convolutional Neural Network

Table 2

Comparison of proposed AdaBoost-SNMV-CNN with different models. We can observe that the proposed method has better performance compared to other methods on the LIDC-IDRI dataset.

Dataset	Models	Accuracy	Sensitivity	Specificity
LIDC-IDRI	Two-stage CNN	0.844	0.835	0.915
	Multicrop	0.8714	0.77	0.93
	MVKBC	0.916	0.865	0.940
	Zhao et al.	0.823	—	—
	Lyu et al.	0.921	0.921	0.915
	AdaBoost-SNMV-CNN	0.929	0.930	0.921