Table 4.

Comparison of the results of different methods.

Method	Number of nodules	Error (%)
Multiscale CNN [33]	865	15.9
AlexNet + cascaded classifier [34]	1990	15.3
VGG16 + SVM [35]	1945	12.2
B-CNN-FT [4]	3186	8.8
3D-CNN + QIF [36]	664	6.8
3D-CNN + multiscale + multi [20]	962	6.08
3D-Inception-ResNet + hand-crafted features [21]	1036	5.02
DCN + MB-SGD	750	4.0