Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT

Table 1

Summary of the parameters of the feature extractor and the classifier networks.

	Feature extractor	Classifier
Loss function	Cross entropy	Weight cross entropy
Learning method	Adam	Adam
Learning rate	1e − 6	1e − 3
Weight decay	1e − 6	1e − 6
Epochs	600	600
Patients/batch	2	2
Slides/patient	20	n.a.

n.a.: not applicable.