Table 4 Details regarding the training process of each patient-level model.

From: Potential diagnostic application of a novel deep learning- based approach for COVID-19

Model

Input image size

learning rate

Num of epochs

3D-AlexNet

(128 × 128 × 128)

5 × 10–7

50

VoxCNN61

(128 × 128 × 128)

7 × 10–6

50

MASERes

(128 × 128 × 128)

10–6

50