Skip to main content

Table 2 Architectures of the discriminators used in the network model: (a) Local Discriminator, (b) Global Discriminator, and (c) Concatenation Layer

From: Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO)

Type

Kernel

Stride

Outputs

(a) Local Discriminator

Conv

5 × 5

2 × 2

64

Conv

5 × 5

2 × 2

128

Conv

5 × 5

2 × 2

256

Conv

5 × 5

2 × 2

512

Conv

5 × 5

2 × 2

512

FC

–

–

1024

Type

Kernel

Stride

Outputs

(b) Global Discriminator

Conv

5 × 5

2 × 2

64

Conv

5 × 5

2 × 2

128

Conv

5 × 5

2 × 2

256

Conv

5 × 5

2 × 2

512

Conv

5 × 5

2 × 2

512

Conv

5 × 5

2 × 2

512

FC

–

–

1024

Type

Kernel

Stride

Outputs

(c) Concatenation Layer

Conv

–

–

2048

FC

–

–

1

  1. Conv., Convolution layer; FC, Fully-connected layer