Skip to main content

Table 4 The different kernel size configurations

From: Fusing multi-scale information in convolution network for MR image super-resolution reconstruction

Network

\(s_{k}\)/\(n_{k}\) in nMFU

\(s_{k}\)/\(n_{k}\) in reconstruction layer

\(MFCN_{BL}\)

9/32, 3/64

5/1

\(MFCN_{s_{713}}\)

7/32, 1/64

3/1

\(MFCN_{s_{957}}\)

9/32, 5/64

7/1

\(MFCN_{s_{1159}}\)

11/32, 5/64

9/1