Skip to main content

Table 1 Summary of RMSE of the HU values and SSIM within the PTV

From: Geometric and dosimetric impact of 3D generative adversarial network-based metal artifact reduction algorithm on VMAT and IMPT for the head and neck region

RMSE (HU)

SSIM

Artifacts

Water

GAN-MAR

p value

Artifacts

Water

GAN-MAR

p value

m4

       

6.87 (0.84–8.45)

4.22 (0.84–6.66)

4.84 (1.33–6.04)

0.13

0.84 (0.75–0.96)

0.84 (0.76–0.96)

0.91 (0.80–0.96)

0.09

m8

       

8.69 (1.06–10.64)

5.95 (1.05–8.46)

6.24 (1.65–7.34)

< 0.05

0.74 (0.66–0.95)

0.73 (0.65–0.95)

0.86 (0.73–0.92)

< 0.05

  1. Data are shown in median (minimum–maximum)
  2. RMSE root mean square error, SSIM structural similarity, PTV planning target volume