Skip to main content

Table 1 The SSIM between three methods and the original data set

From: Generalization of intensity distribution of medical images using GANs

MethodsSSIM (%)
Generalizer—CycleGAN73.7 ± 5.92
Generalizer—UNIT69.1 ± 4.84
Histogram matched dataset73.2 ± 8.23
  1. We calculate the SSIM for each image, average that, and get the standard deviation (std). We denote the result as mean ± std. The CycleGAN generalizer shows 0.737 of the SSIM (given in italic), higher than the SSIM of other methods