Skip to main content
. Author manuscript; available in PMC: 2022 Oct 15.
Published in final edited form as: Neuroimage. 2022 Jul 13;260:119474. doi: 10.1016/j.neuroimage.2022.119474

Table 1.

Uniform hyperparameter sampling ranges used for synthesizing a training image from a source segmentation map. The specific values were chosen by visual inspection of the generated images to produce a landscape of image contrasts, anatomies, and acquisition characteristics that far exceed the realistic range of medical images. We sample fields with isotropic voxels of the indicated side length, where SD abbreviates standard deviation.

Synthesis hyperparameter Uniform sampling range
Affine translation 0–50 mm
Affine rotation 0–45°
Affine scaling 80–120%
Deformation voxel length 8–16 mm
Deformation SD 0–3 mm
Label intensity mean 0–1
Label intensity SD 0–0.1
Bias field voxel length 4–64 mm
Bias field SD 0–0.5
Exponentiation parameter γ −0.25–0.25
FOV cropping (any axis) 0–50 mm
Down-sample factor r (any axis) 1–5