Skip to main content
. 2023 Jan 6;33(6):4205–4213. doi: 10.1007/s00330-022-09367-1

Table 1.

Top ten reproducible radiomics features

Top 10 Feature name Feature class ICC
Axial vs. axial Energy First order 0.996
TotalEnergy First order 0.996
VoxelVolume Shape 0.996
MeshVolume Shape 0.996
RunLengthNonUniformity GLRLM 0.996
MajorAxisLength Shape 0.994
GrayLevelNonUniformity GLSZM 0.993
DependenceNonUniformity GLDM 0.993
SurfaceArea Shape 0.993
SizeZoneNonUniformity GLSZM 0.992
Axial vs. coronal RunLengthNonUniformity GLRLM 0.995
SurfaceArea Shape 0.995
VoxelVolume Shape 0.991
MeshVolume Shape 0.990
GrayLevelNonUniformity GLSZM 0.990
DependenceNonUniformity GLDM 0.986
SizeZoneNonUniformity GLSZM 0.985
MajorAxisLength Shape 0.983
Maximum3DDiameter Shape 0.978
MinorAxisLength Shape 0.972

Top ten reproducible fetal MRI lung radiomics features according to intra-class correlation coefficients between baseline and repeat axial, and between baseline axial and coronal acquisitions. GLCM Grey Level Co-occurrence Matrix, GLDM Grey Level Dependence Matrix, GLRLM Grey Level Run Length Matrix, GLSZM Grey Level Size Zone Matrix