Skip to main content

Table 2 Fingerprints’ construction for intra-patient lesion similarity analysis

From: Methodological framework for radiomics applications in Hodgkin’s lymphoma

 Fingerprint_1Fingerprint_2Fingerprint_3Fingerprint_4Fingerprint_5Fingerprint_6
Dataset HL, typeNon-R/RR/RNon-R/RR/R
Patients,n2650819
SubsetLesions, siteNodalNodalNodal + extra-nodalNodalNodal + extra-nodal
Lesions,n1202274898105239
Features volume-relatedNameSUVpeakSphere_1mL
TLG
Volume_mL
Volume_voxels
Compacity
CorrelationGLCM
Entropy_log10GLCM
Entropy_log2GLCM
GLNUGLRLM
RLNUGLRLM
CoarsenessNGLDM
BusynessNGLDM
LZHGEGLZLM
GLNUGLZLM
ZLNUGLZLM
TLG
Volume_mL
Volume_voxels
Compacity
CorrelationGLCM
GLNUGLRLM
RLNUGLRLM
CoarsenessNGLDM
BusynessNGLDM
LZEGLZLM
GLNUGLZLM
ZLNUGLZLM
SUVpeakSphere_1mL
TLG
Volume_mL
Volume_voxels
Compacity
Entropy_log10GLCM
Entropy_log2GLCM
GLNUGLRLM
RLNUGLRLM
CoarsenessNGLDM
Busyness NGLDM
GLNUGLZLM
ZLNUGLZLM
TLG
Volume_mL
Volume_vx
Compacity
GLNUGLRLM
RLNUGLRLM
BusynessNGLDM
GLNUGLZLM
ZLNUGLZLM
SUVpeakSphere_1mL
TLG
Volume_mL
Volume_voxels
Compacity
CorrelationGLCM
Entropy_log10GLCM
Entropy_log2GLCM
GLNU GLRLM
GLRLM_RLNU
CoarsenessNGLDM
BusynessNGLDM
GLNUGLZLM
ZLNUGLZLM
TLG
Volume_mL
Volume_voxels
Compacity
CorrelationGLCM
GLNUGLRLM
RLNUGLRLM
BusynessNGLDM
LZEGLZLM
LZHGEGLZLM
GLNUGLZLM
ZLNUGLZLM
Number15121391412
Features non-volume-relatedNameSUVstd
SkewnessHISTO
SUVmin
SUVmean
SUVmax
SUVQ1
SUVQ2
KurtosisHISTO
ExcessKurtosisHISTO
EnergyHISTO
LRLGEGLRLM
LRHGEGLRLM
SkewnessHISTO
LZEGLZLM
LZLGEGLZLM
SUVmin
SUVQ3
HGREGLRLM
SRHGEGLRLM
HGZEGLZLM
SZHGEGLZLM
SkewnessHISTO
EnergyHISTO
LZLGEGLZLM
LRHGEGLRLM
SZHGEGLZLM
Number2103632
PCA retained transformed features (mapping volume + non-volume data)6 + 25 + 44 + 22 + 16 + 35 + 2
  1. HL Hodgkin’s lymphoma, n number, non-R/R non-relapsing/refractory, PCA principal component analysis, R/R relapsing/refractory. For the full spelling of the feature and matrixes names, please refer to the supplementary material