Table 4 Fingerprints construction for inter-patient similarity analysis
From: Methodological framework for radiomics applications in Hodgkin’s lymphoma
Fingerprint_One | Fingerprint_All | ||
|---|---|---|---|
Dataset HL, type | Non-R/R + R/R | Non-R/R + R/R | |
Patients,n | 85 | 85 | |
Subset | Lesions, site | Nodal or extra-nodal | Nodal + extra-nodal |
Lesions,n | 85 | 543 | |
Features volume-related | Name | TLG Volume_mL Volume_vx Compacity GLNUGLRLM RLNUGLRLM GLNUGLZLM ZLNUGLZLM | TLG Volume_mL Volume_vx Compacity CorrelationGLCM GLNUGLRLM RLNUGLRLM Coarseness NGLDM Busyness NGLDM LZEGLZLM LZHGEGLZLM GLNUGLZLM ZLNUGLZLM ZPGLZLM |
Number | 8 | 14 | |
Features non-volume-related | Name | SUVmean SUVQ2 SUVQ3 Entropy_log10 HISTO Entropy_log2 HISTO EnergyHISTO LGREGLRLM HGREGLRLM SRHGEGLRLM LRLGEGLRLM LRHGEGLRLM HGZE LZLM | SUVQ3 Entropy_log10 HISTO Entropy_log2 HISTO HGREGLRLM SRHGEGLRLM LRHGEGLRLM HGZEGLZLM |
Number | 12 | 7 | |
PCA retained transformed features (mapping volume + non-volume data) | 2 + 2 | 7 + 2 | |