Methodological framework for radiomics applications in Hodgkin’s lymphoma

Sollini, Martina; Kirienko, Margarita; Cavinato, Lara; Ricci, Francesca; Biroli, Matteo; Ieva, Francesca; Calderoni, Letizia; Tabacchi, Elena; Nanni, Cristina; Zinzani, Pier Luigi; Fanti, Stefano; Guidetti, Anna; Alessi, Alessandra; Corradini, Paolo; Seregni, Ettore; Carlo-Stella, Carmelo; Chiti, Arturo

doi:10.1186/s41824-020-00078-8

EJNMMI Reports

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

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

		Fingerprint_1	Fingerprint_2	Fingerprint_3	Fingerprint_4	Fingerprint_5	Fingerprint_6
Dataset HL, type		Non-R/R	R/R	Non-R/R		R/R
Patients,n		26	50	8		19
Subset	Lesions, site	Nodal		Nodal	Nodal + extra-nodal	Nodal	Nodal + extra-nodal
Subset	Lesions,n	120	227	48	98	105	239
Features volume-related	Name	SUVpeak_{Sphere_1mL} TLG Volume_mL Volume_voxels Compacity Correlation_GLCM Entropy_log10_GLCM Entropy_log2_GLCM GLNU_GLRLM RLNU_GLRLM Coarseness_NGLDM Busyness_NGLDM LZHGE_GLZLM GLNU_GLZLM ZLNU_GLZLM	TLG Volume_mL Volume_voxels Compacity Correlation_GLCM GLNU_GLRLM RLNU_GLRLM Coarseness_NGLDM Busyness_NGLDM LZE_GLZLM GLNU_GLZLM ZLNU_GLZLM	SUVpeak_{Sphere_1mL} TLG Volume_mL Volume_voxels Compacity Entropy_log10_GLCM Entropy_log2_GLCM GLNU_GLRLM RLNU_GLRLM Coarseness_NGLDM Busyness _NGLDM GLNU_GLZLM ZLNU_GLZLM	TLG Volume_mL Volume_vx Compacity GLNU_GLRLM RLNU_GLRLM Busyness_NGLDM GLNU_GLZLM ZLNU_GLZLM	SUVpeak_{Sphere_1mL} TLG Volume_mL Volume_voxels Compacity Correlation_GLCM Entropy_log10_GLCM Entropy_log2_GLCM GLNU _GLRLM GLRLM_RLNU Coarseness_NGLDM Busyness_NGLDM GLNU_GLZLM ZLNU_GLZLM	TLG Volume_mL Volume_voxels Compacity Correlation_GLCM GLNU_GLRLM RLNU_GLRLM Busyness_NGLDM LZE_GLZLM LZHGE_GLZLM GLNU_GLZLM ZLNU_GLZLM
Features volume-related	Number	15	12	13	9	14	12
Features non-volume-related	Name	SUVstd Skewness_HISTO	SUVmin SUVmean SUVmax SUVQ1 SUVQ2 Kurtosis_HISTO ExcessKurtosis_HISTO Energy_HISTO LRLGE_GLRLM LRHGE_GLRLM	Skewness_HISTO LZE_GLZLM LZLGE_GLZLM	SUVmin SUVQ3 HGRE_GLRLM SRHGE_GLRLM HGZE_GLZLM SZHGE_GLZLM	Skewness_HISTO Energy_HISTO LZLGE_GLZLM	LRHGE_GLRLM SZHGE_GLZLM
Features non-volume-related	Number	2	10	3	6	3	2
PCA retained transformed features (mapping volume + non-volume data)		6 + 2	5 + 4	4 + 2	2 + 1	6 + 3	5 + 2

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

Back to article page