Radiomic texture analysis based on neurite orientation dispersion and density imaging to differentiate glioblastoma from solitary brain metastasis

Table 1 Clinical characteristics of patients whose data were included in the training and test datasets

Characteristic	Training dataset (n = 143)						p value
Characteristic	GBM (n = 102)	SBM (n = 41)	p value	GBM (n = 44)	SBM (n = 17)	p value
Age, years
Mean ± SD	52.1 ± 12.0	56.5 ± 11.6	0.516	53.0 ± 9.7	55.4 ± 11.4	0.451	0.347
Sex, n			0.855			0.763	0.832
Male (%)	58 (56.8)	24 (58.5)		24 (54.5)	10 (58.8)
Female (%)	44 (43.2)	17 (41.5)		20 (45.5)	7 (41.2)
Variety of SBM, n
Lung, n
Adenocarcinoma (%)		28 (68.3)			13 (76.4)
Squamous cell carcinoma (%)		2 (4.9)
Neuroendocrine carcinoma (%)		3 (7.4)			1 (5.9)
Small cell lung carcinoma (%)		1 (2.4)
Poorly differentiated carcinoma (%)		1 (2.4)
Stomach, n
Adenocarcinoma (%)		1 (2.4)			0
Kidney, n
Clear cell carcinoma (%)		3 (7.4)			1 (5.9)
Uterus, n
Endometrial carcinoma (%)		1 (2.4)			1 (5.9)
Unknown site, n (%)		1 (2.4)			1 (5.9)

GBM, glioblastoma multiforme; SBM, single brain metastasis; SD, standard deviation

ISSN: 1471-2407