Diffusion tensor imaging for characterizing tumor microstructure and improving diagnostic performance on breast MRI: a prospective observational study

Table 3 Multivariate LASSO models for discriminating between malignant and benign lesions

	Odds ratios*
	Clinical/DCE-MRI	DTI only	Clinical/DCE-MRI+ADC	Clinical/DCE-MRI+DTI
Clinical/DCE-MRI parameters
Age, per 1-SD increase	1.23		1.16	1.17
Post-menopausal	NS		NS	NS
MRI indication: known cancer	1.64		1.90	1.88
Dense breasts	0.45		0.64	0.61
BPE category, per 1-category increase	0.68		0.65	0.66
Lesion size^†, per 1-SD increase	1.96		1.95	1.85
Mass vs. NMLE/focus	2.30		2.01	1.89
Washout on delayed phase kinetics	2.92		2.52	2.43
BI-RADS 5 vs. 4	4.47		2.56	2.36
DTI parameters
Mean ADC, per 1-SD increase		0.41	0.44	0.41
Mean FA^†, per 1-SD increase		NS		0.88
Bootstrap-adjusted AUC	0.76	0.75	0.81	0.81
(95% CI)	(0.71, 0.83)	(0.68, 0.82)	(0.77, 0.88)	(0.78, 0.88)

*For continuous variables, ORs are scaled to show change per 1-SD increase in the corresponding variable
^†Variable was log-transformed prior to inclusion in the logistic regression model to reduce right-skewness

ISSN: 1465-542X