Usefulness of Noncontrast MRI-Based Radiomics Combined Clinic Biomarkers in Stratification of Liver Fibrosis

Figure 2

Result of feature selection of boruta and least absolute shrinkage and selection operator (LASSO) for significant fibrosis (F ≥ 2). (a) Importance and attributes of significant fibrosis (F ≥ 2) in boruta. Red represents the rejected attribute and green is the confirmed attribute. Blue represents uncertain attributes. (b), (c) The bottom X-axis represents the value of log (λ), while the upper X-axis represents the number of nonzero parameters. A dotted vertical line was drawn at the optimal values by using the minimum criteria with (λ) 0.00416. (d) Coefficient of the most predictive features.

(a)

(b)

(c)

(d)