Skip to main content
Insights into Imaging
Fig. 3 | Insights into Imaging

Fig. 3

From: Validity of a multiphase CT-based radiomics model in predicting the Leibovich risk groups for localized clear cell renal cell carcinoma: an exploratory study

Fig. 3

The process of triphasic radiomics features selection and radiomics signature construction by the least absolute shrinkage and selection operator (LASSO) regression algorithm. a Based on minimum criteria, we selected tuning parameters (λ) with 5-fold cross-validation. The binomial deviance was plotted versus log(λ). The upper x-axis indicates the average number of radiomics features. The lower x-axis indicates the log(λ) value. The optimal λ value of 0.0578, with log(λ) = − 2.78 was selected. b A coefficient profile plot was generated versus the selected log λ value. c The weighting coefficients of each feature. U, unenhanced phase; A, arterial phase; V, portal-venous phase

Back to article page