Radiomics Analysis on Noncontrast CT for Distinguishing Hepatic Hemangioma (HH) and Hepatocellular Carcinoma (HCC)

Figure 3

Statistical selection process of radiomic features with LASSO regression. (a) Optimal λ value was calculated by LASSO model with 10-fold cross-validation. The binomial deviance curves were drawn versus log (λ). (b) Respective coefficient details were depicted. (c) Five features related to the optimal value were further reserved with respective coefficients to build the radiomics signature model.

(a)

(b)

(c)