Skip to main content
EJNMMI Research
Fig. 2 | EJNMMI Research

Fig. 2

From: Value of 18F-FDG PET/CT-based radiomics model to distinguish the growth patterns of early invasive lung adenocarcinoma manifesting as ground-glass opacity nodules

Fig. 2

The best subset of radiomic features was extracted using the LASSO algorithm and 10-folds cross-validation. a The best feature was selected based on the AUC value. The black vertical line defines the best value of λ, and the model provides the best fit of the data. λ = 0.038 with log (λ) = − 3.2697 is selected as the optimal value. b The LASSO coefficient profiles of 38 radiomic features. The vertical line is the value selected by 10-fold cross-validation in a, where the best λ results in four nonzero coefficients of four selected features

Back to article page