Fig. 3From: Feasibility and effectiveness of automatic deep learning network and radiomics models for differentiating tumor stroma ratio in pancreatic ductal adenocarcinomaThe selection process of the LASSO model. a Lasso coefficient profile plot with different log (λ) was shown. The vertical dashed lines represent 10 radiomics features with nonzero coefficients selected with the optimal λ value. b The LASSO model’s tuning parameter (λ) selection via minimum criterion. The vertical lines indicate the optimal value of the LASSO tuning parameter (λ). c Feature’s weights of selected 10 features. d Heatmap of 10 featuresBack to article page