Fig. 3: Development and validation of the pathomics score.

A The graph shows the LASSO coefficient profiles of 427 pathomics features. B The graph shows the selection of the tuning parameter (λ) in the LASSO model via 10-fold cross-validation based on the minimum criteria. Binomial deviances from the LASSO regression cross-validation procedure were plotted as a function of log(λ); the y-axis indicates binomial deviances. The lower x-axis indicates log(λ), and the upper x-axis shows the mean number of predictors. The red dots indicate the mean deviance values for each model with a given lambda, and the vertical bars through the red dots show the upper and lower values of deviances. The dotted lines define the optimal values of lambda, where the model provides the best fit to the data. The optimal lambda value of 0.056 with log(λ) = −1.252 was selected. C A Lasso regression path plot illustrates the varying coefficients of diverse pathomic features as the regularization parameter changes. D The bar chart illustrates the Pathomics scores for different patients. It distinguishes between two groups, G1 and G2/3, using red and blue colors respectively. E The combined boxplot and scatter plot illustrates the comparison of pathomics scores between G1 and G2/3. F The KM plot shows the progression-free survival (PFS) between the low-risk and high-risk groups according to the cutoff value of the pathomics score, which was 0.24.