Analysis of Bladder Cancer Staging Prediction Using Deep Residual Neural Network, Radiomics, and RNA-Seq from High-Definition CT Images

Figure 8

(a) In the univariate Cox regression analysis, the results demonstrated that 8 differentially expressed genes were associated with the prognosis of bladder cancer patients, (b, c) the lasso regression analysis in bladder cancer cohort, (d) the nomogram was constructed based on radiomics signature and gene signature, (e) the ROC curve shows the predictive value of radiomics signature and gene signature, and (f) the calibration curve shows the predictive value of the nomogram.