Longitudinal computed tomography-based delta-radiomics of visceral adipose tissue predicts infliximab secondary loss of response in Crohn’s disease patients

Figure 1 Flowchart of patient recruitment. CD: Crohn’s disease; IFX: Infliximab; CT: Computed tomography; SLR: Secondary loss of response.

Figure 2 The study design and workflow of radiomics analysis. IFX: Infliximab; CT: Computed tomography; VOI: Volume of interest; LASSO: Least absolute shrinkage and selection operator; ROC: Receiver operating characteristic curves.

Figure 3 Establishment of the combined model and predictive performance of models for predicting secondary loss of response. A: The developed nomogram of combined model scaled by the proportional regression coefficient of each predictor; B and C: Receiver operating characteristic curves of the clinical model, delta-radiomics model and combined model in the training cohort (B) and the validation cohort (C). VAT: Visceral adipose tissue; SAT: Subcutaneous adipose tissue; AUC: Area under the receiver operating characteristic curve. ¹VAT/SAT volume ratio prior to infliximab treatment.

Figure 4 Calibration and clinical utility of models for predicting secondary loss of response to infliximab in patients with Crohn’s disease. A and B: Calibration plots for clinical model, delta-radiomics model and combined model in the training cohort (A) and the validation cohort (B); C and D: Decision curve analysis for these three models in the training cohort (C) and the validation cohort (D).