Published online Jun 7, 2025. doi: 10.3748/wjg.v31.i21.105895
Revised: April 5, 2025
Accepted: May 21, 2025
Published online: June 7, 2025
Processing time: 116 Days and 19.3 Hours
Visceral adipose tissue (VAT) plays a role in the pathogenesis of Crohn's disease (CD) and is associated with treatment outcomes following infliximab (IFX) therapy. We developed and validated the first delta-radiomics model to quantify VAT heterogeneity as a predictive biomarker for IFX response in patients with CD.
To develop a longitudinal computed tomography (CT)-based delta-radiomics model of VAT for predicting secondary loss of response (SLR) in patients with CD.
This retrospective study included 161 patients with CD who achieved clinical remission following IFX induction therapy between 2015 and 2023. All patients underwent CT enterography before IFX initiation and after completing induction therapy. VAT volume was delineated by two radiologists in consensus. Radiomics features were extracted from pre-treatment and post-induction CT images, and delta-radiomics features were calculated as follows: Delta features = Feature-post - Feature-pre. A radiomics model was constructed using logistic regression. Model performance was assessed using discrimination, calibration, and decision curve analyses.
Nine significant delta-radiomics features were used to develop the delta-radiomics model, yielding an area under the receiver operating characteristic curve (AUC) of 0.816 (95%CI: 0.737-0.896) in the training cohort and 0.750 (95%CI: 0.605-0.895) in the validation cohort. Multivariable logistic regression identified platelet count, Montreal behavior classification, and the VAT/subcutaneous adipose tissue volume ratio prior to treatment as independent risk factors for SLR. The combined model integrating clinical predictors and delta-radiomics features achieved superior predictive performance, with an AUC of 0.853 (95%CI: 0.786-0.921) in the training cohort and 0.812 (95%CI: 0.677-0.948) in the validation cohort.
We developed a predictive model based on longitudinal changes in VAT, demonstrating significant potential for identifying patients with CD at high risk of SLR to IFX therapy.
Core Tip: The treatment response to infliximab in patients with Crohn's disease (CD) is heterogeneous, with approximately 23%-46% of those achieving clinical remission after induction therapy experiencing secondary loss of response (SLR) within the first year. This significantly increases the risk of serious adverse outcomes. In this study, we developed a delta-radiomics model based on longitudinal changes in visceral adipose tissue assessed through computed tomography enterography. This model further integrates clinical and imaging biomarkers to identify patients with CD at high risk of SLR. This non-invasive approach holds promise as a valuable tool for optimizing personalized treatment regimens and guiding monitoring strategies.