Retrospective Study
Copyright ©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Jun 7, 2025; 31(21): 105895
Published online Jun 7, 2025. doi: 10.3748/wjg.v31.i21.105895
Longitudinal computed tomography-based delta-radiomics of visceral adipose tissue predicts infliximab secondary loss of response in Crohn’s disease patients
Xi Li, Fu-Long Song, Hai-Feng He, Shu-Min Zeng, Zhi-Chao Feng, Peng-Fei Rong
Xi Li, Fu-Long Song, Shu-Min Zeng, Zhi-Chao Feng, Peng-Fei Rong, Department of Radiology, The Third Xiangya Hospital, Central South University, Changsha 410013, Hunan Province, China
Hai-Feng He, Department of Radiology, Hunan Cancer Hospital/The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha 410013, Hunan Province, China
Zhi-Chao Feng, Department of Radiology, Department of Medical Imaging, SJTU-Ruijin-UIH Institute for Medical Imaging Technology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
Zhi-Chao Feng, Department of Medical Imaging, Yueyang Central Hospital, Yueyang 414020, Hunan Province, China
Co-first authors: Xi Li and Fu-Long Song.
Co-corresponding authors: Zhi-Chao Feng and Peng-Fei Rong.
Author contributions: Li X, Song FL, He HF, and Zeng SM were tasked with data collection. They gathered information from various clinical sources, carefully extracted key clinical variables such as patient age, disease stage, etc., and assessed images using professional tools. Li X and Song FL conceptualized and designed the research, choosing suitable research methods and setting the direction. They analyzed data using statistical methods and segmented medical images accurately. They also took the lead in writing the manuscript and are co-first authors. Feng ZC and Rong PF participated in the overall study design and provided valuable suggestions. They supervised data analysis to ensure accuracy and revised the manuscript thoroughly. As co-corresponding authors, they coordinated the whole process. He HF helped with the literature review and looked for relevant studies, while Zeng SM validated the data. They are responsible for patient screening, enrollment, clinical data and imaging index collection. All authors read and approved the final manuscript, ensuring the quality of this research work.
Supported by the National Natural Science Foundation of China, No. 82372072 and No. 82071986.
Institutional review board statement: This retrospective study was reviewed and approved by the Institutional Ethics Review Board of the Third Xiangya Hospital of Central South University, No. Kuai20018.
Informed consent statement: The need for patient consent was waived due to the retrospective nature of the study.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Data sharing statement: Data are available upon reasonable request and pursuant to appropriate agreements from the corresponding author at rongpengfei66@163.com.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Peng-Fei Rong, Department of Radiology, The Third Xiangya Hospital, Central South University, No. 138 Tongzipo Road, Changsha 410013, Hunan Province, China. rongpengfei66@163.com
Received: February 10, 2025
Revised: April 5, 2025
Accepted: May 21, 2025
Published online: June 7, 2025
Processing time: 116 Days and 19.3 Hours
Abstract
BACKGROUND

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.

AIM

To develop a longitudinal computed tomography (CT)-based delta-radiomics model of VAT for predicting secondary loss of response (SLR) in patients with CD.

METHODS

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.

RESULTS

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.

CONCLUSION

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.

Keywords: Crohn’s disease; Computed tomography enterography; Infliximab; Delta-radiomics; Secondary loss of response

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.