AI-Assisted MRE for Intestinal Fibrosis in Crohn's Disease

A Prospective, Multi-center Study to Characterize Intestinal Fibrosis in Patients With Crohn's Disease (CD) Using MR Enterography (MRE)-Based Artificial Intelligence

Intestinal fibrotic strictures represent a severe complication of Crohn's disease (CD), affecting over half of the patients. Despite the continuous emergence of novel medications, effective treatment options remain scarce. Endoscopy fails to identify the full-thickness fibrosis of the bowel wall, and standardized assessment for cross-sectional imaging has yet to be established. Previous studies have demonstrated that radiomics models based on computed tomography and deep learning models exhibit commendable diagnostic capability. Thus, this project seeks to conduct a prospective multicenter study, with plans to recruit 234 CD patients requiring bowel resection from five medical centers. The aim is to develop and validate a deep learning model based on magnetic resonance enterography (MRE) to accurately characterize intestinal fibrosis.

Study Overview

• Status: Recruiting
• Conditions: Crohn Disease (CD)

Detailed Description

Quality Assurance Plan The registry implements a comprehensive quality assurance (QA) plan to validate data and maintain protocol adherence. This includes routine site monitoring, regular audits, and verification of data consistency. Sites participating in the registry are periodically reviewed for compliance with the established operational standards.

Data Entry and Summary Process Management will enforce access regulations to ensure only authorized personnel can enter or query data. Patient information meeting inclusion criteria will be entered into a Tencent form from the hospital's medical record system. Research assistants will supplement this form with details about intestinal surgical specimens, including condition, quantity, and storage, and summarize all specimens. Researchers will summarize the MRE imaging data for the relevant patients. No one may delete, alter, copy, print, or output confidential data without management's consent.

Verification System During patient enrollment, information collection, and specimen collection, two or more research assistants or researchers will confirm the process. Relevant information will be verified again during specimen collection, labeling, and storage. In the analysis phase, researchers will recheck the accuracy of imaging, patient information, and specimens. Management will conduct a random audit every three months to verify patient inclusion criteria and confirm specimen information accuracy.

Data Dictionary A comprehensive data dictionary is used to define each variable collected within the registry. It includes the source of the variable, coding standards and any relevant normal ranges for clinical measures. This data dictionary serves as a reference to ensure uniformity in data collection and analysis.

Standard Operating Procedures (SOPs) The registry follows established Standard Operating Procedures (SOPs) for various registry functions, including patient recruitment, data collection, management, and analysis. SOPs also cover reporting procedures for adverse events, including guidelines for data reporting and event classification. Change management processes are in place to address any amendments or updates to registry protocols.

Sample Size Assessment A statistical sample size calculation has been performed to ensure that the registry is adequately powered to detect meaningful differences or effects. This calculation takes into account the expected incidence of the event of interest, anticipated variability, and the desired statistical power. The required number of participants or participant years is specified based on the primary and secondary objectives of the study.

Plan for Missing Data The registry has a clear policy for handling missing data, including cases where data may be unavailable, uninterpretable, or missing due to inconsistencies (e.g., out-of-range results). A specific protocol is followed for imputing missing values or excluding incomplete data from analysis, ensuring the final dataset remains reliable and valid for statistical analysis.

Statistical Analysis Methods Automatic recognition and segmentation of intestinal lesions in images, based on multi-parametric MRI data and artificial intelligence models, are used to evaluate intestinal fibrosis and assist in clinical decision-making. Specifically, the process includes: performing VOI annotation to generate 3D VOI; normalizing and resampling MRE images, cropping voxel intensity and applying min-max normalization; decomposing each 3D MRE lesion image into patches, and applying 5-fold data augmentation as input to the network; developing a deep learning segmentation algorithm using the nnU-Net model for automatic recognition of intestinal lesion images, with performance evaluated using the Dice similarity coefficient; constructing a ResNet model to accurately assess different degrees of intestinal fibrosis, with output as a predicted probability between 0 and 1; collecting multi-parametric MRI data prior to model construction and extracting features not affected by intestinal inflammation; excluding relevant features during model development, retaining only those reflecting intestinal fibrosis; after model construction, grouping patients based on inflammation severity and re-evaluating the AI model's recognition capability. Through these steps and the integration of multi-omics data, molecular subtyping and related prognostic analysis of patients are achieved to assist in clinical treatment decision-making.

• Study Type: Observational
• Enrollment (Estimated): 234

Contacts and Locations

• Study Contact: Name: Minhu Chen, Professor; Phone Number: +86 13802957089; Email: chenminhu@mail.sysu.edu.cn
• Study Contact Backup: Name: Ren Mao, Professor; Phone Number: +86 13544476809; Email: maor5@mail.sysu.edu.cn

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 510080
      • Recruiting
      • The First Affiliated Hospital,Sun Yat-sen University
      • Contact: Minhu Chen; Phone Number: +86 13802957089; Email: chenminhu@mail.sysu.edu.cn
      • Sub-Investigator: Pingxin Zhang, Dr.
    • Guangzhou, Guangdong, China
      • Not yet recruiting
      • Sixth Affiliated Hospital of Sun Yat-sen University
      • Contact: Xiang Gao, Professor; Phone Number: +86 13502405878; Email: gxiang@sysu.edu.cn
  • Jiangsu
    • Nanjing, Jiangsu, China
      • Not yet recruiting
      • Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University
      • Contact: Yi Li, Professor; Phone Number: +86 13851843735; Email: liyi1860@126.com
  • Shanghai
    • Huangpu, Shanghai, China
      • Not yet recruiting
      • Ruijin Hospital, Shanghai Jiaotong University School of Medicine
      • Contact: Duowu Zou, Professor; Phone Number: +86 13901617608; Email: zdwrjxh66@sjtu.edu.cn
  • Zhejiang
    • Hangzhou, Zhejiang, China
      • Recruiting
      • Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
      • Contact: Qian Cao, Professor; Phone Number: +86 13588706896; Email: caoq@srrsh.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

The study population consists of patients from five tertiary-level IBD treatment centers located in different regions of China

Description

Inclusion Criteria:

1. Patients Over 18 years old with a confirmed diagnosis of CD based on the criteria of ECCO guideline.
2. Planning to receive a bowel resection due to stricture in ileum or colon, and availability of histological specimens of resected intestinal walls matched with MRE are expected to be available.
3. Clear boundaries of the target bowel tract enable accurate semi-automatic or fully automatic intestinal segmentation

Exclusion Criteria:

1. Cannot undergo MRI examination
2. Difficult to obtain suitable tissue after surgery
3. MRE imaging is of poor quality or contains artifacts
4. The target bowel is located at the anastomosis (ie, anastomotic stricture)
5. Intestinal lesions concurrent with other diseases

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
training group; This group of patients is used in the training phase of the predictive model to fit an appropriate model.
validation group; This group of patients is used to validate the trained model to determine whether the model has broad applicability.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
histologic inflammation score	Histologic evaluation of intestinal surgical specimens from enrolled patients was performed using hematoxylin and eosin (H&E) staining for the histologic inflammation score. The scoring system is graded on a 0-3 scale, with higher scores indicating a greater degree of inflammatory infiltration.	1 week after surgery
histologic fibrosis score	Histologic evaluation of intestinal surgical specimens from enrolled patients was performed using Masson's trichrome staining for the histologic fibrosis score. The scoring system is graded on a 0-3 scale, with higher scores indicating a greater degree of fibrosis severity.	1 week after surgery
Magnetization Transfer Ratio	All enrolled patients underwent Magnetic Resonance Enterography examinations four weeks prior to surgery. Magnetization Transfer Ratio (MTR) is calculated as MTR = [1 - (Msat / M0)] × 100, where Msat represents the signal intensity with the magnetization transfer pulse applied, and M0 represents the signal intensity without the MT pulse. To minimize individual variability, MTR is normalized using the skeletal muscle MTR, making it a reliable indicator for assessing intestinal fibrosis.	4 weeks before surgery
Apparent Diffusion Coefficient	All enrolled patients underwent Magnetic Resonance Enterography examinations four weeks prior to surgery. The Apparent Diffusion Coefficient (ADC) is derived from diffusion-weighted imaging (DWI) and measures the movement of water molecules in tissues, indirectly reflecting inflammation and fibrosis severity. Lower ADC values suggest restricted diffusion, which is associated with fibrosis, allowing differentiation between fibrotic and non-fibrotic bowel walls.	4 weeks before surgery
Percentage of Enhancement Gain	All enrolled patients underwent Magnetic Resonance Enterography examinations four weeks prior to surgery. The Percentage of Enhancement Gain is calculated using % Gain = [(WSI_7min - WSI_70s) / WSI_70s] × 100, where WSI_70s and WSI_7min are the bowel wall signal intensities at 70 seconds and 7 minutes post-contrast injection, respectively. This parameter evaluates hemodynamic changes in the bowel wall, reflecting tissue perfusion characteristics related to inflammation and fibrosis.	4 weeks before surgery

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
IBD Montreal classification	The Montreal classification of Crohn's disease includes three main categories: age, disease location, and disease behavior. Age (A) is classified as ≤16 years (A1), 17-40 years (A2), and ≥40 years (A3). Disease location (L) is categorized into terminal ileum (L1), colon (L2), ileocolon (L3), and upper gastrointestinal tract (L4). Disease behavior (B) is classified as non-stricturing, non-penetrating (B1), stricturing (B2), and penetrating (B3). Additionally, perianal fistulizing disease (P) can occur in association with any of the disease behavior subtypes.	2 weeks before surgery
Crohn's Disease Activity Index	The Crohn's Disease Activity Index (CDAI) ranges from a minimum of 0 with no fixed maximum value. When using CDAI to assess disease status, different score thresholds are commonly applied: CDAI <150 indicates remission, while CDAI ≥150 indicates active disease. Within the active disease category, 150-220 is classified as mild activity, 221-450 as moderate activity, and >450 as severe activity.	2 weeks before surgery
complete blood count	Calculate the quantity and percentage of each category of serum cells.	2 weeks before surgery
C-reactive protein	Measure the concentration of serum C-reactive protein, expressed in mg/L.	2 weeks before surgery
procalcitonin	Measure the concentration of serum procalcitonin, expressed in ng/mL.	2 weeks before surgery
erythrocyte sedimentation rate	Measure the erythrocyte sedimentation rate of the blood，expressed in mm/h.	2 weeks before surgery
serum albumin	Measure the level of serum albumin, expressed in g/L.	2 weeks before surgery

Collaborators and Investigators

• Sponsor: Minhu Chen
• Collaborators: Ruijin Hospital; Sixth Affiliated Hospital, Sun Yat-sen University; Sir Run Run Shaw Hospital; Jinling Hospital, China; MSD R&D (China) Co., Ltd.
• Investigators: Study Chair: Minhu Chen, First Affiliated Hospital, Sun Yat-Sen University

Publications and helpful links

General Publications

• Zhang MC, Li XH, Huang SY, Mao R, Fang ZN, Cao QH, Zhang ZW, Yan X, Chen MH, Li ZP, Sun CH, Feng ST. IVIM with fractional perfusion as a novel biomarker for detecting and grading intestinal fibrosis in Crohn's disease. Eur Radiol. 2019 Jun;29(6):3069-3078. doi: 10.1007/s00330-018-5848-6. Epub 2018 Dec 13.
• Li XH, Feng ST, Cao QH, Coffey JC, Baker ME, Huang L, Fang ZN, Qiu Y, Lu BL, Chen ZH, Li Y, Bettenworth D, Iacucci M, Sun CH, Ghosh S, Rieder F, Chen MH, Li ZP, Mao R. Degree of Creeping Fat Assessed by Computed Tomography Enterography is Associated with Intestinal Fibrotic Stricture in Patients with Crohn's Disease: A Potentially Novel Mesenteric Creeping Fat Index. J Crohns Colitis. 2021 Jul 5;15(7):1161-1173. doi: 10.1093/ecco-jcc/jjab005.
• Li X, Zhang N, Hu C, Lin Y, Li J, Li Z, Cui E, Shi L, Zhuang X, Li J, Lu J, Wang Y, Liu R, Yuan C, Lin H, He J, Ke D, Tang S, Zou Y, He B, Sun C, Chen M, Huang B, Mao R, Feng ST. CT-based radiomics signature of visceral adipose tissue for prediction of disease progression in patients with Crohn's disease: A multicentre cohort study. EClinicalMedicine. 2022 Dec 30;56:101805. doi: 10.1016/j.eclinm.2022.101805. eCollection 2023 Feb.
• Li Z, Chen Z, Zhang R, et, al. Eur J Nucl Med Mol Imaging. 2024 Feb 15.
• Du JF, Lu BL, Huang SY, Mao R, Zhang ZW, Cao QH, Chen ZH, Li SY, Qin QL, Sun CH, Feng ST, Li ZP, Huang L, Li XH. A novel identification system combining diffusion kurtosis imaging with conventional magnetic resonance imaging to assess intestinal strictures in patients with Crohn's disease. Abdom Radiol (NY). 2021 Mar;46(3):936-947. doi: 10.1007/s00261-020-02765-3. Epub 2020 Sep 22.
• Huang SY, Li XH, Huang L, Sun CH, Fang ZN, Zhang MC, Lin JJ, Jiang MJ, Mao R, Li ZP, Zhang Z, Feng ST. T2* Mapping to characterize intestinal fibrosis in crohn's disease. J Magn Reson Imaging. 2018 Apr 17. doi: 10.1002/jmri.26022. Online ahead of print.
• Li Z, Lu B, Lin J, He S, Huang L, Wang Y, Meng J, Li Z, Feng ST, Lin S, Mao R, Li XH. A Type I Collagen-Targeted MR Imaging Probe for Staging Fibrosis in Crohn's Disease. Front Mol Biosci. 2021 Nov 11;8:762355. doi: 10.3389/fmolb.2021.762355. eCollection 2021.
• Li XH, Mao R, Huang SY, Fang ZN, Lu BL, Lin JJ, Xiong SS, Chen MH, Li ZP, Sun CH, Feng ST. Ability of DWI to characterize bowel fibrosis depends on the degree of bowel inflammation. Eur Radiol. 2019 May;29(5):2465-2473. doi: 10.1007/s00330-018-5860-x. Epub 2019 Jan 11.
• Chen YJ, Mao R, Li XH, Cao QH, Chen ZH, Liu BX, Chen SL, Chen BL, He Y, Zeng ZR, Ben-Horin S, Rimola J, Rieder F, Xie XY, Chen MH. Real-Time Shear Wave Ultrasound Elastography Differentiates Fibrotic from Inflammatory Strictures in Patients with Crohn's Disease. Inflamm Bowel Dis. 2018 Sep 15;24(10):2183-2190. doi: 10.1093/ibd/izy115.
• Li XH, Mao R, Huang SY, Sun CH, Cao QH, Fang ZN, Zhang ZW, Huang L, Lin JJ, Chen YJ, Rimola J, Rieder F, Chen MH, Feng ST, Li ZP. Characterization of Degree of Intestinal Fibrosis in Patients with Crohn Disease by Using Magnetization Transfer MR Imaging. Radiology. 2018 May;287(2):494-503. doi: 10.1148/radiol.2017171221. Epub 2018 Jan 19.
• Meng J, Luo Z, Chen Z, Zhou J, Chen Z, Lu B, Zhang M, Wang Y, Yuan C, Shen X, Huang Q, Zhang Z, Ye Z, Cao Q, Zhou Z, Xu Y, Mao R, Chen M, Sun C, Li Z, Feng ST, Meng X, Huang B, Li X. Intestinal fibrosis classification in patients with Crohn's disease using CT enterography-based deep learning: comparisons with radiomics and radiologists. Eur Radiol. 2022 Dec;32(12):8692-8705. doi: 10.1007/s00330-022-08842-z. Epub 2022 May 26.
• Li X, Liang D, Meng J, Zhou J, Chen Z, Huang S, Lu B, Qiu Y, Baker ME, Ye Z, Cao Q, Wang M, Yuan C, Chen Z, Feng S, Zhang Y, Iacucci M, Ghosh S, Rieder F, Sun C, Chen M, Li Z, Mao R, Huang B, Feng ST. Development and Validation of a Novel Computed-Tomography Enterography Radiomic Approach for Characterization of Intestinal Fibrosis in Crohn's Disease. Gastroenterology. 2021 Jun;160(7):2303-2316.e11. doi: 10.1053/j.gastro.2021.02.027. Epub 2021 Feb 17.

Study record dates

Study Major Dates

• Study Start (Actual): June 3, 2025
• Primary Completion (Estimated): February 28, 2027
• Study Completion (Estimated): February 28, 2027

Study Registration Dates

• First Submitted: February 19, 2025
• First Submitted That Met QC Criteria: February 27, 2025
• First Posted (Actual): March 5, 2025

Study Record Updates

• Last Update Posted (Actual): August 5, 2025
• Last Update Submitted That Met QC Criteria: August 4, 2025
• Last Verified: August 1, 2025

More Information

Terms related to this study

• Keywords: Fibrosis; Artificial Intelligence; Crohn Disease; MRE
• Additional Relevant MeSH Terms: Pathologic Processes; Intestinal Diseases; Digestive System Diseases; Gastrointestinal Diseases; Gastroenteritis; Inflammatory Bowel Diseases; Fibrosis; Crohn Disease
• Other Study ID Numbers: No.840[2024]; MISP-102507 (Other Grant/Funding Number: MSD R&D(CHINA)CO.,LTD)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

IPD Plan Description

In this study, we do not intend to publicly release raw patient data for the following reasons:

1. Patient Privacy Protection: Raw data may include sensitive personal information, such as names and medical history. Public release could expose this information, violating patient privacy rights and privacy regulations.
2. Data Security: The raw data includes medical images and clinical information, which could be misused if released. Access will be restricted to the research team to ensure data security.
3. Ethical Considerations: Informed consent was obtained from patients with clear terms regarding data usage. They did not consent to public release of raw data, and doing so could breach the original agreement.
4. De-identification: While de-identified data may be used, raw data that could identify patients will not be released to protect their privacy.
5. Prevention of Data Misuse: Releasing raw data could lead to misuse by unauthorized parties.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No