AI-enhanced MRE to detect bowel 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

This project will test whether an AI program applied to magnetic resonance enterography (MRE) scans can accurately identify and characterize bowel wall fibrosis in adults with Crohn's disease who are scheduled for bowel resection.

Quick facts

• Study type: Observational
• Enrollment: 234 (estimated)
• Ages: 18 Years to 75 Years
• Sex: All
• Sponsor: First Affiliated Hospital, Sun Yat-Sen University (other)
• Locations: 5 sites (Guangzhou, Guangdong and 4 other locations)
• Trial ID: NCT06858553 on ClinicalTrials.gov

What this trial studies

This is a prospective multicenter observational effort enrolling about 234 adults with Crohn's disease who require ileal or colonic resection for strictures. Preoperative MRE scans will be paired with histological analysis of the resected bowel to train and validate a deep learning model that can detect and grade full-thickness intestinal fibrosis. Participating centers will follow a centralized quality assurance plan, including routine monitoring, double verification of data and specimens, and periodic audits. The project requires clear target-segment boundaries on MRE to enable semi-automatic or automatic segmentation for model development.

Who should consider this trial

Good fit: Adults (over 18) with a confirmed diagnosis of Crohn's disease who are planning bowel resection for an ileal or colonic stricture and who can undergo MRI with clear MRE images suitable for segmentation are ideal candidates.

Not a fit: Patients who cannot have MRI, whose MRE scans are poor quality or contain artifacts, who have anastomotic strictures, or whose lesions are complicated by other diseases are unlikely to benefit from this project.

Why it matters

Potential benefit: If successful, the AI-enhanced MRE tool could allow noninvasive, more accurate detection of full-thickness bowel fibrosis to help guide medical versus surgical treatment decisions.

How similar studies have performed: Prior radiomics and deep learning work on CT and other imaging modalities has shown promising diagnostic capability, but prospective multicenter development of AI models specifically using MRE matched to histology is relatively novel.

Eligibility criteria

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

Where this trial is running

Guangzhou, Guangdong and 4 other locations

• The First Affiliated Hospital,Sun Yat-sen University — Guangzhou, Guangdong, China (RECRUITING)
• Sixth Affiliated Hospital of Sun Yat-sen University — Guangzhou, Guangdong, China (NOT_YET_RECRUITING)
• Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University — Nanjing, Jiangsu, China (NOT_YET_RECRUITING)
• Ruijin Hospital, Shanghai Jiaotong University School of Medicine — Huangpu, Shanghai Municipality, China (NOT_YET_RECRUITING)
• Sir Run Run Shaw Hospital, Zhejiang University School of Medicine — Hangzhou, Zhejiang, China (RECRUITING)

Study contacts

• Study coordinator: Minhu Chen, Professor

Conditions: Crohn Disease, MRE, Artificial Intelligence, Fibrosis