AI-powered multimodal imaging for diagnosing and predicting digestive disease outcomes
AI-Driven Multimodal Imaging Integration for Diagnosis and Prognostication of Digestive System Diseases
This project will test an AI tool that combines CT and MR enterography with endoscopy data to help diagnose and predict outcomes for people with Crohn's disease, ulcerative colitis, intestinal tuberculosis, or Behçet's disease.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 5000 (estimated) |
| Sex | All |
| Sponsor | First Affiliated Hospital, Sun Yat-Sen University Academic / other |
| Locations | 1 site (Shanghai) |
| Trial ID | NCT07087418 on ClinicalTrials.gov |
What this trial studies
This observational program combines retrospective and prospective imaging, endoscopic, and clinical data to build an AI system that integrates multimodal images (MRE and CTE) for diagnosis and prognostication of digestive diseases. Investigators retrospectively collected data from 21 centers across China to train and iteratively optimize the model, and will prospectively validate performance at two centers. The workflow includes real-world deployment in endoscopy suites to verify lesion localization using a virtual endoscopy model-assisted approach. Eligible cases require multimodal-confirmed diagnoses and at least one technically adequate CT or MR scan with a high-quality colonoscopy performed within one month of imaging.
Who should consider this trial
Good fit: Ideal candidates are people with clinically, endoscopically, and pathologically confirmed Crohn's disease, ulcerative colitis, intestinal tuberculosis, or Behçet's disease who have high-quality CT or MR enterography plus a high-quality colonoscopy within one month of imaging.
Not a fit: Patients without adequate imaging quality, poor bowel preparation or incomplete colonoscopy, or with conditions outside the targeted digestive diseases are unlikely to benefit from the model.
Why it matters
Potential benefit: If successful, the tool could enable more accurate, noninvasive diagnosis and better prediction of disease course, potentially reducing reliance on invasive procedures and speeding treatment decisions.
How similar studies have performed: Prior AI research in radiology and IBD imaging has shown promising results for lesion detection and diagnosis, but fully integrated multimodal imaging platforms with prospective, real-world validation remain relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patients with multimodal-confirmed diagnoses (clinical, imaging, endoscopic, and pathological) of: * Inflammatory bowel disease (IBD; Crohn's disease or ulcerative colitis) * Intestinal tuberculosis * Behçet's disease * Availability of ≥1 technically adequate CT or MR scan with high-quality colonoscopy performed within ±1 month of imaging. Exclusion Criteria: * ・Suboptimal imaging quality (e.g., low-dose artifacts, metal artifacts) * Inadequate bowel preparation for endoscopy * Incomplete examinations due to poor tolerance
Where this trial is running
Shanghai
- XploreMET v3.0 system — Shanghai, China (Recruiting)
Study contacts
- Principal investigator: Xuehua Li — Sun Yat-sen University First Affiliated Hospital Department of Radiology
- Study coordinator: Xuehua Li
- Email: lxueh@mail.sysu.edu.cn
- Phone: 13580364103
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.