AI-guided diagnosis and management of pancreatic cysts using endoscopic ultrasound
A Multimodal Artificial Intelligence Model for Subtyping Diagnosis and Clinical Management of Pancreatic Cystic Lesions Based on Endoscopic Ultrasound and Clinical Information
This project will test an AI tool that uses EUS images plus CT/MRI and lab data to help doctors tell mucinous from non-mucinous pancreatic cysts and guide care for adults with pancreatic cystic lesions.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 500 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Huazhong University of Science and Technology Academic / other |
| Drugs / interventions | chemotherapy |
| Locations | 2 sites (Wuhan, Hubei and 1 other locations) |
| Trial ID | NCT07463872 on ClinicalTrials.gov |
What this trial studies
Researchers will retrospectively collect endoscopic ultrasound images, radiology (CT or MRI), laboratory results, and clinical records from patients with pancreatic cystic lesions seen at Tongji Hospital. They will train a multimodal artificial intelligence model called Cyst-AI to integrate imaging and clinical data to distinguish mucinous from non-mucinous cysts and to provide risk stratification. The model's outputs will be compared to pathological, clinical, and follow-up data to measure diagnostic and management concordance. The goal is to create a tool to assist endoscopists in decision-making about surveillance, further testing, or intervention.
Who should consider this trial
Good fit: Adults (18+) who had EUS showing pancreatic cystic or cystoid lesions and who have available EUS images, radiologic (CT/MRI) and laboratory data, without prior pancreatic surgery or prior chemo/radiation for pancreatic tumors are ideal candidates for inclusion.
Not a fit: People under 18, those lacking usable EUS images or key clinical/radiologic data, patients with prior pancreatic surgery or prior chemo/radiation, or those whose lesions are metastatic or have unclear final diagnoses would likely not benefit from or be eligible for this analysis.
Why it matters
Potential benefit: If successful, Cyst-AI could help doctors make more accurate diagnoses and better tailor monitoring or treatment, potentially reducing unnecessary procedures and missed malignant cysts.
How similar studies have performed: Previous AI work has improved image-based interpretation for pancreatic and other lesions, but combining EUS with multimodal clinical and radiologic data for cyst differentiation and management remains relatively novel and not yet widely validated.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion criteria: * Patients whose EUS results indicates pancreatic cystic or cystoid lesions; * Mucinous lesions: including mucinous cystic neoplasm (MCN), intraductal papillary mucinous neoplasm (IPMN); * Non-mucinous lesions: including pancreatic pseudocyst, serous cystic neoplasm (SCN), cystic neuroendocrine tumor (cNET). Exclusion criteria: * Patients whose age is less than 18 years old; * Patients who have undergone pancreatic surgery before the EUS examination; * Patients who have received chemotherapy and radiotherapy for pancreatic tumors before the EUS examination; * Pathological results indicate that pancreatic lesions are metastatic lesions from other sites; * Patients whose EUS images or reports are missing; * EUS image quality does not meet the requirements for review, such as blurry imaging or containing artifacts, biopsy needles, measuring scales, or other additional annotations that are not part of the original EUS image; * Patients whose final diagnosis is unclear.
Where this trial is running
Wuhan, Hubei and 1 other locations
- Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology — Wuhan, Hubei, China (Not_yet_recruiting)
- Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology — Wuhan, Hubei, China (Recruiting)
Study contacts
- Study coordinator: Bin Cheng
- Email: b.cheng@tjh.tjmu.edu.cn
- Phone: 86-13986097542
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.