Endoscopic Ultrasound-guided Fine-needle Aspiration of Solid Pancreatic Lesions With Rapid Staining of Cytological Smears Followed by Whole Slide Scanning and Artificial Intelligence Diagnosis: A Prospective, Multicenter Study.

Recruiting

• Conditions: Pancreatic Disease

• Registration Number: NCT06824909
• Lead Sponsor: Ruijin Hospital

Brief Summary

The objective of this observational study is to investigate whether the self-developed whole slide scanning and artificial intelligence diagnostic system for pancreatic solid lesion puncture cytopathology (hereinafter referred to as the "Zhiying Shunxi" ROSE-AI diagnostic system) can promptly and accurately diagnose solid pancreatic lesions (SPLs). The main question it aims to answer is:

By utilizing optical imaging technology to capture RGB images of Diff-Quik stained smears from pancreatic punctures, can the development of artificial intelligence algorithms assist in differentiating solid pancreatic space-occupying diseases (such as pancreatic ductal adenocarcinoma, pancreatic neuroendocrine tumors, and non-neoplastic benign lesions)?

Researchers will compare the diagnoses of SPLs made by the ROSE-AI system with the actual pathological diagnoses of the SPLs themselves to determine whether the ROSE-AI system can effectively diagnose SPLs.

Detailed Description

Not available

Study Timeline

• Study Start: 2024-12-31
• Status Verified: 2025-01
• Study First Submitted: 2025-01-22
• Study First Submitted QC: 2025-02-08
• Last Update Submitted: 2025-02-08
• Study First Posted: 2025-02-13
• Last Update Posted: 2025-02-13
• Primary Completion: 2027-05-31
• Study Completion: 2027-06-30

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 1500

Inclusion Criteria

• A dated and signed informed consent form A commitment to abide by the research procedures and cooperate throughout the entire study Subjects aged 18 and above, regardless of gender Diagnosis or suspicion of a solid pancreatic space-occupying lesion based on imaging studies (B-mode ultrasound, CT, or MRI)

Exclusion Criteria

• Unable or refusing to sign the informed consent form Unable to suspend anticoagulation/antiplatelet therapy Pregnant or lactating Having a mental illness or other medical conditions that are unsuitable for undergoing FNA/B biopsy Presence of coagulation disorders (PLT < 50 × 10^3/μl, INR > 1.5) Pancreatic cystic lesions Non-diagnostic EUS-FNA/B specimens Having less than 8 microscopic fields of interest (ROI) in the digital pathology images of the entire Diff-Quik smear slide

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Accuracy	through study completion, an average of 2 years	Accuracy = (TP + TN) / (TP + FP + FN + TN)

Trial Locations

Locations (2)

Ruijin Hospital, Shanghai Jiaotong University School of Medicine; 🇨🇳 Shanghai, Shanghai, China

Department of Gastroenterolog, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine; 🇨🇳 Shanghai, Shanghai, China