An Artificial Intelligence System for Multimodal, Multi-class Diagnosing Solid Pancreatic Lesions Based on Endoscopic Ultrasound

An Artificial Intelligence System for Multimodal, Multi-class Diagnosing Solid Pancreatic Lesions Based on Endoscopic Ultrasound

The aim of this study is to validate an artificial intelligence system named iEUS-SPL(intelligent endoscopic ultrasound system-solid pancreatic lesion) for detecting and multimodal, multi-class diagnosing solid pancreatic lesions during endoscopic ultrasound(EUS) examination.

This is an observational study with a prospective, cohort design. We have developed an artificial intelligence system named iEUS-SPL for multimodal, multi-class diagnosing solid pancreatic lesions using endoscopic ultrasound images, endoscopic ultrasound features, clinical data and imaging features from retrospectively collected patients who underwent EUS. The lesion detection rate and diagnostic performance of iEUS-SPL in identifying solid pancreatic lesions will be evaluated in real-time EUS scanning videos over prospective enrolled cases.

Inclusion Criteria:

1. Patients aged ≥18 years scheduled for EUS with suspected solid pancreatic lesions based on clinical symptoms, medical history, laboratory tests or radiological examinations agree to participate in the research and be able to sign informed consent.
2. Patients with no prior history of treatment for pancreatic lesions.

Exclusion Criteria:

1. Patients with absolute contraindications to EUS examination.
2. Pregnancy or lactating.
3. Uncorrectable coagulopathy(PTT>50 seconds or INR>1.5) and/or uncorrectable thrombocytopenia(platelet count<50×109/L).
4. Upper gastrointestinal obstruction.
5. Patients who underwent surgical treatment or anatomical alterations of the pancreas due to lesions in other thoracic and/or abdominal organs, as well as patients with congenital anatomical abnormalities.
6. Patients who have undergone biliary/pancreatic duct stent placement.
7. Patients who refuse to sign the informed consent.