Intraductal Papillary Mucinous Neoplasm of Pancreas

This prospective pilot study will evaluate the diagnostic performance of a previously validated artificial intelligence (AI) model when applied in real time during digital per-oral pancreatoscopy (POPS). The study will include adults undergoing clinically indicated pancreatoscopy for suspected or known intraductal papillary mucinous neoplasm (IPMN), indeterminate pancreatic-duct abnormalities, or preoperative assessment of IPMN extent. During the procedure, the endoscopist will first record a visual assessment while the AI system is hidden. The AI overlay will then be activated during the same pancreatoscopy examination, and its findings will be recorded independently. AI and endoscopist assessments will be compared with a prespecified reference standard based on surgical histopathology when available or tissue sampling and clinical/imaging follow-up when surgery is not performed. The primary objective is to estimate the sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy of real-time AI for identifying high-grade dysplasia or invasive carcinoma. The study is designed as a pilot to assess feasibility and generate preliminary diagnostic-accuracy estimates for future confirmatory research.

Pancreatic ductal adenocarcinoma (PDAC) is one of the cancers with the poorest prognosis and is often diagnosed at an advanced stage, resulting in very low 5-year survival rates. Many PDACs arise from non-invasive precursor lesions that develop over years, including pancreatic intraepithelial neoplasia (PanIN) and intraductal papillary mucinous neoplasms (IPMN). Only a minority of pancreatic cystic lesions progress to invasive carcinoma, and current clinical and radiologic criteria have limited accuracy in predicting which patients are at high risk. This observational translational study will enroll adult patients undergoing pancreatic surgical resection for suspected pancreatic neoplasm (IPMN, PanIN, or PDAC) at IRCCS "Saverio de Bellis". Residual tumor tissue not required for diagnostic purposes, and when available adjacent non-neoplastic tissue, will be collected, coded, and pseudonymized for molecular analyses. Tumor cells will be used to generate three-dimensional cultures (tumorspheres and organoids) and will undergo genomic characterization by next-generation sequencing, RNA-sequencing-based transcriptomic profiling, protein expression analyses, advanced imaging, and in-vitro drug response assays. The main goal is to identify and validate molecular biomarkers predictive of progression to PDAC, improve risk stratification of patients with pancreatic precursor lesions, and support the development of innovative precision medicine strategies.

The primary objective is to construct a multimodal AI model (Cyst-AI) based on EUS images and clinical data such as imaging features(CT or MRI) and laboratory tests to assist endoscopists in the diagnosis of pancreatic cystic lesions(PCLs), mainly differentiating mucinous from non-mucinous lesions. The secondary objective is to evaluate the model's effectiveness in risk stratification and clinical management for patients with PCLs.

This study investigates the impact of GLP-1 receptor agonists (GLP-1 RAs) on patients with intraductal papillary mucinous neoplasms (IPMNs), a type of pancreatic cystic neoplasm that can progress to malignancy. With the increasing use of GLP-1 RAs for managing diabetes and obesity, concerns about their potential to influence pancreatic conditions, like IPMNs, have emerged. Although GLP-1 RAs are generally safe, their effects on pre-existing pancreatic conditions remain unclear. The study aims to evaluate whether GLP-1 RA use in IPMN patients is linked to changes in pancreatic cyst characteristics, the incidence of acute pancreatitis, variations in tumor markers, and the progression of IPMNs to high-grade dysplasia or malignancy. A retrospective analysis will be conducted using medical data from patients diagnosed with IPMNs and treated with GLP-1 RAs between 2010 and 2024 at three Swiss hospitals. Key outcomes will include radiological changes, the incidence of acute pancreatitis, and potential shifts in IPMN surveillance or need for surgical intervention

The goal of this single-arm intervention trial is to determine the feasibility of implementing endoscopic ultrasound-guided pancreatic cyst chemoablation (EUS-PCA) using gemcitabine and paclitaxel for intraductal papillary mucinous neoplasms (IPMN) in two New Zealand tertiary interventional endoscopy centres.

Under the hypotheses that a more accurate patients selection could limit the problem of overtreatment and that benign intraductal papillary mucinous neoplasms (IPMN) have a distinguishable Endocrine/Metabolic/Inflammatory (EMI) profile from those with high-grade disease/invasive carcinoma, this study has three specific aims. The first aim is to evaluate and confirm the accuracy of the updated versions of International and European guidelines for the management of IPMN and it will be addressed by retrospectively applying the criteria included in the two guidelines on 350 patients with resected IPMN in order to determine the most accurate criteria to identify High Grade Dysplasia(HGD)/Invasive Carcinoma (IC). The second aim is to identify pre-operative biological and/or radiological/endosonographic biomarker(s) able to distinguish low- versus high-risk IPMN for cancer progression in a prospective study by enrolling a cohort of 186 (of which 145 surgically-resected) patients. The third aim is to prospectively validate biological and/or radiological/endosonographic biomarker(s) (previously identified and optimized) on a new cohort of 50 patients with IPMN undergoing surgical resection.