AI-Assisted Differentiation of Autoimmune Pancreatitis and Pancreatic Cancer Using EUS: A Multicenter Ambispective Study

Focal autoimmune pancreatitis (f-AIP) and pancreatic ductal adenocarcinoma (PDAC) exhibit substantial overlap in clinical manifestations and imaging features, posing a major diagnostic challenge in pancreatic diseases. Given the marked differences in treatment strategies and prognosis, accurate differentiation is essential to avoid unnecessary surgery and ensure timely initiation of anticancer treatment. This study aims to collect endoscopic ultrasound (EUS) images from patients with confirmed f-AIP or PDAC across multiple centers, using a previously established multicenter database. Data collected before January 2026 will be used to develop an artificial intelligence (AI) model based on EUS radiomics for differential diagnosis. Subsequently, prospectively collected data from participating centers from 2026 onward will be used for model testing and validation. The diagnostic performance of the model will be evaluated and compared with that of endoscopists with different levels of experience. Furthermore, this study will investigate the clinical value of interpretable radiomic features, with particular emphasis on challenging diagnostic scenarios, including IgG4-negative AIP, AIP with elevated carbohydrate antigen 19-9 (CA19-9) levels, and PDAC with imaging features resembling those of AIP. The ultimate goal is to provide a reliable tool for accurate, noninvasive preoperative differential diagnosis while promoting the standardization of multicenter AIP databases and the sharing and utilization of imaging data resources.

Inclusion C\*\*Inclusion Criteria:\*\* \*\*1. Focal Autoimmune Pancreatitis (f-AIP) Group\*\* * Diagnosis of type 1 or type 2 autoimmune pancreatitis (AIP) according to the 2023 Chinese guidelines for the diagnosis and treatment of AIP or the 2011 International Consensus Diagnostic Criteria. * Imaging evidence of a focal pancreatic mass confined to a specific pancreatic segment. * Preoperative endoscopic ultrasound (EUS) examination with at least five clear images of the lesion obtained from different imaging planes. * Histopathological confirmation of AIP based on EUS-guided fine-needle aspiration/biopsy (EUS-FNA/FNB) or surgical pathology. * Complete clinical data, including demographic characteristics, serological findings, imaging results, treatment information, and follow-up records. * Written informed consent from the patient or legal representative, as applicable. \*\*2. Pancreatic Ductal Adenocarcinoma (PDAC) Group\*\* * Histological or cytological confirmation of pancreatic ductal adenocarcinoma (PDAC) by EUS-FNA/FNB or surgical pathology. * Preoperative EUS examination with at least five clear images of the lesion obtained from different imaging planes. * A pancreatic parenchymal lesion comparable to f-AIP, with a maximum diameter of 5 cm or less. * Complete clinical data, including demographic characteristics, serological findings, imaging results, treatment information, and follow-up records. * Written informed consent from the patient or legal representative, as applicable. \*\*Exclusion Criteria:\*\* The following criteria apply to both groups: * Poor-quality EUS images, including severe blurring, artifacts, or inadequate lesion visualization, preventing radiomic analysis. * Uncertain or inconclusive pathological diagnosis. * Concurrent pancreatic diseases, such as acute pancreatitis, non-AIP chronic pancreatitis, pancreatic cystic neoplasms, or pancreatic neuroendocrine tumors. * Previous treatment for pancreatic disease, including corticosteroid therapy, chemotherapy, radiotherapy, or surgery, before EUS examination. * Missing essential clinical or imaging data. * Pregnancy or breastfeeding. * Inability to complete the required study-related examinations.iteria: Exclusion Criteria: \-