Pancreatic cancer
Conditions
Interventions
None listed
Sponsors
Kobe University
Eligibility
Sex/Gender
All
Inclusion criteria
Inclusion criteria: Pancreatic cancer group: Patients diagnosed with pancreatic cancer with a primary tumor diameter of <=20 mm between January 1, 2014 and December 31, 2024. Pancreatic cancer is defined as either of the following: Histological diagnosis of adenocarcinoma of the pancreas. Histological diagnosis of pancreatic intraepithelial neoplasia grade 3 (PanIN-3)/high-grade PanIN. Subgroup: Tis/<=10 mm pancreatic cancer group Among the pancreatic cancer group, patients who meet all of the following: Diagnosed with pancreatic carcinoma in situ/PanIN-3/high-grade PanIN. Tumor size diagnosed as <=10 mm. Normal control group: Patients who underwent contrast-enhanced or non-contrast abdominal CT between January 1, 2014 and December 31, 2024 for the diagnosis of diseases other than pancreatic cancer, and who had no pancrea
Exclusion criteria
Exclusion criteria: Patients who requested not to participate in this study based on publicly available information Patients without pancreatic CT imaging data or with poor image quality that precludes evaluation Patients younger than 18 years (for cases prior to March 31, 2022, patients younger than 20 years)
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Concordance between the presence or absence of pancreatic cancer as determined by the AI-based imaging algorithm and the definitive diagnosis based on the pathological findings. | — |
Secondary
| Measure | Time frame |
|---|---|
| Presence or absence of pancreatic cancer as determined by expert radiologists (pancreatic cancer present/pancreatic cancer absent) Detection of direct findings (tumor mass) by the AI-based imaging algorithm Detection of direct findings (tumor mass) by expert radiologists Detection of indirect findings (e.g., main pancreatic duct dilatation, localized pancreatic atrophy) by the AI-based imaging algorithm Detection of indirect findings (e.g., main pancreatic duct dilatation, localized pancreatic atrophy) by expert radiologists Presence or absence of pancreatic cancer in past imaging as determined by the AI-based imaging algorithm Presence or absence of pancreatic cancer in past imaging as determined by the reference standard (consensus of two expert radiologists) | — |
Countries
Japan
Contacts
Public ContactAtsuhiro Masuda
Kobe University Graduate School of Medicine Division of Gastroenterology, Department of Internal Medicine
Outcome results
None listed