Pancreatic cancer is a highly lethal disease associated with significant morbidity and mortality. In the United States (US), the overall 5-year relative survival rate for pancreatic cancer during the 2012–2018 period was 11.5%. However, the cancer stage at diagnosis strongly influences relative survival in these patients. Per the National Cancer Institute (NCI) statistics for 2012–2018, the 5-year relative survival rate for patients with localized disease was 43.9%, while it was 3.1% for patients with distant metastasis. The poor survival rates are primarily due to the late development of clinical signs and symptoms. Hence, early diagnosis is critical in improving treatment outcomes. In recent years, artificial intelligence (AI) has gained immense popularity in gastroenterology. AI-assisted endoscopic ultrasound (EUS) models have been touted as a breakthrough in the early detection of pancreatic cancer. These models may also accurately differentiate pancreatic cancer from chronic pancreatitis and autoimmune pancreatitis, which mimics pancreatic cancer on radiological imaging. In this review, we detail the application of AI-assisted EUS models for pancreatic cancer detection. We also highlight the utility of AI-assisted EUS models in differentiating pancreatic cancer from radiological mimickers. Furthermore, we discuss the current limitations and future applications of AI technology in EUS for pancreatic cancers.
All Science Journal Classification (ASJC) codes