Synopsis

Characterization of pancreatic diseases may be challenging because of some overlap in imaging appearance. To overcome the current limitations of imaging, researchers have developed radiomics. Radiomics refers to the extraction and analysis of quantitative features from medical images to build predictive models, relating imaging features to clinical outcomes. Most radiomics studies of　pancreatic diseases used CT data; however, MRI-based radiomics of the pancreas is increasing in recent years. Several studies have assessed the potential of radiomics in the diagnosis of pancreatic tumors, prediction of tumor grade, prediction of recurrence or complications after surgery, and assessment of chronic pancreatitis.