A primer on artificial intelligence in pancreatic imaging

• Published in: Diagnostic and interventional imaging 2023-09, Vol.104 (9), p.435-447
• Main Authors: Ahmed, Taha M., Kawamoto, Satomi, Hruban, Ralph H., Fishman, Elliot K., Soyer, Philippe, Chu, Linda C.
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Deep learning; Pancreas; Radiomics
• ISSN: 2211-5684; 2211-5684
• DOI: 10.1016/j.diii.2023.03.002

•Preliminary studies support the idea that artificial intelligence may facilitate earlier pancreatic tumor detection and improve disease classification and prognostication.•Most pancreas artificial intelligence studies are single-center retrospective studies, which raises concerns about external validity and generalizability.•The radiomics quality score provides an objective assessment of the quality of radiomics studies, and should be taken into account in the design of future validation studies. Artificial Intelligence (AI) is set to transform medical imaging by leveraging the vast data contained in medical images. Deep learning and radiomics are the two main AI methods currently being applied within radiology. Deep learning uses a layered set of self-correcting algorithms to develop a mathematical model that best fits the data. Radiomics converts imaging data into mineable features such as signal intensity, shape, texture, and higher-order features. Both methods have the potential to improve disease detection, characterization, and prognostication. This article reviews the current status of artificial intelligence in pancreatic imaging and critically appraises the quality of existing evidence using the radiomics quality score.