Hyperpolarized Magnetic Resonance and Artificial Intelligence: Frontiers of Imaging in Pancreatic Cancer (Preprint)
BACKGROUND There is an unmet need for non-invasive imaging markers that help identify the aggressive sub-type(s) of pancreatic ductal adenocarcinoma (PDAC) at diagnosis and to evaluate the efficacy of therapy prior to tumor reduction. In the last few years, there are two major developments that can have a significant impact in developing imaging biomarkers for PDAC: I) hyperpolarized metabolic Magnetic Resonance (HP-MR) and II) applications of Artificial Intelligence (AI). OBJECTIVE Our objective is to discuss these two exciting but independent developments in the realm of PDAC imaging and detection from the available literature to date. METHODS A systematic review following the PRISMA Extension for Scoping Reviews (PRISMA-ScR) guidelines was conducted. The manuscript addressing the utilization of Hyperpolarization-based magnetic resonance (HP-MR) and/or Artificial Intelligence for early detection, assessing aggressiveness, and interrogating the early efficacy of therapy in PDAC cited in recent clinical guidelines were extracted from PubMed and Google Scholar. The studies were reviewed by reviewers following the exclusion and inclusion criteria and grouped based on the utilization of HP-MR and AI in PDAC diagnosis. RESULTS HP-MR increases the sensitivity of conventional MR by over 10,000-fold enabling real-time metabolic measurements. The utility of HP-MR in PDAC has been verified in several preclinical studies, but has not been proven in a clinical setting. In contrast, AI applications in PDAC imaging in the clinic are nascent, but mostly limited to Computational Tomography (CT) imaging datasets. CONCLUSIONS Combining AI and HP-MR applications may lead to the development of real-time biomarkers of early detection, assessing aggressiveness, and interrogating the early efficacy of therapy in PDAC.