Approximately 700,000 pancreatic cysts are incidentally detected by imaging each year. Up to 70% of these radiologically-detected cysts are intraductal papillary mucinous neoplasms (IPMNs), bona fide precursor lesions to pancreatic cancer, the only solid malignancy with a 5-year relative survival rate in the single digits. Once detected, existing imaging modalities and molecular markers cannot reliably distinguish low/moderate grade (benign) IPMNs that merit surveillance from high-grade/invasive (malignant) IPMNs that warrant surgical resection, posing a great clinical challenge. Based on preliminary data generated by our group, we hypothesize that unexplored categories of quantitative ‘radiomic’ features extracted from preoperative computed tomography (CT) scans will have added diagnostic value in predicting malignant IPMN pathology, compared to standard radiologic features. We further hypothesize that a liquid biopsy that measures microRNAs circulating in blood plasma (a miRNA genomic classifier (MGC)) that we have developed may help to further enhance diagnostic accuracy. The goals of this proposal are to 1) Evaluate the diagnostic performance of novel radiomic CT features in predicting IPMN pathology, compared to standard radiologic features, using data and specimens from a retrospective series (Aim 1a) and a prospective multi-institutional series of IPMN cases (Aim 1b); 2) Generate prototype clinical decision-making models (nomograms) that take into account radiomic data, the MGC, and other clinical characteristics (Aim 2); and 3) Evaluate the relationship between radiomic features and biological processes that underlie IPMN tumor development and/or progression. By leveraging interdisciplinary expertise and largely existing data unique to our institutions, our long-term goal is to discover a combined quantitative imaging and biomarker approach that is noninvasive and has added value in predicting IPMN pathology beyond that provided by standard radiologic characteristics. This line of translational research has potential to foster clinically actionable information that could be used to rapidly and cost-effectively personalize care for individuals with IPMNs and ultimately reduce the burden of pancreatic cancer as a major health problem.