Development of a Novel Multiparametric MRI Radiomic Nomogram for Preoperative Evaluation of Early Recurrence in Resectable Pancreatic Cancer

<jats:sec><jats:title>Background</jats:title><jats:p>In pancreatic cancer, methods to predict early recurrence (ER) and identify patients at increased risk of relapse are urgently required.</jats:p></jats:sec><jats:sec><jats:title>Purpose</jats:title><jats:p>To develop a radiomic nomogram based on MR radiomics to stratify patients preoperatively and potentially improve clinical practice.</jats:p></jats:sec><jats:sec><jats:title>Study Type</jats:title><jats:p>Retrospective.</jats:p></jats:sec><jats:sec><jats:title>Population</jats:title><jats:p>We enrolled 303 patients from two medical centers. Patients with a disease‐free survival ≤12 months were assigned as the ER group (<jats:italic>n</jats:italic> = 130). Patients from the first medical center were divided into a training cohort (<jats:italic>n</jats:italic> = 123) and an internal validation cohort (<jats:italic>n</jats:italic> = 54). Patients from the second medical center were used as the external independent validation cohort (<jats:italic>n</jats:italic> = 126).</jats:p></jats:sec><jats:sec><jats:title>Field Strength/Sequence</jats:title><jats:p>3.0T axial T<jats:sub>1</jats:sub>‐weighted (T<jats:sub>1</jats:sub>‐w), T<jats:sub>2</jats:sub>‐weighted (T<jats:sub>2</jats:sub>‐w), contrast‐enhanced T<jats:sub>1</jats:sub>‐weighted (CET<jats:sub>1</jats:sub>‐w).</jats:p></jats:sec><jats:sec><jats:title>Assessment</jats:title><jats:p>ER was confirmed via imaging studies as MRI or CT. Risk factors, including clinical stage, CA19‐9, and radiomic‐related features of ER were assessed. In addition, to determine the intra‐ and interobserver reproducibility of radiomic features extraction, the intra‐ and interclass correlation coefficients (ICC) were calculated.</jats:p></jats:sec><jats:sec><jats:title>Statistical Tests</jats:title><jats:p>The area under the receiver‐operator characteristic (ROC) curve (AUC) was used to evaluate the predictive accuracy of the radiomic signature in both the training and test groups. The results of decision curve analysis (DCA) indicated that the radiomic nomogram achieved the most net benefit.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>The AUC values of ER evaluation for the radiomics signature were 0.80 (training cohort), 0.81 (internal validation cohort), and 0.78 (external validation cohort). Multivariate logistic analysis identified the radiomic signature, CA19‐9 level, and clinical stage as independent parameters of ER. A radiomic nomogram was then developed incorporating the CA19‐9 level and clinical stage. The AUC values for ER risk evaluation using the radiomic nomogram were 0.87 (training cohort), 0.88 (internal validation cohort), and 0.85 (external validation cohort).</jats:p></jats:sec><jats:sec><jats:title>Data Conclusion</jats:title><jats:p>The radiomic nomogram can effectively evaluate ER risks in patients with resectable pancreatic cancer preoperatively, which could potentially improve treatment strategies and facilitate personalized therapy in pancreatic cancer.</jats:p><jats:p><jats:bold>Level of Evidence:</jats:bold> 4</jats:p><jats:p><jats:bold>Technical Efficacy:</jats:bold> Stage 4</jats:p><jats:p>J. Magn. Reson. Imaging 2020;52:231–245.</jats:p></jats:sec>