Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms

Abstract

Intraductal papillary mucinous neoplasms (IPMNs) are pancreatic cancer precursors incidentally discovered by cross-sectional imaging. Consensus guidelines for IPMN management rely on standard radiologic features to predict pathology, but they lack accuracy. Using a retrospective cohort of 38 surgically-resected, pathologically-confirmed IPMNs (20 benign; 18 malignant) with preoperative computed tomography (CT) images and matched plasma-based ‘miRNA genomic classifier (MGC)’ data, we determined whether quantitative ‘radiomic’ CT features (+/- the MGC) can more accurately predict IPMN pathology than standard radiologic features ‘high-risk’ or ‘worrisome’ for malignancy. Logistic regression, principal component analyses, and cross-validation were used to examine associations. Sensitivity, specificity, positive and negative predictive value (PPV, NPV) were estimated. The MGC, ‘high-risk,’ and ‘worrisome’ radiologic features had area under the receiver operating characteristic curve (AUC) values of 0.83, 0.84, and 0.54, respectively. Fourteen radiomic features differentiated malignant from benign IPMNs (p<0.05) and collectively had an AUC=0.77. Combining radiomic features with the MGC revealed an AUC=0.92 and superior sensitivity (83%), specificity (89%), PPV (88%), and NPV (85%) than other models. Evaluation of uncertainty by 10-fold cross-validation retained an AUC>0.80 (0.87 (95% CI:0.84-0.89)). This proof-of-concept study suggests a noninvasive radiogenomic approach may more accurately predict IPMN pathology than ‘worrisome’ radiologic features considered in consensus guidelines.

Radiomics Features of Multiparametric MRI as Novel Prognostic Factors in Advanced Nasopharyngeal Carcinoma

“…The field of radiomics aims to develop decision support tools. Therefore, it involves combining radiomics data with other patient characteristics, as available, to increase the power of the decision support models (17,34). We showed that radiomics features complemented the TNM staging system, helping to provide better prognostic ability for pretreatment PFS.…”

A pilot study of radiologic measures of abdominal adiposity: weighty contributors to early pancreatic carcinogenesis worth evaluating?

“…External validation in a large, independent data set is warranted. Furthermore, with a larger sample size, multivariable modeling and receiver characteristic curve analyses will be helpful to determine the utility of gender-specific radiologic measures of abdominal obesity in discriminating malignant from benign IPMNs, independent of and in combination with novel molecular and radiologic markers 19,20 , standard clinical and radiologic features encompassed by consensus guidelines 12 , and BMI. …”

“…The study population included a fixed cohort of 37 patients with IPMNs whose pre-operative CT images had recently been evaluated as part of a different study 20 . The cases had initially been identified using a prospectively maintained clinical database of individuals who underwent a pancreatic resection for an IPMN between 2006 and 2011 at Moffitt Cancer Center and Research Institute (Moffitt) and provided written consent for medical images and clinical data to be donated for research through protocols approved by the Institutional Review Board (IRB) of the University of South Florida, including Total Cancer Care 41 .…”

“…Most of the CT scans from this series of patients were obtained on the Siemens Sensation (16, 40, or 64) using an abdominal or pancreatic CT angio (CTA) protocol according to standard operating procedures described previously 20 . Archived non-enhanced CT images performed within the three months prior to surgery, were acquired from Moffitt’s GE Centricity Picture Archiving and Communication System (PACS).…”

“…However, consensus guidelines 12 incorrectly predict pathology in 30%–70% of cases 12,14-18 , causing under- and over-treatment. Thus, rationale exists for identifying noninvasive markers to improve diagnostic accuracy for IPMNs, especially those without high risk stigmata 19,20 . …”