Format

Send to

Choose Destination
Oncotarget. 2016 Dec 27;7(52):85785-85797. doi: 10.18632/oncotarget.11768.

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

Author information

1
Cancer Epidemiology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA.
2
Gastrointestinal Oncology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA.
3
Diagnostic Imaging and Interventional Radiology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA.
4
Cancer Imaging and Metabolism, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA.
5
Biostatistics and Bioinformatics, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA.
6
Department of Clinical Surgery/Surgical Oncology, Palmetto Health/USC School of Medicine, Columbia, South Carolina, USA.
7
Radiation Oncology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA.
8
Anatomic Pathology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA.
9
Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, China.
10
Department of Surgery, Division of General Surgery, University of Florida Health Sciences Center, Gainesville, Florida, USA.
11
Department of Surgery, Sylvester Comprehensive Cancer Center at the University of Miami Miller School of Medicine, Miami, Florida, USA.

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.

KEYWORDS:

miRNA; pancreas; pre-malignant lesions; radiomics; risk stratification

PMID:
27589689
PMCID:
PMC5349874
DOI:
10.18632/oncotarget.11768
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Impact Journals, LLC Icon for PubMed Central
Loading ...
Support Center