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

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.

[1]  M. Goggins Markers of Pancreatic Cancer: Working Toward Early Detection , 2011, Clinical Cancer Research.

[2]  J. Jett,et al.  Added Value of a Serum Proteomic Signature in the Diagnostic Evaluation of Lung Nodules , 2012, Cancer Epidemiology, Biomarkers & Prevention.

[3]  K. Lillemoe,et al.  Branch Duct Intraductal Papillary Mucinous Neoplasms: Does Cyst Size Change the Tip of the Scale? A Critical Analysis of the Revised International Consensus Guidelines in a Large Single-Institutional Series , 2013, Annals of surgery.

[4]  Neema Jamshidi,et al.  Illuminating radiogenomic characteristics of glioblastoma multiforme through integration of MR imaging, messenger RNA expression, and DNA copy number variation. , 2013, Radiology.

[5]  Olivier Gevaert,et al.  Addition of MR imaging features and genetic biomarkers strengthens glioblastoma survival prediction in TCGA patients. , 2015, Journal of neuroradiology. Journal de neuroradiologie.

[6]  P. Lambin,et al.  CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. , 2015, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[7]  P. Lambin,et al.  Stability of FDG-PET Radiomics features: An integrated analysis of test-retest and inter-observer variability , 2013, Acta oncologica.

[8]  Robert J. Gillies,et al.  Quantitative Computed Tomographic Descriptors Associate Tumor Shape Complexity and Intratumor Heterogeneity with Prognosis in Lung Adenocarcinoma , 2015, PloS one.

[9]  M. Al-Haddad,et al.  International Consensus Guidelines parameters for the prediction of malignancy in intraductal papillary mucinous neoplasm are not properly weighted and are not cumulative. , 2014, HPB : the official journal of the International Hepato Pancreato Biliary Association.

[10]  Samuel H. Hawkins,et al.  Reproducibility and Prognosis of Quantitative Features Extracted from CT Images. , 2014, Translational oncology.

[11]  D. Sahani,et al.  Prospective evaluation of reader performance on MDCT in characterization of cystic pancreatic lesions and prediction of cyst biologic aggressiveness. , 2011, AJR. American journal of roentgenology.

[12]  B. Goh,et al.  Utility of the Sendai Consensus Guidelines for Branch-Duct Intraductal Papillary Mucinous Neoplasms: A Systematic Review , 2014, Journal of Gastrointestinal Surgery.

[13]  M. Büchler,et al.  Pancreatic Main-Duct Involvement in Branch-Duct IPMNs: An Underestimated Risk , 2014, Annals of surgery.

[14]  Jie Tian,et al.  Automated delineation of lung tumors from CT images using a single click ensemble segmentation approach , 2013, Pattern Recognit..

[15]  R. Gillies,et al.  Quantitative imaging in cancer evolution and ecology. , 2013, Radiology.

[16]  Olivier Gevaert,et al.  Non-small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data--methods and preliminary results. , 2012, Radiology.

[17]  T. Yeatman,et al.  A Genome-Wide Investigation of MicroRNA Expression Identifies Biologically-Meaningful MicroRNAs That Distinguish between High-Risk and Low-Risk Intraductal Papillary Mucinous Neoplasms of the Pancreas , 2015, PloS one.

[18]  M. Fabbri,et al.  microRNAs in the tumor microenvironment: solving the riddle for a better diagnostics , 2014, Expert review of molecular diagnostics.

[19]  Myeong-Jin Kim,et al.  Relative accuracy of CT and MRI in the differentiation of benign from malignant pancreatic cystic lesions. , 2011, Clinical radiology.

[20]  K. Miles,et al.  Tumour heterogeneity in non-small cell lung carcinoma assessed by CT texture analysis: a potential marker of survival , 2012, European Radiology.

[21]  C. la Vecchia,et al.  Clinical utility of a plasma-based miRNA signature classifier within computed tomography lung cancer screening: a correlative MILD trial study. , 2014, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[22]  R. Gillies,et al.  Radiologically defined ecological dynamics and clinical outcomes in glioblastoma multiforme: preliminary results. , 2014, Translational oncology.

[23]  M. Kuo,et al.  Radiogenomic analysis to identify imaging phenotypes associated with drug response gene expression programs in hepatocellular carcinoma. , 2007, Journal of vascular and interventional radiology : JVIR.

[24]  R. Yantiss,et al.  Commercial Molecular Panels Are of Limited Utility in the Classification of Pancreatic Cystic Lesions , 2012, The American journal of surgical pathology.

[25]  Andre Dekker,et al.  Radiomics: the process and the challenges. , 2012, Magnetic resonance imaging.

[26]  S. Park,et al.  Imaging Features to Distinguish Malignant and Benign Branch-Duct Type Intraductal Papillary Mucinous Neoplasms of the Pancreas: A Meta-analysis , 2014, Annals of surgery.

[27]  V. Goh,et al.  Non-small cell lung cancer: histopathologic correlates for texture parameters at CT. , 2013, Radiology.

[28]  D. D. Maki,et al.  Radiogenomic analysis of breast cancer using MRI: a preliminary study to define the landscape. , 2012, AJR. American journal of roentgenology.

[29]  Robert J. Gillies,et al.  Test–Retest Reproducibility Analysis of Lung CT Image Features , 2014, Journal of Digital Imaging.

[30]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[31]  C. Good,et al.  Measurements of heterogeneity in gliomas on computed tomography relationship to tumour grade , 2012, Journal of Neuro-Oncology.

[32]  Ugo Pastorino,et al.  MicroRNA signatures in tissues and plasma predict development and prognosis of computed tomography detected lung cancer , 2011, Proceedings of the National Academy of Sciences.

[33]  Matthew B Schabath,et al.  Semiquantitative Computed Tomography Characteristics for Lung Adenocarcinoma and Their Association With Lung Cancer Survival. , 2015, Clinical lung cancer.

[34]  Benjamin D. Smith,et al.  Projecting cancer incidence and deaths to 2030: the unexpected burden of thyroid, liver, and pancreas cancers in the United States. , 2014, Cancer research.

[35]  T. Jiang,et al.  Relationship between magnetic resonance imaging features and miRNA gene expression in patients with glioblastoma multiforme. , 2013, Chinese medical journal.

[36]  J. Farrell Prevalence, Diagnosis and Management of Pancreatic Cystic Neoplasms: Current Status and Future Directions , 2015, Gut and liver.

[37]  W. Brugge,et al.  Intraductal papillary mucinous neoplasm of the pancreas , 2006, Cancer.

[38]  K. Miles,et al.  Tumour heterogeneity in oesophageal cancer assessed by CT texture analysis: preliminary evidence of an association with tumour metabolism, stage, and survival. , 2012, Clinical radiology.

[39]  K. Aldape,et al.  Identification of noninvasive imaging surrogates for brain tumor gene-expression modules , 2008, Proceedings of the National Academy of Sciences.

[40]  Jin-Young Jang,et al.  International consensus guidelines 2012 for the management of IPMN and MCN of the pancreas. , 2012, Pancreatology : official journal of the International Association of Pancreatology (IAP) ... [et al.].

[41]  B. Ramakrishna,et al.  Intraductal papillary mucinous neoplasm of the pancreas , 2010, Indian journal of gastroenterology : official journal of the Indian Society of Gastroenterology.

[42]  H. Reber,et al.  Pancreatic surgery. , 2006, Current opinion in gastroenterology.

[43]  A. Šimundić Measures of Diagnostic Accuracy: Basic Definitions , 2009, EJIFCC.

[44]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[45]  D. Coppola,et al.  Plasma MicroRNAs as Novel Biomarkers for Patients with Intraductal Papillary Mucinous Neoplasms of the Pancreas , 2015, Cancer Prevention Research.

[46]  David Fenstermacher,et al.  Implementing personalized medicine in a cancer center. , 2011, Cancer journal.

[47]  Howard Y. Chang,et al.  Decoding global gene expression programs in liver cancer by noninvasive imaging , 2007, Nature Biotechnology.

[48]  Balaji Ganeshan,et al.  Predicting Overall Survival in Patients With Metastatic Melanoma on Antiangiogenic Therapy and RECIST Stable Disease on Initial Posttherapy Images Using CT Texture Analysis. , 2015, AJR. American journal of roentgenology.

[49]  R. Subramani,et al.  Emerging roles of microRNAs in pancreatic cancer diagnosis, therapy and prognosis (Review) , 2015, International journal of oncology.

[50]  Olivier Gevaert,et al.  Prognostic PET 18F-FDG uptake imaging features are associated with major oncogenomic alterations in patients with resected non-small cell lung cancer. , 2012, Cancer research.