European Radiology

, Volume 29, Issue 12, pp 6880–6890 | Cite as

CT radiomics may predict the grade of pancreatic neuroendocrine tumors: a multicenter study

  • Dongsheng Gu
  • Yabin Hu
  • Hui Ding
  • Jingwei Wei
  • Ke Chen
  • Hao Liu
  • Mengsu ZengEmail author
  • Jie TianEmail author
Computer Applications



To develop and validate a radiomics-based nomogram for preoperatively predicting grade 1 and grade 2/3 tumors in patients with pancreatic neuroendocrine tumors (PNETs).


One hundred thirty-eight patients derived from two institutions with pathologically confirmed PNETs (104 in the training cohort and 34 in the validation cohort) were included in this retrospective study. A total of 853 radiomic features were extracted from arterial and portal venous phase CT images respectively. Minimum redundancy maximum relevance and random forest methods were adopted for the significant radiomic feature selection and radiomic signature construction. A fusion radiomic signature was generated by combining both the single-phase signatures. The nomogram based on a comprehensive model incorporating the clinical risk factors and the fusion radiomic signature was established, and decision curve analysis was applied for clinical use.


The fusion radiomic signature has significant association with histologic grade (p < 0.001). The nomogram integrating independent clinical risk factor tumor margin and fusion radiomic signature showed strong discrimination with an area under the curve (AUC) of 0.974 (95% CI 0.950–0.998) in the training cohort and 0.902 (95% CI 0.798–1.000) in the validation cohort with good calibration. Decision curve analysis verified the clinical usefulness of the predictive nomogram.


We proposed a comprehensive nomogram consisting of tumor margin and fusion radiomic signature as a powerful tool to predict grade 1 and grade 2/3 PNET preoperatively and assist the clinical decision-making for PNET patients.

Key Points

• Radiomic signature has strong discriminatory ability for the histologic grade of PNETs.

• Arterial and portal venous phase CT imaging are complementary for the prediction of PNET grading.

• The comprehensive nomogram outperformed clinical factors in assisting therapy strategy in PNET patients.


Neoplasm grading Pancreas Neuroendocrine tumor Radiomics CT 







Area under the curve


Carbohydrate antigen 19-9


Carcinoembryonic antigen


Confidence interval


Computed tomography


Dilatation of the main pancreatic duct


Gray level co-occurrence matrix


Gray level dependence matrix


Gray level run length matrix


Gray level size zone matrix


Intra- and inter-class correlation coefficient


Magnetic resonance


Minimum redundancy maximum relevance


Neighboring gray tone difference matrix


Negative predictive value


Pancreatic atrophy


Picture archiving and communication system


Preoperative blood glucose


Protrusion from the outline of the pancreas


Preoperative liver metastasis


Pancreatic neuroendocrine tumors


Positive predictive value


Random forest


Receiver operating characteristics


Region of interest






World Health Organization



This study has received funding by the National Natural Science Foundation of China (No. 81227901, 81527805, 61231004, 81771924, 81501616), National Key Research and Development Program of China (2017YFA0205200, 2017YFC1308700), and the Science and Technology Service Network Initiative of the Chinese Academy of Sciences (KFJ-SW-STS-160).

Compliance with ethical standards


The scientific guarantor of this publication is Jie Tian.

Conflict of interest

The authors declare that they have no competing interests.

Statistics and biometry

Dr. Jingwei Wei from the University of Chinese Academy of Sciences, who is one of the authors, has significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board of Zhongshan Hospital Affiliated to Shanghai Fudan University and Affiliated Hospital (Laoshan hospital) of Qingdao University.

Ethical approval

Institutional Review Board approval was obtained.


• retrospective

• diagnostic or prognostic study

• multicenter study

Supplementary material

330_2019_6176_MOESM1_ESM.docx (1.2 mb)
ESM 1 (DOCX 1238 kb)


  1. 1.
    Yao JC, Hassan M, Phan A et al (2008) One hundred years after “carcinoid”: epidemiology of and prognostic factors for neuroendocrine tumors in 35,825 cases in the United States. J Clin Oncol 26:3063–3072CrossRefGoogle Scholar
  2. 2.
    Ohmoto A, Rokutan H, Yachida S (2017) Pancreatic neuroendocrine neoplasms: basic biology, current treatment strategies and prospects for the future. Int J Mol Sci 18:143CrossRefGoogle Scholar
  3. 3.
    Bosman FT, Carneiro F, Hruban RH, Theise ND (2010) WHO classification of tumours of the digestive system, 4th edn. International Agency for Research on Cancer, LyonGoogle Scholar
  4. 4.
    Reid MD, Balci S, Saka B, Adsay NV (2014) Neuroendocrine tumors of the pancreas: current concepts and controversies. Endocr Pathol 25:65–79CrossRefGoogle Scholar
  5. 5.
    Klimstra DS, Modlin IR, Coppola D, Lloyd RV, Suster S (2010) The pathologic classification of neuroendocrine tumors: a review of nomenclature, grading, and staging systems. Pancreas 39:707–712CrossRefGoogle Scholar
  6. 6.
    Scarpa A, Mantovani W, Capelli P et al (2010) Pancreatic endocrine tumors: improved TNM staging and histopathological grading permit a clinically efficient prognostic stratification of patients. Mod Pathol 23:824–833CrossRefGoogle Scholar
  7. 7.
    Zhou C, Zhang J, Zheng Y, Zhu Z (2012) Pancreatic neuroendocrine tumors: a comprehensive review. Int J Cancer 131:1013–1022CrossRefGoogle Scholar
  8. 8.
    Öberg K (2012) Neuroendocrine tumors of the digestive tract: impact of new classifications and new agents on therapeutic approaches. Curr Opin Oncol 24:433–440CrossRefGoogle Scholar
  9. 9.
    Larghi A, Capurso G, Carnuccio A et al (2012) Ki-67 grading of nonfunctioning pancreatic neuroendocrine tumors on histologic samples obtained by EUS-guided fine-needle tissue acquisition: a prospective study. Gastrointest Endosc 76:570–577CrossRefGoogle Scholar
  10. 10.
    Horiguchi S, Kato H, Shiraha H et al (2017) Dynamic computed tomography is useful for prediction of pathological grade in pancreatic neuroendocrine neoplasm. J Gastroenterol Hepatol 32:925–931CrossRefGoogle Scholar
  11. 11.
    De Robertis R, Cingarlini S, Martini PT et al (2017) Pancreatic neuroendocrine neoplasms: magnetic resonance imaging features according to grade and stage. World J Gastroenterol 23:275–285CrossRefGoogle Scholar
  12. 12.
    Kim JH, Eun HW, Kim YJ, Han JK, Choi BI (2013) Staging accuracy of MR for pancreatic neuroendocrine tumor and imaging findings according to the tumor grade. Abdom Imaging 38:1106–1114CrossRefGoogle Scholar
  13. 13.
    Jang KM, Kim SH, Lee SJ, Choi D (2014) The value of gadoxetic acid-enhanced and diffusion-weighted MRI for prediction of grading of pancreatic neuroendocrine tumors. Acta Radiol 55:140–148CrossRefGoogle Scholar
  14. 14.
    Besa C, Ward S, Cui Y, Jajamovich G, Kim M, Taouli B (2016) Neuroendocrine liver metastases: value of apparent diffusion coefficient and enhancement ratios for characterization of histopathologic grade. J Magn Reson Imaging 44:1432–1441CrossRefGoogle Scholar
  15. 15.
    Belousova E, Karmazanovsky G, Kriger A et al (2017) Contrast-enhanced MDCT in patients with pancreatic neuroendocrine tumours: correlation with histological findings and diagnostic performance in differentiation between tumour grades. Clin Radiol 72:150–158CrossRefGoogle Scholar
  16. 16.
    Min JH, Kang TW, Kim YK et al (2018) Hepatic neuroendocrine tumour: apparent diffusion coefficient as a potential marker of prognosis associated with tumour grade and overall survival. Eur Radiol 28:2561–2571CrossRefGoogle Scholar
  17. 17.
    Hwang EJ, Lee JM, Yoon JH et al (2014) Intravoxel incoherent motion diffusion-weighted imaging of pancreatic neuroendocrine tumors: prediction of the histologic grade using pure diffusion coefficient and tumor size. Invest Radiol 49:396–402CrossRefGoogle Scholar
  18. 18.
    Choi TW, Kim JH, Yu MH, Park SJ, Han JK (2018) Pancreatic neuroendocrine tumor: prediction of the tumor grade using CT findings and computerized texture analysis. Acta Radiol 59:383–392CrossRefGoogle Scholar
  19. 19.
    Canellas R, Burk KS, Parakh A, Sahani DV (2018) Prediction of pancreatic neuroendocrine tumor grade based on CT features and texture analysis. AJR Am J Roentgenol 210:341–346CrossRefGoogle Scholar
  20. 20.
    Guo C, Chen X, Xiao W, Wang Q, Sun K, Wang Z (2017) Pancreatic neuroendocrine neoplasms at magnetic resonance imaging: comparison between grade 3 and grade 1/2 tumors. Onco Targets Ther 10:1465CrossRefGoogle Scholar
  21. 21.
    Kim DW, Kim HJ, Kim KW et al (2015) Neuroendocrine neoplasms of the pancreas at dynamic enhanced CT: comparison between grade 3 neuroendocrine carcinoma and grade 1/2 neuroendocrine tumour. Eur Radiol 25:1375–1383CrossRefGoogle Scholar
  22. 22.
    Kang J, Ryu JK, Son JH et al (2018) Association between pathologic grade and multiphase computed tomography enhancement in pancreatic neuroendocrine neoplasm. J Gastroenterol Hepatol 33:1677–1682CrossRefGoogle Scholar
  23. 23.
    Zhao W, Quan Z, Huang X et al (2018) Grading of pancreatic neuroendocrine neoplasms using pharmacokinetic parameters derived from dynamic contrast-enhanced MRI. Oncol Lett 15:8349–8356PubMedPubMedCentralGoogle Scholar
  24. 24.
    Lambin P, Leijenaar R, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749CrossRefGoogle Scholar
  25. 25.
    Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006CrossRefGoogle Scholar
  26. 26.
    Chen J, Tian J (2009) Real-time multi-modal rigid registration based on a novel symmetric-SIFT descriptor. Progress in Natural Science-Materials International 19:643-651Google Scholar
  27. 27.
    Cameron A, Khalvati F, Haider MA, Wong A (2016) MAPS: a quantitative radiomics approach for prostate cancer detection. IEEE Trans Biomed Eng 63:1145–1156CrossRefGoogle Scholar
  28. 28.
    Huang YQ, Liang CH, He L et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34:2157–2164CrossRefGoogle Scholar
  29. 29.
    Liu Z, Zhang XY, Shi YJ et al (2017) Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Clin Cancer Res 23:7253–7262CrossRefGoogle Scholar
  30. 30.
    Elhalawani H, Kanwar A, Mohamed ASR et al (2018) Investigation of radiomic signatures for local recurrence using primary tumor texture analysis in oropharyngeal head and neck cancer patients. Sci Rep 8:13CrossRefGoogle Scholar
  31. 31.
    Ger RB, Cardenas CE, Anderson BM, Yang J, Mackin DS, Zhang L (2018) Guidelines and experience using imaging biomarker explorer (IBEX) for Radiomics. J Vis Exp:e57132Google Scholar
  32. 32.
    Zhang B, Tian J, Dong D et al (2017) Radiomics Features of Multiparametric MRI as Novel Prognostic Factors in Advanced Nasopharyngeal Carcinoma. Clin Cancer Res 23:4259–4269Google Scholar
  33. 33.
    Ding JL, Xing ZY, Jiang ZX et al (2018) CT-based radiomic model predicts high grade of clear cell renal cell carcinoma. Eur J Radiol 103:51–56CrossRefGoogle Scholar
  34. 34.
    Huang X, Cheng Z, Huang Y et al (2018) CT-based radiomics signature to discriminate high-grade from Low-grade colorectal adenocarcinoma. Acad Radiol.
  35. 35.
    Tian Q, Yan LF, Zhang X et al (2018) Radiomics strategy for glioma grading using texture features from multiparametric MRI. J Magn Reson Imaging.
  36. 36.
    Peng H, Long F, Ding C (2005) Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27:1226–1238CrossRefGoogle Scholar
  37. 37.
    Phuong TM, Lin Z, Altman RB (2005) Choosing SNPs using feature selection. Computational Systems Bioinformatics Conference 301–309Google Scholar
  38. 38.
    Kramer AA, Zimmerman JE (2007) Assessing the calibration of mortality benchmarks in critical care: the Hosmer-Lemeshow test revisited. Crit Care Med 35:2052–2056CrossRefGoogle Scholar
  39. 39.
    Vickers AJ, Elkin EB (2006) Decision curve analysis: a novel method for evaluating prediction models. Med Decis Mak 26:565–574CrossRefGoogle Scholar
  40. 40.
    Hu Y, Rao S, Xu X, Tang Y, Zeng M (2018) Grade 2 pancreatic neuroendocrine tumors: overbroad scope of Ki-67 index according to MRI features. Abdom Radiol (NY).
  41. 41.
    Kasajima A, Yazdani S, Sasano H (2015) Pathology diagnosis of pancreatic neuroendocrine tumors. J Hepatobiliary Pancreat Sci 22:586–593CrossRefGoogle Scholar
  42. 42.
    Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJ (2015) Machine learning methods for quantitative radiomic biomarkers. Sci Rep 5:13087CrossRefGoogle Scholar
  43. 43.
    Breiman L (2001) Random forests. Mach Learn 45:5–32CrossRefGoogle Scholar
  44. 44.
    Horton KM, Hruban RH, Yeo C, Fishman EK (2006) Multi–detector row CT of pancreatic islet cell tumors. Radiographics 26:453–464CrossRefGoogle Scholar
  45. 45.
    Low G, Panu A, Millo N, Leen E (2011) Multimodality imaging of neoplastic and non-neoplastic solid lesions of the pancreas. Radiographics 31:993–1015CrossRefGoogle Scholar
  46. 46.
    Valle JW, Eatock M, Clueit B, Gabriel Z, Ferdinand R, Mitchell S (2014) "A systematic review of non-surgical treatments for pancreatic neuroendocrine tumours" (vol 40, pg 376, 2014). Cancer Treat Rev 40:1037–1037CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  1. 1.Key Laboratory of Molecular Imaging, Institute of AutomationChinese Academy of SciencesBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina
  3. 3.Department of Radiology, Zhongshan HospitalFudan University and Shanghai Institute of Medical ImagingShanghaiChina
  4. 4.Department of RadiologyAffiliated Hospital (Laoshan hospital) of Qingdao UniversityQingdaoChina
  5. 5.Department of Pathology, Zhongshan HospitalFudan UniversityShanghaiChina
  6. 6.Department of RadiologyCentral Hospital of ZiBoShandongChina
  7. 7.Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of MedicineBeihang UniversityBeijingChina
  8. 8.Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and TechnologyXidian UniversityXi’anChina

Personalised recommendations