Radiomics on multi-modalities MR sequences can subtype patients with non-metastatic nasopharyngeal carcinoma (NPC) into distinct survival subgroups

  • En-Hong Zhuo
  • Wei-Jing Zhang
  • Hao-Jiang Li
  • Guo-Yi Zhang
  • Bing-Zhong Jing
  • Jian Zhou
  • Chun-Yan Cui
  • Ming-Yuan Chen
  • Ying Sun
  • Li-Zhi LiuEmail author
  • Hong-Min CaiEmail author
Head and Neck



To explore and evaluate the feasibility of radiomics in stratifying nasopharyngeal carcinoma (NPC) into distinct survival subgroups through multi-modalities MRI.


A total of 658 patients (training cohort: 424; validation cohort: 234) with non-metastatic NPC were enrolled in the retrospective analysis. Each slice was considered as a sample and 4863 radiomics features on the tumor region were extracted from T1-weighted, T2-weighted, and contrast-enhanced T1-weighted MRI. Consensus clustering and manual aggregation were performed on the training cohort to generate a baseline model and classification reference used to train a support vector machine classifier. The risk of each patient was defined as the maximum risk among the slices. Each patient in the validation cohort was assigned to the risk model using the trained classifier. Harrell’s concordance index (C-index) was used to measure the prognosis performance, and differences between subgroups were compared using the log-rank test.


The training cohort was clustered into four groups with distinct survival patterns. Each patient was assigned to one of the four groups according to the estimated risk. Our method gave a performance (C-index = 0.827, p < .004 and C-index = 0.814, p < .002) better than the T-stage (C-index = 0.815, p = .002 and C-index = 0.803, p = .024), competitive to and more stable than the TNM staging system (C-index = 0.842, p = .003 and C-index = 0.765, p = .050) in the training cohort and the validation cohort.


Through investigating a large one-institutional cohort, the quantitative multi-modalities MRI image phenotypes reveal distinct survival subtypes.

Key Points

• Radiomics phenotype of MRI revealed the subtype of nasopharyngeal carcinoma (NPC) patients with distinct survival patterns.

• The slice-wise analysis method on MRI helps to stratify patients and provides superior prognostic performance over the TNM staging method.

• Risk estimation using the highest risk among slices performed better than using the majority risk in prognosis.


Nasopharynx Magnetic resonance imaging Radiomics Survival analysis 

Abbreviations and acronyms


American Joint Committee on Cancer


Confidence interval


Epstein-Barr virus


Gastric cancer


Intensity-modulated radiation therapy


Locoregional recurrence-free survival


Nasopharyngeal carcinoma


Primary gastric lymphoma


Region of interest


Tumor, node and metastasis


Union for International Cancer Control



This work was supported by grants from the National Natural Science Foundation of China (no.61771007, no.81572652), Health & Medical Collaborative Innovation Project of Guangzhou City, China (grants 201604020003, 201803010021), Science and Technology Planning Projects of Guangdong Province (2016A010101013, 2017B020226004), and the Fundamental Research Fund for the Central Universities (2017ZD051).

Compliance with ethical standards


The scientific guarantor of this publication is Hong-min Cai.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.


• retrospective

• diagnostic or prognostic study

• performed at one institution

Supplementary material

330_2019_6075_MOESM1_ESM.doc (76 kb)
ESM 1 (DOC 76 kb)


  1. 1.
    Yao J, Zhou G, Wang Y et al (2017) Prognostic values of the integrated model incorporating the volume of metastatic regional cervical lymph node and pretreatment serum Epstein–Barr virus DNA copy number in predicting distant metastasis in patients with N1 nasopharyngeal carcinoma. Chin J Cancer 36:98CrossRefGoogle Scholar
  2. 2.
    Feng X, Lin J, Xing S, Liu W, Zhang G (2017) Higher IGFBP-1 to IGF-1 serum ratio predicts unfavourable survival in patients with nasopharyngeal carcinoma. BMC Cancer 17:90CrossRefGoogle Scholar
  3. 3.
    Zhang L, Li Y, Hu J et al (2018) Proposal of a pretreatment nomogram for predicting local recurrence after intensity-modulated radiation therapy in t4 nasopharyngeal carcinoma: a retrospective review of 415 Chinese patients. Cancer Res Treat 50:1084CrossRefGoogle Scholar
  4. 4.
    Xu Y, Zheng Z, Gao Y et al (2017) High expression of IMPDH2 is associated with aggressive features and poor prognosis of primary nasopharyngeal carcinoma. Sci Rep-UK 7:745CrossRefGoogle Scholar
  5. 5.
    He S, Wang Y, Chen H et al (2016) C-reactive protein/albumin ratio (CAR) as a prognostic factor in patients with non-metastatic nasopharyngeal carcinoma. J Cancer 7:2360CrossRefGoogle Scholar
  6. 6.
    Yuan H, Ai Q, Kwong DL et al (2017) Cervical nodal volume for prognostication and risk stratification of patients with nasopharyngeal carcinoma, and implications on the TNM-staging system. Sci Rep-UK 7:10387CrossRefGoogle Scholar
  7. 7.
    Du X, Tang L, Mao Y et al (2016) Circulating EBV DNA, globulin and nodal size predict distant metastasis after intensity-modulated radiotherapy in stage II nasopharyngeal carcinoma. J Cancer 7:664CrossRefGoogle Scholar
  8. 8.
    Chang S, Chan T, Chen T, Lee S, Lin L, Win KT (2017) HOXC6 overexpression is associated with ki-67 expression and poor survival in NPC patients. J Cancer 8:1647CrossRefGoogle Scholar
  9. 9.
    Chen J, Li S, Xiao Y et al (2017) P53R2 as a novel prognostic biomarker in nasopharyngeal carcinoma. BMC Cancer 17:846CrossRefGoogle Scholar
  10. 10.
    He Y, Jing Y, Wei F et al (2018) Long non-coding RNA PVT1 predicts poor prognosis and induces radioresistance by regulating DNA repair and cell apoptosis in nasopharyngeal carcinoma. Cell Death Dis 9:235CrossRefGoogle Scholar
  11. 11.
    Aerts HJWL, Velazquez ER, Leijenaar RTH et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5Google Scholar
  12. 12.
    Huang Y, Liang C, 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
  13. 13.
    Kickingereder P, Burth S, Wick A et al (2016) Radiomic profiling of glioblastoma: identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models. Radiology 280:880–889CrossRefGoogle Scholar
  14. 14.
    Li H, Zhu Y, Burnside ES et al (2016) MR imaging radiomics signatures for predicting the risk of breast cancer recurrence as given by research versions of MammaPrint, Oncotype DX, and PAM50 gene assays. Radiology 281:382–391CrossRefGoogle Scholar
  15. 15.
    Lv W, Yuan Q, Wang Q et al (2018) Robustness versus disease differentiation when varying parameter settings in radiomics features: application to nasopharyngeal PET/CT. Eur Radiol:1–10Google Scholar
  16. 16.
    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 23:4259–4269CrossRefGoogle Scholar
  17. 17.
    Zhang B, He X, Ouyang F et al (2017) Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma. Cancer Lett 403:21–27CrossRefGoogle Scholar
  18. 18.
    Liu J, Mao Y, Li Z et al (2016) Use of texture analysis based on contrast-enhanced MRI to predict treatment response to chemoradiotherapy in nasopharyngeal carcinoma. J Magn Reson Imaging 44:445–455CrossRefGoogle Scholar
  19. 19.
    Wang G, He L, Yuan C, Huang Y, Liu Z, Liang C (2018) Pretreatment MR imaging radiomics signatures for response prediction to induction chemotherapy in patients with nasopharyngeal carcinoma. Eur J Radiol 98:100–106CrossRefGoogle Scholar
  20. 20.
    Mao J, Fang J, Duan X et al (2019) Predictive value of pretreatment MRI texture analysis in patients with primary nasopharyngeal carcinoma. Eur Radiol:1–9Google Scholar
  21. 21.
    Liu H, Zhao R, Fang H, Cheng F, Fu Y, Liu Y (2017) Entropy-based consensus clustering for patient stratification. Bioinformatics 33:2691–2698CrossRefGoogle Scholar
  22. 22.
    Amin MB, Edge S, Greene F et al (2017) AJCC cancer staging manual. Springer, New YorkCrossRefGoogle Scholar
  23. 23.
    Pan J, Xu Y, Qiu S et al (2015) A comparison between the Chinese 2008 and the 7th edition AJCC staging systems for nasopharyngeal carcinoma. Am J Clin Oncol 38:189–196CrossRefGoogle Scholar
  24. 24.
    Tang L, Chen Y, Mao Y et al (2017) Validation of the 8th edition of the UICC/AJCC staging system for nasopharyngeal carcinoma from endemic areas in the intensity-modulated radiotherapy era. J Natl Compr Canc Netw 15:913–919CrossRefGoogle Scholar
  25. 25.
    Kang M, Zhou P, Li G et al (2017) Validation of the 8th edition of the UICC/AJCC staging system for nasopharyngeal carcinoma treated with intensity-modulated radiotherapy. Oncotarget 8:70586Google Scholar
  26. 26.
    Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446CrossRefGoogle Scholar
  27. 27.
    Ma Z, Fang M, Huang Y et al (2017) CT-based radiomics signature for differentiating Borrmann type IV gastric cancer from primary gastric lymphoma. Eur J Radiol 91:142–147CrossRefGoogle Scholar
  28. 28.
    Huang Y, Liu Z, He L et al (2016) Radiomics signature: a potential biomarker for the prediction of disease-free survival in early-stage (i or ii) non-small cell lung cancer. Radiology 281:947–957CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  • En-Hong Zhuo
    • 1
  • Wei-Jing Zhang
    • 2
  • Hao-Jiang Li
    • 2
  • Guo-Yi Zhang
    • 3
  • Bing-Zhong Jing
    • 2
  • Jian Zhou
    • 2
  • Chun-Yan Cui
    • 2
  • Ming-Yuan Chen
    • 2
  • Ying Sun
    • 2
  • Li-Zhi Liu
    • 2
    Email author
  • Hong-Min Cai
    • 1
    • 4
    Email author
  1. 1.School of Computer Science and EngineeringSouth China University of TechnologyGuangzhouPeople’s Republic of China
  2. 2.State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and TherapySun Yat-sen University Cancer CenterGuangzhouPeople’s Republic of China
  3. 3.Department of Radiation Oncology, Cancer CenterFirst People’s Hospital of FoshanFoshanPeople’s Republic of China
  4. 4.Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information, South China University of TechnologyGuangzhouPeople’s Republic of China

Personalised recommendations