Radiomics on multi-modalities MR sequences can subtype patients with non-metastatic nasopharyngeal carcinoma (NPC) into distinct survival subgroups
- 78 Downloads
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.
• 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.
KeywordsNasopharynx Magnetic resonance imaging Radiomics Survival analysis
Abbreviations and acronyms
American Joint Committee on Cancer
Intensity-modulated radiation therapy
Locoregional recurrence-free survival
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.
Written informed consent was waived by the Institutional Review Board.
Institutional Review Board approval was obtained.
• diagnostic or prognostic study
• performed at one institution
- 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
- 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
- 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
- 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
- 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