In this study, we focused on 65 patients with NPC having undergone RHES + CCRT, among whom 41 (63.0%) were allocated to the responder group and 24 to the non-responder group. The tumor treatment response of our study was evaluated at the end of the RHES + CCRT treatment. This was different from the previous studies, which remain only about 16% of patients treated with CCRT remained residual tumour 6 months after the treatment(Chen et al. 2019). According to recent studies, the RHES + IMRT treatment has shown good therapeutic effects and good safety in the clinical treatment of patients with NPC (Xu et al. 2013).
Since the use of RHES for the treatment of tumors is still in phase III clinical trials, there were fewer NPC patients treated with this drug. In addition, this study strictly adhered to the enrollment requirements and included only patients with locally advanced NPC treated with RHES + CCRT. Therefore, the number of cases included in this study was relatively small. Considering the small sample size of the data, we did not split the data into training and validation groups; however, 10-fold cross-validation was applied, proving that texture analysis was valuable in discriminating between responder and non-responder groups and that the result was not due to overfitting. Future researches with a larger sample size are needed in the future overcome such challenges.
Recently, to predict the early response to treatment in patients with NPC, the following three imaging modalities are commonly used: diffusion-weighted MR imaging (DWI) (Chen et al. 2014), intravoxel incoherent motion diffusion weighted MR imaging (IVIM-DWI) (Xiao et al. 2015), and dynamic CE MR imaging (DCE-MRI) (Zheng et al. 2017). However, researches on the early response of RHES + CCRT in patients with NPC using these imaging modalities are relatively rare. In a study on mice with colon carcinoma, researchers explored non-invasive methods to monitor RHES -induced tumor vascular normalization and found IVIM DWI-MRI to be a promising method (Pan et al. 2018). Based on the principle that radiomics can reflect the heterogeneity of tumors and is related to treatment efficacy and prognosis, we established and validated a multi-parameter MRI-based radiomics approach to predict early response to RHES + CCRT in patients with advanced NPC.
In our research, the AUC values of the combined model and radiomics model were 0.74 and 0.71, respectively, and both of them were higher than the AUC of the clinics model (AUC = 0.63). Compared with the radiomics model, the combined model, which combined imaging texture features with selected clinical factors (shortest diameter), showed marginally improved diagnostic performance in predicting treatment response to RHES + CCRT. The role of the combination of radiomics and clinical factors needs to be clarified. In our study, even though the baseline shortest diameter was the only aspect that significantly differed between responders and non-responders, we found the combined model to be better than the radiomics model or clinics model alone. Notably, the endpoint in this study was clinical treatment response after RHES + CCRT. The model combined radiomics and clinical factors seemed to be more sensitively and closely related to our defined clinical endpoint (the endpoint in this study was clinical treatment response after RHES + CCRT) when compared with radiomics or clinical information alone. It is expected that instead of functional MRI technology, a reliable predictive model can be constructed using conventional sequence texture features to predict the response of RHES + CCRT in patients with NPC in the future. In a retrospective study, a radiomic nomogram was established by combining a radiomics signature with TNM, which showed significantly better prediction of progression-free survival(PFS) in patients with NPC than TNM alone (Zhang et al. 2017). One study reported the development of a radiomics nomogram that integrated radiomics signatures from the joint T1-CE, T1-WI, and T2-WI with all the clinical factors. This radiomics nomogram provided a higher concordance index (C-index) in both the training cohort (TC) and validation cohort (VC), suggesting that this model was more accurate than the clinics model or radiomics signature model in predicting IC response in patients with NPC (Zhao et al. 2020). In another study, scholars found that a model that factored in T1-CE-based uniformity, tumor volume, and the overall stage had better predictive power than a model factoring in either tumor volume or the overall stage in terms of the PFS, and the AUC values were 0.825, 0.659, and 0.616, respectively (Mao et al. 2019). Therefore, it can be concluded that the combined model based on radiomics and clinics models better predicted treatment response of patients with NPC to different regimens.
In our study, the finally retained eight texture features that were strongly related to responder and non-responder labeling of the patients were calculated from T2WI_FS, including T2WI_FS_GLCM, T2WI_FS_GLRLM and T2WI_FS_Shape. The established model and prediction accuracies varied with different research designs. Simultaneously, the types and numbers of extracted imaging features would differ among different modeling methods (Shu et al. 2019). One study focused on two different treatments in patients with advanced NPC and compared the performance of radiomics in predicting IC response to both the treatments. In that study, a total of 1188 imaging features were extracted from joint T1-CE, T1-WI, and T2-WI, and the researchers reported that the features extracted from these three sequences had good performance in predicting treatment response, with the accuracy of TC and VC being 0.852 and 0.853, respectively (Zhang et al. 2020). In the study of Zhao et al., the results also showed that a model based on joint T1-CE, T1-WI, and T2-WI had a better prognostic performance in evaluating IC response than a radiomic characteristic model (Zhao et al. 2020). The features of multi-parameter MRI described the distribution of voxel intensity within the image as well as represented the heterogeneity of NPC (Zhuo et al. 2019). For example, GLCM-based features reflected tumor roughness and heterogeneity(Zhang et al. 2020).
Our results suggest that the accuracy of combined model and radiomics model for RHES + CCRT response assessment in NPC were better than those of the clinics model (0.723, 0.723 vs. 0.677). At the same time, we found that the accuracy of combined model and radiomics model were the same. There was not any improvement in the accuracy by combining the imaging texture features with selected clinical factors (shortest diameter). Based on the radiomics signature of MR imaging, a predictive factor was developed to preoperatively discriminate between responders or non-responders scheduled to undergo RHES + CCRT treatment for NPC. This would allow individuals identified as non-responders to avoid predictably ineffective RHES + CCRT. However, before a radiomics signature can be considered as clinically useful and applicable, further external verification and standardized data processing methods are required because the PPV for the combined model was 0.600.
Our study had some limitations. First, this study was a single-center study, which may limit the applicability of our research results to patients from other institutions, and further external validation research is needed to expand this applicability. Second, only anatomical MRI technology was used for research, and functional MRI was not included in the research design. Third, our study was based on RECIST 1.1. We delineated tumor response or non-response by volume changes before and after RHES + CCRT, which may not be the best indicator for clinical results. Fourth, this study did not carry out related studies on the lymph node metastasis of the neck region of NPC at the same time, and this part of the content still has certain challenges. Finally, varying doses of radiation of NPC patients were adopted for radiotherapy regimen. These different strategies might be confounding factors for the evaluation of response.
In conclusion, in this study, pretreatment MRI-based radiomics could predict RHES + CCRT response better than clinical factors in patients with NPC. The radiomics signature as a non-invasive MR-based imaging biomarker may provide a valuable and practical method for promoting personalized treatment for and optimizing the management of patients with NPC.