Development And Validation Of A Magnetic Resonance Imaging-based Model For The Prediction Of Distant Metastasis Before Initial Treatment Of Nasopharyngeal Carcinoma

ObjectiveWe aimed to identify a magnetic resonance imaging(MRI)-based model for assessment of the risk of individual distant metastasis(DM)before initial treatment of nasopharyngeal carcinoma(NPC).Materials and MethodsThe institutional review board of Guangdong General Hospital approved this retrospective analysis of anonymous data and waived the requirement for informed consent.This retrospective cohort analysis included 176 patients with NPC.Eligible patients were randomly divided into a training cohort(n = 123)and an independent validation cohort(n = 53)in a ratio of 7:3.We acquired axial T2-weighted(T2-w)Digital Imaging and Communications in Medicine(DICOM)images and contrast-enhanced T1-weighted(CET1-w)DICOM images that had been archived using the Picture Archiving and Communication Systems(PACS,Carestream,Canada).Segmentation for regions of interest(ROIs)was performed using ITK-SNAP software,and it for the entire tumor in each patient was delineated on each slice of both axial T2-w and CET1-w images.Using the PyRadiomics platform,we extracted the imaging features of primary tumors in all patients who did not exhibit DM before treatment.Subsequently,we used univariate analysis and multivariate analysis to select the strongest features.Using the final features,we constructed a classification model called a distant metastasis MRI-based model(DMMM),with coefficients weighted by logistic regression analysis in the training cohort.An optimal cutoff value for classifying the patients into low-and high-risk groups based on the risk of DM.Kaplan-Meier survival curves and the log-rank test were used to compare 5-year survival between the high-risk and low-risk groups,and we also performed a subgroup analysis to compare 5-year survival between high-risk patients who received concurrent chemoradiotherapy and low-risk patients who received the same treatment.We used nomogram to achieve visualization.Feature selection and model development were performed in the training cohort,while the independent validation cohort was used to evaluate the performance of the model.The independent statistical significance of multiple clinical variables was tested using multivariate logistic regression analysis.ResultsIn total,2780 radiomic features were extracted.ADM MRI-based model(DMMM)comprising six radiomic features and a clinical variable was constructed for the classification of patients into high-and low-risk groups in a training cohort and validated in an independent cohort.We calculated the risk score for each patient using a formula resulting from the seven features weighted by their regression coefficients.5-year survival was significantly shorter in the high-risk group than in the low-risk group(P<0.001).A radiomics nomogram based on radiomic features and clinical variables was developed for DM risk assessment in each patient,and it showed a significant predictive ability in the training[area under the curve(AUC),0.827;95%confidence interval(CI),0.754-0.900]and validation(AUC,0.792;95%CI,0.633-0.952)cohorts.We also found that DMMM performed better than the radiomic signatures and the clinical model in both the training(AUC,0.792;95%CI,0.633-0.952)and validation(AUC,0.792 vs.0.713 vs.0.660)cohorts.ConclusionsIn conclusion,we developed a novel DMMM combining radiomic features and clinical variables for the prediction of DM before initial treatment in patients with NPC and the differentiation of patients with high and low risks of DM.Our nomogram can serve as a visual prognostic tool that can aid clinicians in identifying patients with a high risk of DM and accordingly optimizing their therapeutic strategies.