Enhancing Nasopharyngeal Carcinoma Survival Prediction: Integrating Pre- and Post-Treatment MRI Radiomics with Clinical Data

Abstract

Recurrences are frequent in nasopharyngeal carcinoma (NPC) despite high remission rates with treatment, leading to considerable morbidity. This study aimed to develop a prediction model for NPC survival by harnessing both pre- and post-treatment magnetic resonance imaging (MRI) radiomics in conjunction with clinical data, focusing on 3-year progression-free survival (PFS) as the primary outcome. Our comprehensive approach involved retrospective clinical and MRI data collection of 276 eligible NPC patients from three independent hospitals (180 in the training cohort, 46 in the validation cohort, and 50 in the external cohort) who underwent MRI scans twice, once within 2 months prior to treatment and once within 10 months after treatment. From the contrast-enhanced T1-weighted images before and after treatment, 3404 radiomics features were extracted. These features were not only derived from the primary lesion but also from the adjacent lymph nodes surrounding the tumor. We conducted appropriate feature selection pipelines, followed by Cox proportional hazards models for survival analysis. Model evaluation was performed using receiver operating characteristic (ROC) analysis, the Kaplan-Meier method, and nomogram construction. Our study unveiled several crucial predictors of NPC survival, notably highlighting the synergistic combination of pre- and post-treatment data in both clinical and radiomics assessments. Our prediction model demonstrated robust performance, with an accuracy of AUCs of 0.66 (95% CI: 0.536-0.779) in the training cohort, 0.717 (95% CI: 0.536-0.883) in the testing cohort, and 0.827 (95% CI: 0.684-0.948) in validation cohort in prognosticating patient outcomes. Our study presented a novel and effective prediction model for NPC survival, leveraging both pre- and post-treatment clinical data in conjunction with MRI features. Its constructed nomogram provides potentially significant implications for NPC research, offering clinicians a valuable tool for individualized treatment planning and patient counseling.

Keywords: Artificial intelligence; Magnetic resonance radiomics; Nasopharyngeal carcinoma; Prognosis.

Fig. 1

Flow chart on clinical and MRI data collection process of eligible NPC patients

Fig. 2

Clinical and radiomics feature extraction workflow in this study. Radiomics features were extracted from ROI segmentations of pre- and post-treatment MRI images by PyRadiomics and then screened for highly correlated variables using Pearson’s before being input into LASSO regression (a tenfold cross-validation was applied to select the optimal penalty parameter λ, resulting in λ = 0.1486442 for pre-radiomics and λ = 0.06743348 for post-radiomics). Clinical variables underwent a similar screening process through the Pearson correlation analysis and were subsequently divided into two groups: categorical and continuous variables. These variables were analyzed to determine their statistical significance on survival rate using the F-test for categorical variables and the T-test for continuous variables. The selected variables were then evaluated for univariate survival association

Fig. 3

ROC curves were plotted for four models: the clinical model, pre-radiomics model, post-radiomics model, assembling pre- and post-radiomics model, and assembling clinical, pre-, and post-radiomics model in a training cohort, b testing cohort, and c validation cohort. Pairwise comparisons of the area under the ROC curves (d) were conducted, specifically focusing on the assembled clinical, pre-, and post-radiomics model against the other models across different cohorts. All analyses were based on predictions of 3-year progression-free survival (PFS)

Fig. 4

The Kaplan–Meier survival analysis of risk levels was computed from clinical, pre-, and post-treatment MRI risk scores in a training cohort, b testing cohort, and c validation cohort, with respect to 3-year progression-free survival (PFS)

Fig. 5

a An established nomogram including clinical and risk factor scores derived from clinical and radiomics predictors for 3-year and 5-year progression-free survival, and b calibration curves to estimate progression-free survival in NPC patients