Baseline MRI-based radiomics model assisted predicting disease progression in nasopharyngeal carcinoma patients with complete response after treatment

Dan Bao,Zhou Liu,Dehong Luo,Yayuan Geng,Yanfeng Zhao,Haijun Xu,Lin Li,Xinming Zhao,Ya Zhang,Lei Hu

doi:10.1186/s40644-022-00448-4

Abstract

BackgroundAccurate pretreatment prediction for disease progression of nasopharyngeal carcinoma is key to intensify therapeutic strategies to high-risk individuals. Our aim was to evaluate the value of baseline MRI-based radiomics machine-learning models in predicting the disease progression in nasopharyngeal carcinoma patients who achieved complete response after treatment.MethodsIn this retrospective study, 171 patients with pathologically confirmed nasopharyngeal carcinoma were included. Using hold-out cross validation scheme (7:3), relevant radiomic features were selected with the least absolute shrinkage and selection operator method based on baseline T2-weighted fat suppression and contrast-enhanced T1-weighted images in the training cohort. After Pearson’s correlation analysis of selected radiomic features, multivariate logistic regression analysis was applied to radiomic features and clinical characteristics selection. Logistic regression analysis and support vector machine classifier were utilized to build the predictive model respectively. The predictive accuracy of the model was evaluated by ROC analysis along with sensitivity, specificity and AUC calculated in the validation cohort.ResultsA prediction model using logistic regression analysis comprising 4 radiomics features (HGLZE_T2H, HGLZE_T1, LDLGLE_T1, and GLNU_T1) and 5 clinical features (histology, T stage, N stage, smoking history, and age) showed the best performance with an AUC of 0.75 in the training cohort (95% CI: 0.66–0.83) and 0.77 in the validation cohort (95% CI: 0.64–0.90). The nine independent impact factors were entered into the nomogram. The calibration curves for probability of 3-year disease progression showed good agreement. The features of this prediction model showed satisfactory clinical utility with decision curve analysis.ConclusionsA radiomics model derived from pretreatment MR showed good performance for predicting disease progression in nasopharyngeal carcinoma and may help to improve clinical decision making.

Highlights

Accurate pretreatment prediction for disease progression of nasopharyngeal carcinoma is key to intensify therapeutic strategies to high-risk individuals
The results of correlation analysis showed that age (P = 0.04), gender (P = 0.01) and smoking history (P = 0.02) were significantly associated with disease progression but not for other clinical variables (P > 0.05)
The best performance was found in the model trained with both 4 radiomic features and 5 clinical features (Model L4), with an area under the curve (AUC) of 0.75 in the training cohort and 0.77 in the validation cohort

Summary

Introduction

Accurate pretreatment prediction for disease progression of nasopharyngeal carcinoma is key to intensify therapeutic strategies to high-risk individuals. Our aim was to evaluate the value of baseline MRI-based radiomics machine-learning models in predicting the disease progression in nasopharyngeal carcinoma patients who achieved complete response after treatment. Despite proven effectiveness of radiotherapy and chemotherapy, treatment failure due to locoregional recurrence or distant metastasis occurs in nearly 10–15% of patients during the first 2 years after tumor remission [3]. It is vital to identify those NPC patients with high risk of disease progression after remission, so as to individualize treatment plan and better manage NPC. Tumor-node-metastasis (TNM) staging system has been widely used to predict prognosis of patients with NPC. NPCs with same TNM stage can have completely different responses to chemoradiotherapy and prognosis [4], part of which may be attributed to the fact that TNM staging system mainly reflects the relationship between tumor and surrounding anatomical structures and ignores intra-tumor characteristics, including tumor morphology itself, morphological heterogeneity, etc. [5]

Objectives

Methods

Results

Discussion

Conclusion