Purpose The purpose of this study was to explore the potential value of the radiomics model based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), compared with the clinical model mostly based on the epidermal growth factor receptor (EGFR) expression, in predicting progression-free survival (PFS) in patients with locally advanced nasopharyngeal carcinoma (LA-NPC) treated with nimotuzumab (NTZ). Methods A total of 136 patients with LA-NPC who received NTZ treatment between January 2018 and June 2022 were included in this study. Patients were randomly divided into training (n = 95) and validation (n = 41) groups in a 7:3 ratio. DCE-MRI radiomics, clinical, and clinical-radiomics models were built to predict PFS. The relationship between EGFR expression levels and NTZ efficacy was assessed using Kaplan–Meier curves. Model performance was assessed using the area under the curve, calibration, and DeLong tests. Decision curve analysis evaluated net clinical benefit. Patients were stratified into high- and low-risk groups based on optimal model radiomic scores, and prognoses were compared using Kaplan–Meier curves. Results Univariate Cox regression analysis demonstrated that EGFR expression level was the only independent predictive factor of PFS (p < 0.05). Patients with EGFR 3+ receiving NTZ therapy had significantly longer PFS than those with EGFR 1+ (hazard ratio = 3.025, p < 0.05). The clinical-radiomics model exhibited superior predictive efficacy, compared with the radiomics and clinical models (training set: 0.887 vs. 0.845, 0.654; validation set: 0.831, 0.824 vs. 0.567, all p < 0.001). Conclusions The clinical-radiomics models using DCE-MRI and EGFR levels can effectively predict NTZ efficacy in LA-NPC patients, providing objective evidence for personalized treatment adjustments. Key Points <Emphasis Type="BoldItalic">Question</Emphasis> How can the response to nimotuzumab treatment in patients with locally advanced nasopharyngeal carcinoma be accurately predicted using non-invasive imaging methods? <Emphasis Type="BoldItalic">Findings</Emphasis> A combined clinical and radiomic model using dynamic contrast-enhanced magnetic resonance imaging showed improved predictive performance for progression-free survival in patients treated with nimotuzumab. <Emphasis Type="BoldItalic">Clinical relevance</Emphasis> The study provides evidence for using a combined clinical and radiomic approach, offering a non-invasive method to predict treatment response and guide personalized treatment strategies for patients with locally advanced nasopharyngeal carcinoma, potentially improving patient outcomes.

Predicting progression-free survival using dynamic contrast-enhanced imaging-based radiomics in advanced nasopharyngeal carcinoma patients treated with nimotuzumab

期刊论文
发表日期：

2025年2月14日

查看全文

Xin Jin,
Wen-zhu Li,
Yi-hao Guo,
Gang Wu,
Wei-yuan Huang,
Feng Chen

摘要

Purpose

The purpose of this study was to explore the potential value of the radiomics model based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), compared with the clinical model mostly based on the epidermal growth factor receptor (EGFR) expression, in predicting progression-free survival (PFS) in patients with locally advanced nasopharyngeal carcinoma (LA-NPC) treated with nimotuzumab (NTZ).

Methods

A total of 136 patients with LA-NPC who received NTZ treatment between January 2018 and June 2022 were included in this study. Patients were randomly divided into training (n = 95) and validation (n = 41) groups in a 7:3 ratio. DCE-MRI radiomics, clinical, and clinical-radiomics models were built to predict PFS. The relationship between EGFR expression levels and NTZ efficacy was assessed using Kaplan–Meier curves. Model performance was assessed using the area under the curve, calibration, and DeLong tests. Decision curve analysis evaluated net clinical benefit. Patients were stratified into high- and low-risk groups based on optimal model radiomic scores, and prognoses were compared using Kaplan–Meier curves.

Results

Univariate Cox regression analysis demonstrated that EGFR expression level was the only independent predictive factor of PFS (p < 0.05). Patients with EGFR 3+ receiving NTZ therapy had significantly longer PFS than those with EGFR 1+ (hazard ratio = 3.025, p < 0.05). The clinical-radiomics model exhibited superior predictive efficacy, compared with the radiomics and clinical models (training set: 0.887 vs. 0.845, 0.654; validation set: 0.831, 0.824 vs. 0.567, all p < 0.001).

Conclusions

The clinical-radiomics models using DCE-MRI and EGFR levels can effectively predict NTZ efficacy in LA-NPC patients, providing objective evidence for personalized treatment adjustments.

Key Points

Question How can the response to nimotuzumab treatment in patients with locally advanced nasopharyngeal carcinoma be accurately predicted using non-invasive imaging methods?

Findings A combined clinical and radiomic model using dynamic contrast-enhanced magnetic resonance imaging showed improved predictive performance for progression-free survival in patients treated with nimotuzumab.

Clinical relevance The study provides evidence for using a combined clinical and radiomic approach, offering a non-invasive method to predict treatment response and guide personalized treatment strategies for patients with locally advanced nasopharyngeal carcinoma, potentially improving patient outcomes.