JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

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

  • 0Department of Radiology, Hainan Affiliated Hospital of Hainan Medical University (Hainan General Hospital), Haikou, China.
European Radiology +

|

February 14, 2025

|

February 14, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

A new clinical-radiomics model combining imaging and EGFR levels accurately predicts nimotuzumab treatment response in locally advanced nasopharyngeal carcinoma (LA-NPC) patients, aiding personalized therapy.

Area Of Science

  • Oncology
  • Radiology
  • Medical Imaging

Background

  • Locally advanced nasopharyngeal carcinoma (LA-NPC) treatment response can be challenging to predict.
  • Epidermal growth factor receptor (EGFR) expression is a known factor, but non-invasive predictive models are needed.

Purpose Of The Study

  • To evaluate a radiomics model from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for predicting progression-free survival (PFS) in LA-NPC patients treated with nimotuzumab (NTZ).
  • To compare the radiomics model's predictive value against a clinical model based on EGFR expression.

Main Methods

  • 136 LA-NPC patients treated with NTZ were analyzed.
  • Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics, clinical, and combined clinical-radiomics models were developed to predict PFS.
  • Model performance was assessed using area under the curve, calibration, and DeLong tests.

Main Results

  • EGFR expression level was the sole independent predictor of PFS (p < 0.05).
  • Patients with higher EGFR expression (3+) had significantly longer PFS (HR = 3.025, p < 0.05).
  • The combined clinical-radiomics model demonstrated superior predictive efficacy over individual models in both training and validation sets (AUCs > 0.83, p < 0.001).

Conclusions

  • Clinical-radiomics models integrating DCE-MRI and EGFR levels effectively predict nimotuzumab efficacy in LA-NPC.
  • This approach offers objective evidence for personalized treatment adjustments and improved patient outcomes.

Keywords: