897P - Tumor habitat-based MRI features assessing early response in locally advanced nasopharyngeal carcinoma

Background

The early response to concurrent chemoradiotherapy in patients with locally advanced nasopharyngeal carcinoma (LA-NPC) is closely correlated with prognosis. In this study, we aimed to predict early response using a combined model that combines sub-regional radiomics features from multi-sequence MRI with clinically relevant factors.

Methods

A total of 104 patients with LA-NPC were randomly divided into training and validation cohorts at a ratio of 3:1. Radiomic features were extracted from subregions within the tumor area using the K-means clustering method, and feature selection was performed using LASSO regression. Four models were established: classical radiomics model, clinical medol, Intratumor Heterogeneity (ITH) score-based model and a fusion model combining ITH score with clinical factors. The predictive performance of these models was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).

Results

Among the models, the combined model incorporating ITH score and clinical factors demonstrated the highest predictive performance in the test cohort (AUC = 0.838). Additionally, the models based on ITH score showed superior prognostic value in both the training cohort (AUC = 0.888) and the test cohort (AUC = 0.833).

Conclusions

The combined model that integrates the ITH score with clinical factors exhibited superior performance in predicting early response following concurrent chemoradiotherapy in patients with locally advanced nasopharyngeal carcinoma.

Clinical trial identification

Editorial acknowledgement

The authors would like to thank Yuandong Cao, Weilin Xu, and Shu Zhou for their valuable comments and discussions. We also express their gratitude to Jinling Yuan and Mengxing Wu for their assistance with data analysis. This work was supported by the Jiangsu Province Doctoral Start-up Foundation for Entrepreneurship and Innovation (Grant No. 2019303073386ER19) and the Clinical Competence Enhancement Project of Jiangsu Provincial People's Hospital (Grant No. JSPH-MC-2021-17).

Legal entity responsible for the study

The First Affiliated Hospital of Nanjing Medical University.

Funding

Jiangsu Province Entrepreneurship and Innovation Doctoral Talent Program.

Disclosure

All authors have declared no conflicts of interest.