Prediction of programmed death-1 expression status in non-small cell lung cancer based on intratumoural and peritumoral computed tomography (CT) radiomics nomogram

  • 0Department of Radiology, Affiliated Tumor Hospital of Nantong University, Nantong, Jiangsu 226361, PR China.

|

|

Summary

This summary is machine-generated.

This study developed a computed tomography (CT) radiomics nomogram to predict programmed death-1 (PD-1) expression in non-small cell lung cancer (NSCLC). The combined intratumoral and peritumoral CT radiomics model showed high predictive performance for PD-1 status.

Area Of Science

  • Oncology
  • Radiology
  • Medical Imaging

Background

  • Programmed death-1 (PD-1) expression is a crucial biomarker for immunotherapy in non-small cell lung cancer (NSCLC).
  • Accurate prediction of PD-1 expression is vital for guiding treatment decisions in NSCLC patients.

Purpose Of The Study

  • To develop and validate a computed tomography (CT) radiomics nomogram for predicting PD-1 expression in NSCLC.
  • To assess the performance of intratumoral and peritumoral radiomic features in predicting PD-1 status.

Main Methods

  • Retrospective analysis of 200 NSCLC patients from two institutions.
  • Extraction of radiomic features from gross tumor volume (GTV) and peritumoral volume (PTV) on CT images.
  • Development of a CT radiomics nomogram incorporating GTV, PTV, and clinical predictors (prealbumin, monocyte).

Main Results

  • The combined GTV + PTV radiomics model demonstrated superior predictive performance compared to individual models.
  • The nomogram integrating radiomics features and clinical predictors achieved high area under the curve (AUC) values (0.92, 0.88, 0.80) across training, internal, and external validation cohorts.
  • Prealbumin and monocyte were identified as independent clinical predictors.

Conclusions

  • The developed intratumoral and peritumoral CT radiomics nomogram shows promise for individualized prediction of PD-1 expression in NSCLC.
  • This tool may aid in optimizing immunotherapy selection for NSCLC patients.