JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

CT-radiomics combined with inflammatory indicators for prediction of progression free survival of resectable esophageal squamous cell carcinoma

  • 0Department of Medical Imaging, The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University, Huai'an, Jiangsu, China.
Scientific Reports +

|

May 10, 2025

|

May 10, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

A new nomogram model combining inflammatory indicators and CT radiomics effectively predicts progression-free survival (PFS) in esophageal squamous cell carcinoma (ESCC) patients post-surgery. This tool aids in risk stratification and improving patient outcomes.

Area Of Science

  • Oncology
  • Radiology
  • Medical Informatics

Background

  • Esophageal squamous cell carcinoma (ESCC) is a significant cause of cancer mortality.
  • Accurate prediction of progression-free survival (PFS) is crucial for effective management of ESCC patients after radical surgery.
  • Current predictive models may not fully integrate diverse prognostic factors.

Purpose Of The Study

  • To develop and validate a nomogram model for predicting PFS in ESCC patients.
  • To combine clinical inflammatory indicators and CT radiomics features for enhanced predictive accuracy.
  • To assess the model's utility in risk stratification and guiding follow-up strategies.

Main Methods

  • Retrospective analysis of 258 ESCC patients who underwent radical surgery.
  • Integration of clinical data, laboratory results, pathology, and pre-operative CT radiomics features.
  • Development and validation using Cox regression, C-index, calibration curves, DeLong test, and Decision Curve Analysis (DCA).

Main Results

  • The combined nomogram model demonstrated superior predictive efficacy for PFS compared to inflammatory or radiomics models alone in both training and test sets.
  • Significant differences in PFS were observed between high-risk and low-risk groups identified by the nomogram (P < 0.001).
  • The nomogram model showed better net benefit in Decision Curve Analysis, indicating clinical utility.

Conclusions

  • A nomogram integrating inflammatory markers and CT radiomics provides a robust tool for predicting PFS in ESCC patients post-operation.
  • This model facilitates accurate risk stratification, potentially improving patient prognosis and guiding personalized follow-up care.
  • The combined approach offers a more comprehensive assessment than individual feature sets.

Keywords: