Development and Validation of an 18F-FDG PET/CT-based Radiomics Nomogram for Predicting the Prognosis of Patients with Esophageal Squamous Cell Carcinoma.

RATIONALE AND

OBJECTIVES

The aim of this study was to develop and validate a nomogram, integrating clinical factors and radiomics features, capable of predicting overall survival (OS) in patients diagnosed with esophageal squamous cell carcinoma (ESCC).

METHODS

In this study, we retrospectively analyzed the case data of 130 patients with ESCC who underwent 18F-FDG PET/CT before treatment. Radiomics features associated with OS were screened by univariate Cox regression (p < 0.05). Further selection was performed by applying the least absolute shrinkage and selection operator Cox regression to generate the weighted Radiomics-score (Rad-score). Independent clinical risk factors were obtained by multivariate Cox regression, and a nomogram was constructed by combining Rad-score and independent risk factors. The predictive performance of the model for OS was assessed using the time-dependent receiver operating characteristic curve, concordance index (C-index), calibration curve, and decision curve analysis.

RESULTS

Five radiomics features associated with prognosis were finally screened, and a Rad-score was established. Multivariate Cox regression analysis revealed that surgery and clinical M stage were identified as independent risk factors for OS in ESCC. The combined clinical-radiomics nomogram exhibited C-index values of 0.768 (95% CI: 0.699-0.837) and 0.809 (95% CI: 0.695-0.923) in the training and validation cohorts, respectively. Ultimately, calibration curves and decision curves for the 1-, 2-, and 3-year OS demonstrated the satisfactory prognostic prediction and clinical utility of the nomogram.

CONCLUSION

The developed nomogram, leveraging 18F-FDG PET/CT radiomics and clinically independent risk factors, demonstrates a reliable prognostic prediction for patients with ESCC, potentially serving as a valuable tool for guiding and optimizing clinical treatment decisions in the future.