Abstract
Background/Aim: Sarcopenia is an independent survival predictor in several tumor types. Computed tomography (CT) is the standard measurement for body composition assessment. Radiomics analysis of CT images allows for the precise evaluation of skeletal muscles. This study aimed to construct a prognostic survival model for patients with esophageal cancer who underwent radical irradiation using skeletal muscle radiomics. Patients and Methods: We retrospectively identified patients with esophageal cancer who underwent radical irradiation at our institution between April 2008 and December 2017. Skeletal muscle radiomics were extracted from an axial pretreatment CT at the third lumbar vertebral level. The prediction model was constructed using machine learning coupled with the least absolute shrinkage and selection operator (LASSO). The predictive nomogram model comprised clinical factors with radiomic features. Three prediction models were created: clinical, radiomics, and combined. Results: Ninety-eight patients with 98 esophageal cancers were enrolled in this study. The median observation period was 57.5 months (range=1-98 months). Thirty-five radiomics features were selected by LASSO analysis, and a prediction model was constructed using training and validation data. The average of the accuracy, specificity, sensitivity, and area under the concentration-time curve for predicting survival in esophageal cancer in the combined model were 75%, 92%, and 0.86, respectively. The C-indices of the clinical, radiomics, and combined models were 0.76, 0.80, and 0.88, respectively. Conclusion: A prediction model with skeletal muscle radiomics and clinical data might help determine survival outcomes in patients with esophageal cancer treated with radical radiotherapy.
- Received January 12, 2023.
- Revision received January 20, 2023.
- Accepted January 23, 2023.
- Copyright © 2023 International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved.
This article requires a subscription to view the full text. If you have a subscription you may use the login form below to view the article. Access to this article can also be purchased.