(Tuesday, 7/16/2019) 1:15 PM - 1:45 PM
Room: Exhibit Hall | Forum 2
Purpose: To investigate the treatment response prediction feasibility and accuracy of an integrated model combining computed tomography (CT) radiomic features and dosimetric parameters for patients with esophageal cancer (EC) who underwent concurrent chemoradiation (CRT) using machine learning.
Methods: The radiomics features and dosimetric parameters of 94 EC patients were extracted and modeled using Support Vector Classification (SVM) and Extreme Gradient Boosting algorithm (XGBoost). The 94-sample dataset was randomly divided into a 70-sample training subset and a 24-sample independent test set while keeping the class proportions intact via stratification. A receiver operating characteristic (ROC) curve was used to assess the performance of models using radiomics features alone and using combined radiomics features and dosimetric parameters.
Results: A total of 42 radiomics features and 18 dosimetric parameters plus the patients’ characteristic parameters were extracted for these 94 cases (58 responders and 36 non-responders). XGBoost plus principal component analysis (PCA) achieved an accuracy and area under the curve of 0.708 and 0.541, respectively, for models with radiomics features combined with dosimetric parameters, and 0.689 and 0.479, respectively, for radiomics features alone. Image features of GlobalMean X.333.1, Coarseness, Skewness, and GlobalStd contributed most to the model. The dosimetric parameters of gross tumor volume (GTV) homogeneity index (HI), Cord Dmax, Prescription dose, Heart-Dmean and Heart-V50 also had a strong contribution to the model.
Conclusion: The model with radiomics features combined with dosimetric parameters is promising and outperforms that with radiomics features alone in predicting the treatment response of patients with EC who underwent CRT.
Keywords
Not Applicable / None Entered.
Taxonomy
Not Applicable / None Entered.
Contact Email
