Libin Liu

Analysis code for predicting radiation esophagitis after lung cancer radiotherapy using dose-volume, radiomic and dosiomic features

This software package contains the analysis code supporting the study “Predicting radiation esophagitis after lung cancer radiotherapy using dose-volume, radiomic and dosiomic features: an external validation study”. It includes DICOM data quality control and preprocessing, ROI-specific feature extraction, direct elastic-net logistic regression, nested cross-validation, frozen external validation, paired DeLong tests, stratified bootstrap confidence intervals, calibration analysis and decision-curve analysis. Patient-level clinical data, DICOM files, patient identifiers and model prediction files are not included. The software is released under the BSD 3-Clause License.