Radiomics-based explainable artificial intelligence to predict treatment response following lung stereotactic body radiation therapy.

Objective: To develop and validate a CT-based radiomic-clinical-dosimetric model to assess the treatment response of lung metastasis following stereotactic body radiation therapy (SBRT).

Methods: 80 lung metastases treated with SBRT curative intent in a single institution were analyzed. The treatment responses of lung lesions were categorized as a complete responding (CR) group vs. a non-complete responding (NCR) group according to RECIST criteria. For each lesion, 107 features were extracted from the CT planning images. The least absolute shrinkage and selection operator (LASSO) was used for features selection. An eXtreme Gradient Boosting (XGBoost) model was trained and validated. SHAP analysis was used to provide insights into the impact of each variable on the model's predictions.

Results: Eight radiomic features, one dosimetric variable and no clinical variables were identified by LASSO and used to build the XGBoost model. The model yielded AUCs of 0.897 (95%CI 0.860-0.935) and 0.864 (95%CI 0.803-0.924) in the training cohort and validation cohort, respectively. Skewness, surface-volume ratio, sphericity and BED10 were the most significant variables in predicting CR. The SHAP plots illustrated the feature's global and local impact to the model, explaining the model output in a clinician-friendly way.

Conclusion: The integration of the XGBoost model with the SHAP strategy was able to assess lung lesions CR following SBRT, with the potential to assist clinicians in directing personalized SBRT strategies in an understandable manner.

Advances in knowledge: The explanaible radiomics model we propose can better predict the treatment response of lung metastasis after SBRT and provide further guidance for clinical practice.