CT-based intratumoral heterogeneity predicts immunochemotherapy response in lung cancer

A CT-derived intratumoral heterogeneity model achieved AUCs of 0.824 (training) and 0.792 (validation) for predicting major pathological response to neoadjuvant immunochemotherapy in resectable NSCLC. The model combined 2D and 3D heterogeneity scores and systemic inflammation in…

• In a two-center study of 287 patients, CatBoost model using CT-derived 2D and 3D intratumoral heterogeneity scores and systemic immune-inflammation index predicted MPR.
• 2D and 3D ITHscores were the most influential predictors per SHAP analysis, with mean absolute SHAP values of 0.403 and 0.326.
• The model was externally validated at Center B (AUC 0.792) after training at Center A (AUC 0.824).

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.