CT Radiomics Model Predicts Airspace Spread Grade in Lung Cancer

CT radiomics model predicts spread through air spaces (STAS) grade in lung adenocarcinoma; STAS grade II independently linked to worse recurrence-free survival (P=0.037). Random forest detected STAS with AUC 0.886 internally and 0.779 externally, aiding surgical decisions.

• STAS grade II (dissemination distance >2500 µm) was an independent predictor of poorer recurrence-free survival, while grade I was not, improving prognostic stratification.
• For STAS detection, a random forest classifier achieved an AUC of 0.779 and accuracy of 69.6% on the external NLST validation cohort; a combined clinical-radiomics model slightly improved AUC to 0.802.

Automated summary

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