Evaluation of AI-derived LAD artery dose metrics for survival stratification in stage III NSCLC: A secondary analysis of RTOG 0617 trial.

Abstract

Background: While the radiation dose to left anterior descending (LAD) artery is associated with overall survival (OS) in NSCLC patients, manual segmentation is labor-intensive. Several auto-segmentation models were developed on average 4DCT with promising geometric agreement, yet their feasibility in clinical outcome analysis on lung CT remains unclear.

Purpose: This study evaluates whether automated LAD segmentation can reproduce, at the group level, the established dose-survival association in a multi-institutional clinical trial dataset.

Methods: Three deep learning-based auto-segmentation (DLAS) models for automatic segmentation of the LAD coronary artery were applied to 460 patients from the NRG Oncology/RTOG 0617 dataset. Kaplan-Meier curves and Cox proportional hazard ratio (HR) were calculated using each model's segmentation. The LAD V15 Gy was used to stratify patients into high-and low-risk groups, and the cut-off values were determined by minimizing mean absolute error (MAE) between DLAS-derived and manual OS curves.

Results: All three models demonstrated significantly different OS curves between the high risk and low risk groups (p < 0.05). The HR was 1.40 (95% CI: 1.02-1.93; p = 0.0381; MAE = 7.1%), 1.32 (95% CI: 1.03-1.68; p = 0.0258; MAE = 9.6%), and 1.37 (95% CI: 1.03-1.84; p = 0.0331; MAE = 7.9%) for the three models using a common V15 Gy ≥ 10% cut-off. After optimizing the cut-off, one model aligned well with what was derived from manual segmentation (MAE = 4.3%).

Conclusion: Among the evaluated models, one DL model showed the strongest performance of survival groups separation and achieved group-level overall survival stratification comparable to that previously reported using manual contours in the multi-institutional cohort. Further validation with paired manual contours and pre-specified cutoffs is warranted.